翻译下面的文档

翻译下面的文档

请说中文

请翻译下面我发的文档

18 IEEE INTERNET OF THINGS JOURNAL
committee of International Organization for Standard-
ization (ISO), World Wide Web Consortium (W3C)
International Telecommunication Union (ITU), Institute
of Electrical and Electronics Engineering (IEEE) and
Internet Engineering Task Force (IETF). ISO develops
standards for nomenclature, terminology, ontology and
architecture, privacy, identity, security, interoperability,
smart contracts, and Governance. The W3C is a stan-
dardization organization produced web standards and
they have started a community group for blockchain
to develop standards for message format, guidelines for
storage in private and public blockchain, torrent, and side
chain. The ITU has created a focus group on distributed
ledger technology (DLT) to recognize and examine the
services and applications of DLT, to create guidelines
and practices for the implementation of these services
and applications in the global market. IEEE has created
a project for blockchain; namely standardization initia-
tive for the blockchain framework in IoT. IETF defines
suite for Internet protocol for interoperability standards
and network communication for blockchain technologies
[126].
• Scalable Architectures: Skyline Queries are added ben-
efits in optimal dataset query processing. These queries
will help to retrieve the results from an optimal-related
set instead of searching the whole dataset. This, in
turn, reduces the data processing time and removes the
overhead in storing larger datasets [127]. The resource
management framework using blockchain proposed in
[128] alleviates the tremendous amount of energy con-
sumed by processing the explosive data accumulation at
the cloud data centers. Though edge computing offers
low latency response, edge nodes have a limited capacity,
which makes it difficult when the user demand increases
[129]. This leads to constrained access to IoT devices and
undetermined network latency. The virtual resources are
hosted on the edge nodes with blockchain for managing
these transactions [130]. Access control to the devices
is provided by blockchain through the management hub
[131] on the edge of the sensor networks. Furthermore,
these IoT devices are more vulnerable to various se-
curity attacks because of their resource constraints. So
a permission blockchain with Edge computing, namely
EdgeChain, was developed in [132].
2) Other Future Directions and Enabling Technologies:
Though multiple issues were solved in literature, the BEoT
should be compatible and upgraded itself for known and un-
known future problems. Therefore these challenges should be
addressed before the full-fledged adoption of BEoT. Some of
the future directions in the BEoT environment that evolves as
the technology advances are usability, cybersecurity, memory
management, Access control for resources and users, real-
time data stream delivery, and predictions on future trends
and patterns [133].
Enhancing Blockchain Performance for the Betterment of
BEoT: Though blockchain is secure, the blockchain security
issues discussed in terms of challenges and the vulnerabilities
imposed by ES and IoT devices will have a greater impact
on the future BEoT framework. Furthermore, the ability of
blockchain to store entire transaction data may create storage
burden leading to scalability issues. This ability of blockchain
consumes more energy, network bandwidth and thereby re-
ducing the throughput. As the IoT devices will be increasing
rapidly, the scalability and storage issues will significantly
impact the performance. Therefore a lightweight consensus
mechanism should be incorporated for blockchain mining
processes by segregating the appropriate data from the ledger
and storing it in side chains [122]. Also, data inconsistency
due to proliferation of nodes in the lightweight blockchain
will remain. Although skyline queries provide effective data
processing, data privacy still remains a baffling issue [127]. A
lightweight blockchain framework with efficient data process-
ing and service validation, alleviating the scalability issue will
be a research direction for future BEoT. Bigdata processing
systems will be an essential candidate to handle the enormous
data accumulations. Also, the bigdata processing will provide
effective processing of data in resource constrained ES to
ensure low latency response.
Integration of AI and BEoT: As BEoT lacks intelligence
required for predictive analysis in smart applications, AI will
provide a more sophisticated solution. AI aids the machines
to mimic the natural intelligence possessed by humans [134].
These intelligent agents (AI incorporated machine) were pro-
grammed to simulate the cognitive behavior of the human
and their brain, which is specifically utilized for solving
problems in real-time through experience (learning) [135]. AI
have bought remarkable automation in many domains utilizing
computational schemes. This led to the revolution of smart
computing systems. Some of them are robots in military
applications (mission-critical activities), health care assisted
robot in monitoring patients in the absence of surveillance,
automated transportation (anonymous operated autonomous
vehicles), gaming applications, content delivery network (rout-
ing), marketing (making all predictions on single search),
chatbots (online agent, a virtual assistant to handle customers)
in finance, agricultural robots, rovers in space research, and
social networking (predictive analysis).
The notable subsets of AI are ML and deep learning (DL),
the most significant technological advancements. Indeed, there
are numerous technical challenges in the BEoT paradigm that
can be assisted by the AI’s smartness. Privacy preservation is
the prominent issue in the mission-critical application of BEoT
standard. The study in [136] have suggested the integration of
AI at edge nodes aiming at the higher level of the privacy
to the users with fewer security vulnerabilities by alleviating
the use of third parties to mine the data at the edge. The
proposed model suggests the storage of processed data in
blocks instead of storing the raw data and retrieving it back
for processing later. Edge AI allows the end devices to control
all the mining processes through Ethereum smart contracts
(where the data owners can update their policies involved in
data processing and sharing) directly, which enables to reduce
considerable network bandwidth. Furthermore, they indicate
that data owners at the edge can process their data using
neural network algorithms and make valuable predictions as
IEEE INTERNET OF THINGS JOURNAL 1
Blockchain for Edge of Things:
Applications, Opportunities, and Challenges
Thippa Reddy Gadekallu, Quoc-Viet Pham, Dinh C. Nguyen, Praveen Kumar Reddy Maddikunta,
N Deepa, Prabadevi B, Pubudu N. Pathirana, Jun Zhao, and Won-Joo Hwang
Abstract—In recent years, blockchain networks have attracted
significant attention in many research areas beyond cryptocur-
rency, one of them being the Edge of Things (EoT) that is enabled
by the combination of edge computing and the Internet of Things
(IoT). In this context, blockchain networks enabled with unique
features such as decentralization, immutability, and traceability,
have the potential to reshape and transform the conventional EoT
systems with higher security levels. Particularly, the convergence
of blockchain and EoT leads to a new paradigm, called BEoT that
has been regarded as a promising enabler for future services and
applications. In this paper, we present a state-of-the-art review of
recent developments in BEoT technology and discover its great
opportunities in many application domains. We start our survey
by providing an updated introduction to blockchain and EoT
along with their recent advances. Subsequently, we discuss the
use of BEoT in a wide range of industrial applications, from
smart transportation, smart city, smart healthcare to smart home
and smart grid. Security challenges in BEoT paradigm are also
discussed and analyzed, with some key services such as access
authentication, data privacy preservation, attack detection, and
trust management. Finally, some key research challenges and
future directions are also highlighted to instigate further research
in this promising area.
Index Terms—Blockchain, Edge Computing, Internet of
Things, Edge of Things, Security, Industrial Applications.
I. INTRODUCTION
In recent years, we have witnessed rapid advances in Inter-
net of Things (IoT) empowered by the proliferation of mobile
devices such as smartphones, laptops, sensors, wearables, etc.
It is predicted that by 2030, the number of connected IoT
devices surpasses 500 million [1]. This tremendous expansion
of IoT is expected to create numerous applications and ser-
vices across different application domains, from entertainment
industry to mobile games and surveillance [2]–[4]. Such IoT
applications often require high computing resources to handle
Thippa Reddy Gadekallu, Praveen Kumar Reddy Maddikunta, N Deepa,
Prabadevi B are with the School of Information Technology and Engineering,
V ellore Institute of Technology, Tamilnadu, India (e-mail: {thippareddy.g,
praveenkumarreddy, deepa.rajesh, prabadevi.b}@vit.ac.in).
Quoc-Viet Pham (corresponding author) is with the Korean Southeast
Center for the 4th Industrial Revolution Leader Education, Pusan National
University, Busan 46241, Korea (e-mail: [email protected]).
Dinh C. Nguyen and Pubudu N. Pathirana are with the School of Engi-
neering, Deakin University, Waurn Ponds, VIC 3216, Australia, and also with
the Data61, CSIRO, Docklands, Melbourne, Australia (e-mail: {cdnguyen,
pubudu.pathirana}@deakin.edu.au).
Jun Zhao is with the School of Computer Science and Engineering,
Nanyang Technological University, 50 Nanyang Avenue, 639798 Singapore
(e-mail: [email protected]).
Won-Joo Hwang is with the Department of Biomedical Convergence
Engineering, Pusan National University, Yangsan 50612, Korea (e-mail:
[email protected]).
massive data generated from sensor devices with latency
requirements to provide time-sensitive customer services, like,
transportation and smart healthcare. Cloud computing can
support IoT devices in solving computation tasks, but high
transmission latency remains a challenge due to long distance
from the users. Edge computing has been recently proposed
to support IoT with the creation of Edge of Things (EoT)
networks, by migrating computing and storage to the edge
of the network, e.g., access points or base stations of radio
access networks [5]–[7]. In this regard, the computational
burden posed on resource-constrained IoT sensors can be
eliminated and the communication overhead is significantly
reduced while providing better computing experience for the
users. Therefore, EoT possess the ability to support location-
aware distributed IoT applications to facilitate time-sensitive
service delivery with reduced computation complexities [8].
The distributed nature of EoT introduces new security and
privacy challenges. The migration of large-scale computing
and storage services to the edge creates the possibility of
security threats and helps in controlling the network or prevent
attacks on the resources at edge nodes [9], [10]. Moreover,
uploading data to the network edge also raises critical data
privacy concerns such as data breaches, data attacks and
data modifications. Blockchain, a disruptive technology that
emerged in recent years, has been regarded as a promising
solution to solve security and privacy issues in edge computing
networks as well as empower the next generations of EoT tech-
nology [11]–[13]. In particular, the convergence of blockchain
and EoT creates a novel paradigm called BEoT, which re-
shapes and transforms the conventional edge-IoT networks to
enable new industrial and customer applications and services
[14], [15]. For example, BEoT has been used to provide secure
smart city services such as reliable vehicular management and
low-latency traffic control [16]. Further, BEoT has promoted
smart healthcare analytics and IoT medical processing due to
the large-scale computing and communication features of EoT
and security features of blockchain [17]. The convergence of
these emerging technologies is potentially a key enabler for
future services and applications.
A. BEoT Architecture
In this article, we propose a novel BEoT architecture that
is enabled by the use of blockchain in EoT, as illustrated in
Fig. 1. The proposed architecture consists of three main en-
tities; IoT, edge computing, blockchain, along with industrial
applications and BEoT security services.
arXiv:2110.05022v1 [cs.CR] 11 Oct 2021
IEEE INTERNET OF THINGS JOURNAL 19
the immutable nature of blockchain records all the transaction
involved in mining.
Labelling of datasets in AI empowers the model. It provides
better performance, but the traditional crowdsourcing (gener-
ating labels from the human input) is centralized and have
various issues such as data privacy and delayed processing.
Furthermore, training the DL models from the local edge
server requires larger storage and computing power, which
is not feasible with resource-constrained edge devices. The
training of models can be shifted to the cloud and can be
retrieved for the processing, which may lead to data privacy
issues. Therefore, Edgence, a framework proposed in [137]
provides decentralized crowdsourcing and decentralized AI
training with blockchains for secured and privacy-preserving
data transactions in decentralized IoT applications. Thus,
blockchain ensures the privacy of the data allowing the data
owners to negotiate their data usage by third parties and the
robust AI algorithms processing at the edge, thereby drastically
reducing the network latency and the load on a block in a
blockchain transaction. The survey in [138] have explored
the broader perspectives of blockchain and edge computing
applications. One of the more extensive areas addressed is
the contribution of AI in blockchain-based edge computing
applications and its benefits. With evidence from the literature,
they have suggested that AI will tremendously impact the
performance of BEoT, especially in resource management,
automatic generation of smart contracts, prediction of faults,
and scalable off-chain computation at the network edge.
In-edge AI framework in [139] was proposed for the effec-
tive utilization of the interaction among the mobile edge nodes
to train the AI models with a reduced computational load.
They have employed the DL techniques like DRL to attain
optimal caching at edge nodes with minimal computation
and federated learning for managing the resources effectively.
Furthermore, they suggest that the blockchain framework can
be integrated with this environment, but load distribution
among heterogeneous edge nodes remains unexplored and will
be a research direction.
Cognitive Edge: Cognitive edge is an interesting idea in the
edge computing space that utilizes the cognition from AI al-
gorithms for processing at the edge effectively. A blockchain-
based optimal knowledge paid sharing for AI-enabled edge
nodes was introduced in [140]. For effective knowledge ag-
gregation with reduced computational load, knowledge man-
agement chain and knowledge trading subchains are deployed.
ML algorithms are used for knowledge extraction. AI-enabled
edge nodes are priced for knowledge sharing due to their
imposed selfishness. The blockchain consortium based on
smart contracts uses knowledge coins for knowledge trading
among Edge AI nodes. This ensures tamper-resistant (knowl-
edge coins are stored in knowledge managers), decentralized
and very fair trading. The green blockchain Proof-of-Trading
combines the PoS and PoW for reduced resource consumption.
Thus the optimal pricing will encourage smooth knowledge
trading among buyers and sellers in AI edge nodes.
On the other hand, sharing the economy-related services in
smart environment, leverages computational load as well as
incurs the security burden. Sharing economy related services
and smart contracts have a tremendous impact on the mas-
sive BEoT crowd. Blockchain and AI-based cognitive edge
framework was designed in [72] for facilitating the sharing
economy-related service in a smart city. The proposed model
uses DL algorithms for extracting the meaningful and signifi-
cant event information from the IoT data. The framework uses
cognitive edge nodes for storing and processing the immutable
ledgers of blockchain and off-chain (includes the transactions
involving IIoT and mobile edge devices). The model integrates
the cognitive processing at the edge for sharing economy-
related services. AI is used for data processing and extract-
ing shareable economy-related data from heterogeneous IoT
devices, blockchain and social network media.
Furthermore, as the number of IoT devices in the smart
environment increases, the traffic generation will increase
tremendously leading to higher back-haul data rates. Intelligent
caching is performed to overcome this, by storing popular
contents at different locations of the network. But still, this
has a more significant challenge in decision making based on
future content popularity. This can be resolved with DL and re-
inforcement learning for significant decision making on cache
content prediction [54]. Therefore, when AI is integrated with
the BEoT environment, it reduces the computational power,
increases data processing rate and scalability, increases the
decision making in load management and intelligent caching,
and predicts any system attacks in advance. The major security
concerns and resource optimization with the use of blockchain
for EoT can be alleviated with the power of CE. All these
can be achieved without human intervention but through the
intelligent agents mimicking the human cognition. The greatest
challenge in this adoption is to focus on the effective training
of the AI models in heterogeneous environments. Because the
machine is trained through learning from previous experience,
but training or learning in a dynamically changing environment
is challenging and can impact the overall performance. One
of the most common solutions suggested in the literature is
retrieving information from all the heterogeneous nodes for
training the model, but its effectiveness is still unexplored and
paves a way for future research.
BEoT in 5G: The emerging 5G network is 20 times faster
than the current 4G LTE used in almost all cellular networks
[141]. It can carry a huge payload in a shorter duration by
its variety of spectrum bands. The scalable BEoT environ-
ment requires higher computational resources with low la-
tency response. Also, BEoT applications demand peer to peer
communication for its transactions, 5G has the more suitable
capabilities for hosting the BEoT. Both technologies drive each
other forward. As 5G sorts out the communication constraints
in blockchain and blockchain ensures the privacy concerns.
5G infrastructure crowdsourcing using smart contracts, 5G
infrastructure sharing (i.e., national roaming and spectrum
sharing) without a third party, the most challenging interna-
tional sharing, network slicing to accommodate multiple users
with seamless interaction, massive machine communication
and low-latency ultra-reliable communications. The massive
adoption of 5G with blockchain has particular hindrance
such as managing throughput with scalability, transforming
an enormous number of contracts in 5G into smart contracts,
2 IEEE INTERNET OF THINGS JOURNAL
Internet of Things
IoT
Devices IoT
Devices
IoT
Devices
Smart Transportation Smart City Smart Healthcare Smart Home Smart Grid
BEoT Security
Services
Trust
Management
Access
Authentication
Data Privacy
Attack
Detection
Edge Computing
Previous
Hash
Transactions
Block k+1
Block k
Previous
Hash
Transactions
...
...
Industrial Applications
Blockchain Network
Edge Server Edge Server Edge Server
Blockchain
Fig. 1: The generic architecture of BEoT.
• IoT: IoT devices such as sensors and mobile phones are
responsible for generating or gathering data from the
physical environments and then transmit to the nearby
edge servers (ES) via access points or base stations. IoT
devices with certain resources (e.g. smart phones, laptops)
can act as a mobile blockchain entity to make transactions
in order to communicate directly with the ES or even
join the blockchain mining for extra profits [18]. Other
lightweight IoT devices such as sensors can participate in
the blockchain network via their representative gateways
(e.g., mobile phones) or other mobile blockchain entities
in its IoT network [19].
• Edge computing: In order to reduce the transmission time,
it is necessary for computation nodes to perform data
processing near to the end user. Due to heavy network
traffic, cost of power consumption increases. To solve
these issues, edge computing came into existence. It
performs data storage and computing tasks in their edge
network within short distance to the end user [7]. As the
edge computing nodes are closer to the users, the traffic
flow is also reduced. It also minimizes the bandwidth
demands and latency in data storage and computation
in IoT network. In BEoT networks, IoT devices can
offload their data to the ES located at the base stations
for processing. ESs are typically equipped with rich
computing and storage resources to handle IoT data tasks
and provide data services for end users, ranging from
data analytics, data prediction to data mining and data
storage [20], [21]. Moreover, each ES can also work as
a blockchain miner that aims to verify the transactions
and produce data blocks for maintaining the blockchain
network.
• Blockchain: A blockchain is created to form the BEoT
system running on top of the EoT network, aiming to
interconnect IoT devices, ES and end users together in a
decentralized fashion. Particularly, blockchain can guar-
antee the reliable operations of BEoT systems without the
need of a central authority or third-party, by using some
key services such as data consensus, smart contracts, and
shared ledgers [22].
• Industrial applications: BEoT enable new industrial ap-
plications, thanks to the application of blockchain in EoT.
For example, in a BEoT-based smart transportation sys-
tem, the secure data analytic services at the edge vehicular
servers (i.e., roadside units) under the management of
blockchain can support fast traffic control and reliable
vehicle routing tasks even in the untrusted vehicular
environments [23]. In the following sections, we provide
a comprehensive discussion on the use of BEoT in various
industrial applications, from smart transportation, smart
20 IEEE INTERNET OF THINGS JOURNAL
need for regulatory compliance, privacy, cloud infrastructure
costs, and a trusted registration system [141]. Usually, the
more powerful 5G cellular network with edge computing is
integrated with AI for effective mining of big data accumulated
in the edge nodes as ineffective mining may degrade the
system performance. And blockchain cryptocurrencies namely,
bitcoin and litecoins can be utilized for the privacy-preserving
virtual transaction [142]. Also, the major cost incurred in
handling the cloud infrastructures can be reduced by using
Edge intelligence (edge computing with distributed AI). The
edge enabled 5G-blockchain-based infrastructure for schedul-
ing distributed heterogeneous edge resources was proposed in
[143].
The intelligent transportation framework in [144] was de-
veloped to address the reliable security scheme requirement
of the vehicular ad-hoc network (V ANET) with enhanced
vehicle trust management in traffic monitoring. 5G-VANET
with SDN is used to ensure the utmost reliability and global
traffic network control. The immutable ledger blockchain
with centralized authentication is used to secure the traffic
system from malicious vehicles (the vehicle that violates the
traffic rules and regulation) by creating hazardous traffic in
the network. Blockchain stores the vehicle details, traffic tag
details of its travel path and vehicular messages in the blocks.
Also, blockchain is utilized to offer trust management by
computing the trust value through the integration of PoW
and PoS. The simulation results guarantee the better privacy
preserved trust management for IoT vehicular networks. The
use of blockchain in 5G MEC unlocks the new business value,
brings new value shift, and captures this value in the telecom-
munication industry. The low-latency communications of 5G
are attained through edge computing. The privacy concerns in
heterogeneous MEC are solved by blockchain. The blockchain
is constructed to enhance user privacy as well as privacy
of network topologies (attained using accommodative bloom
filter without revealing the topology privacy by maintaining the
routing consensus) [145]. Their integration is fulcrum behind
the excellent results in 5G BEoT supply chain management
[100] and unmanned vehicular systems [146].
The summary of challenges, future directions, its application
and benefits of BEoT is described in Table V.
VI. CONCLUSION
In this article, we have conducted an extensive survey of the
use of blockchain in EoT networks and associated applications.
We have first introduced an overview of the blockchain and
EoT and discussed the main motivations behind the use of
blockchain in EoT networks. Furthermore, we have also pro-
vided a generic BEoT architecture where IoT, edge computing,
blockchain and succeeding applications and security services
have been analyzed. Subsequently, we have paid attention to
the review of the BEoT adoption in a number of important
industrial applications, including smart transportation, smart
city, smart healthcare, smart home, and smart grid. The secu-
rity benefits of the BEoT paradigm have been discussed, with
some key services such as access authentication, data privacy
preservation, attack detection, and trust management. Finally,
we have outlined some research challenges and pointed out
open research directions toward BEoT-5G networks. We be-
lieve that this article will instigate exemplary approaches on
BEoT research for future applications and services.
REFERENCES
[1] “Cisco edge-to-enterprise IoT analytics for electric utilities
solution overview,” 2020. [Online]. Available: https:
//www.cisco.com/c/en/us/solutions/collateral/data-center-virtualization/
big-data/solution-overview-c22-740248.html
[2] L. Da Xu, W. He, and S. Li, “Internet of Things in industries: A
survey,” IEEE Transactions on industrial informatics, vol. 10, no. 4,
pp. 2233–2243, 2014.
[3] S. R. Islam, D. Kwak, M. H. Kabir, M. Hossain, and K.-S. Kwak,
“The Internet of Things for health care: a comprehensive survey,” IEEE
Access, vol. 3, pp. 678–708, 2015.
[4] A. Al-Fuqaha, M. Guizani, M. Mohammadi, M. Aledhari, and
M. Ayyash, “Internet of Things: A survey on enabling technologies,
protocols, and applications,” IEEE communications surveys & tutorials,
vol. 17, no. 4, pp. 2347–2376, 2015.
[5] H. El-Sayed, S. Sankar, M. Prasad, D. Puthal, A. Gupta, M. Mohanty,
and C.-T. Lin, “Edge of things: the big picture on the integration of
edge, IoT and the cloud in a distributed computing environment,” IEEE
Access, vol. 6, pp. 1706–1717, 2017.
[6] W. Y u, F. Liang, X. He, W. G. Hatcher, C. Lu, J. Lin, and X. Yang,
“A survey on the edge computing for the Internet of Things,” IEEE
Access, vol. 6, pp. 6900–6919, 2017.
[7] L. Nkenyereye, J. Y . Hwang, Q.-V . Pham, and J. S. Song, “Virtual
IoT service slice functions for multi-access edge computing platform,”
IEEE Internet of Things Journal, vol. 8, no. 14, pp. 11 233–11 248,
2021.
[8] P . P . Ray, D. Dash, and D. De, “Edge computing for Internet of Things:
A survey, e-healthcare case study and future direction,” Journal of
Network and Computer Applications, vol. 140, pp. 1–22, 2019.
[9] A. Alrawais, A. Alhothaily, C. Hu, and X. Cheng, “Fog computing
for the Internet of Things: Security and privacy issues,” IEEE Internet
Computing, vol. 21, no. 2, pp. 34–42, 2017.
[10] K. Gai, M. Qiu, Z. Xiong, and M. Liu, “Privacy-preserving multi-
channel communication in edge-of-things,” Future Generation Com-
puter Systems, vol. 85, pp. 190–200, 2018.
[11] Q. Zhou, H. Huang, Z. Zheng, and J. Bian, “Solutions to scalability of
blockchain: A survey,” IEEE Access, vol. 8, pp. 16 440–16 455, 2020.
[12] W. Wang, D. T. Hoang, P . Hu, Z. Xiong, D. Niyato, P . Wang, Y . Wen,
and D. I. Kim, “A survey on consensus mechanisms and mining strategy
management in blockchain networks,” IEEE Access, vol. 7, pp. 22 328–
22 370, 2019.
[13] D. C. Nguyen, P . N. Pathirana, M. Ding, and A. Seneviratne,
“Blockchain for secure EHRs sharing of mobile cloud based e-health
systems,” IEEE Access, vol. 7, pp. 66 792–66 806, 2019.
[14] J. Pan, J. Wang, A. Hester, I. AlQerm, Y . Liu, and Y . Zhao, “Edgechain:
An edge-IoT framework and prototype based on blockchain and smart
contracts,” IEEE Internet of Things Journal, vol. 6, no. 3, pp. 4719–
4732, 2018.
[15] Y . Ren, F. Zhu, J. Qi, J. Wang, and A. K. Sangaiah, “Identity manage-
ment and access control based on blockchain under edge computing
for the industrial Internet of Things,” Applied Sciences, vol. 9, no. 10,
p. 2058, 2019.
[16] P . K. Sharma, S. Y . Moon, and J. H. Park, “Block-VN: A distributed
blockchain based vehicular network architecture in smart city.” Journal
of Information Processing Systems, vol. 13, no. 1, pp. 184–195, 2017.
[17] N. Islam, Y . Faheem, I. U. Din, M. Talha, M. Guizani, and M. Khalil,
“A blockchain-based fog computing framework for activity recognition
as an application to e-healthcare services,” Future Generation Com-
puter Systems, vol. 100, pp. 569–578, 2019.
[18] K. Suankaewmanee, D. T. Hoang, D. Niyato, S. Sawadsitang,
P . Wang, and Z. Han, “Performance analysis and application of
mobile blockchain,” in 2018 international conference on computing,
networking and communications (ICNC) Maui, Hawaii, USA, 2018,
pp. 642–646.
[19] I. Buldin, M. Gorodnichev, S. Makhrov, and E. Denisova, “Next
generation industrial blockchain-based wireless sensor networks,” in
2018 Wave Electronics and its Application in Information and Telecom-
munication Systems (WECONF) Sankt-Peterburg, Russian Federation,
2018, pp. 1–5.
IEEE INTERNET OF THINGS JOURNAL 3
city, smart healthcare to smart home and smart grid.
• Security services: Enabled by the inherent security prop-
erties such as decentralization, immutability, and trace-
ability, blockchains provide a number of important secu-
rity services for BEoT, including access authentication,
data privacy, attack detection, and trust management. The
analysis of such security services will be presented in
detail in later sections.
B. State of the Arts and Our Contributions
In the literature, many studies on blockchain and EoT
topics have been investigated. The works in [24]–[26] present
extensive surveys on the use of blockchain and IoT from
the different perspectives, spanning across various technical
concepts, architectures to research challenges. The potential
of blockchain networks in enabling IoT applications and
services has also been investigated in [27]. Moreover, the
possibility of combining blockchain and edge computing has
been investigated and surveyed in [28], [29]. The survey in
[30] briefly discusses the role of blockchain in edge computing
architectures.
Despite so many research efforts, we have found that a
comprehensive review of the use of blockchain in EoT is
still missing. Moreover, reviewing the state-of-the-art in the
field, BEoT has increasingly attracted much interest, both in
academics and industry with a growing number of applied
domains and use cases. Motivated by these, we provide an
extensive survey on the applications of blockchain in EoT,
ranging from applications, opportunities to research challenges
and future directions in this article. The key objective of
this article is to provide the readers with the state-of-the-
art on blockchain and EoT and the recent advances in the
BEoT technology. The key contributions of this survey are
highlighted as follows.

1. We provide a survey on the state of the art of the
   applications of blockchain in EoT networks, starting
   with an updated discussion on the recent developments
   of blockchain and EoT and highlighting the motivations
   of the use of blockchain in EoT. Moreover, a high-level
   BEoT architecture is also proposed and analysed.
2. The key part of this article is focused on the opportu-
   nities of BEoT in industrial applications. In this regard,
   we present an in-depth survey on the use of BEoT in
   various important application domains, including smart
   transportation, smart city, smart healthcare, smart home,
   and smart grid.
3. Furthermore, the security requirements of the BEoT
   paradigm are also investigated. In particular, we analyze
   the benefits of blockchain in providing key security ser-
   vices for EoT, such as access authentication, data privacy
   preservation, attack detection, and trust management.
4. Based on the extensive survey on the BEoT, we identify
   the potential research challenges and highlight some
   important future directions in BEoT.
   C. Structure of The Survey
   The remainder of the article is organized as follows. Sec-
   tion II describes the state-of-the-art in blockchain and EoT.
   TABLE I: ACRONYMS
   5G 5th Generation
   ACL Access Control Lists
   AI Artificial Intelligence
   DDoS Distributed Denial-of-Service
   DLT Distributed Ledger Technology
   DRL Deep Reinforcement Learning
   EDM Event-Driven Messages
   EDoS Economic Denial of Sustainability
   EHR Electronic Health Records
   EoT Edge of Things
   ES Edge Server
   ICT Information and Communication Technology
   IEEE Institute of Electrical and Electronics Engineering
   IETF Internet Engineering Task Force
   IIoT Industrial IoT
   IoT Internet of Things
   ISO International Organization for Standardization
   ITU International Telecommunication Union
   MEC Multi-access Edge Computing
   PoS Proof of Stake
   PoW Proof of Work
   SDN Software Defined Network
   SGN Smart Grid Network
   SHM Structural Health Monitoring
   SSS Secret Sharing Scheme
   SV Smart Vehicles
   UAV Unmanned Aerial Vehicle
   V2G Vehicle to Grid
   VANET Vehicular ad-hoc network
   VEC Vehicular Edge Computing
   The motivations of the use of blockchain in EoT are also
   highlighted. In Section III, we survey and analyze the recent
   development of BEoT technology in a wide range of indus-
   trial applications, including smart transportation, smart city,
   smart healthcare, smart home, and smart grid. The security
   opportunities due to BEoT paradigm are also presented and
   discussed in Section IV with some key services, such as access
   authentication, data privacy preservation, attack detection, and
   trust management. Section V provides some research chal-
   lenges and outlines some possible future directions in the
   BEoT. Finally, Section VI provides the concluding remarks
   on the core assertions of the paper. A list of key acronyms
   used throughout the paper is presented in Table I.
   II. BLOCKCHAIN AND EOT: STATE OF THE ART
   This section presents the background and recent develop-
   ments of blockchain, EoT, and highlights the motivations of
   the use of blockchain in EoT.
   A. Blockchain
   Since the inception of Bitcoin, there is a huge buzz about
   blockchain. A blockchain is a chain of blocks, which is
   decentralized and distributed that can store information about
   transactions [31]. Each block on the blockchain is linked to its
   immediately-previous block through a hash label. Specifically,
   a block in a blockchain can store the following information:
   (i) transaction details like time, date and value of transaction
   (ii) information about the person who is participating in the
   transactions and (iii) a unique hash code that differentiates a
   block from another block. For every transaction, a new block is
   created and added to the end of the blockchain. The blockchain
   IEEE INTERNET OF THINGS JOURNAL 21
   TABLE V: Challenges, Future Directions and Benefits of BEoT.
   Ref. Challenges Application Description Benefits
   [122] Massive real-time data stream-
   ing and storage overhead in the
   lightweight blockchain
   Smart home
   and surveillance
   systems
   Segregation of metadata through lightweight
   blockchain to scale down processing time and
   edge computing to reduce latency
   Acceptability, long-term sustainabil-
   ity and scalability
   [127] Inefficient mining process when the
   users are increased and skyline
   query processing in blockchain
   Any smart systems Energy-efficient consensus protocol design for
   mining the application-specific data to be
   stored on the ledger
   Scalability, robustness and faster data
   processing
   [128] Massive explosion of data will con-
   sume more energy and the cost will
   be higher
   Smart grid system Decentralized blockchain-based resource man-
   agement with embedded reinforcement learn-
   ing for request migration in smart contracts
   Cost minimization in energy con-
   sumption in power grids
   [129] Load distribution when the net-
   works scale up devices and safety
   loading
   Cloud-centric IoT Provisioning of virtual resources and permis-
   sioned blockchain for access control in edge
   nodes
   Low-latency response and secured
   transaction
   [130] Edge computing resource alloca-
   tion
   Mobile blockchain Number of entries in the block must be opti-
   mal, an economic model with optimal resource
   utilization
   Optimal resource utilization, low-
   latency and scalability
   Ref. Future direction Application Description Benefits
   [131] Global storage of different re-
   source access control details into
   the blockchain
   IoT devices in
   smart environment
   Decentralized blockchain where the access
   control policy of the entire system is stored
   in a single blockchain
   Scalability
   [132] On-demand resource provisioning
   to heterogeneous IoT devices
   Smart systems Permitted blockchain to link IoT devices and
   the resources on the edge nodes and credit
   (internal coins)-based resource management
   Scalability, secure auditing and data
   logging
   [136] BEoT mining at edge nodes by
   alleviating raw content in the block
   Edge AI for smart
   health care
   Edge AI is used for local decision making at
   edge nodes.
   Reduced network resource consump-
   tion at the edge
   [138] BEoT resource management and
   reinforced security management
   policies
   AI’s neural
   networks in
   blockchain
   ML and DL algorithms improve the efficacy
   of BEoT paradigm with reduced energy in
   distributed computation
   Scalable mining at the edge, low com-
   putation overhead and vulnerability
   analysis
   [139] MEC task offloading, resource
   management and load distribution
   when integrated with blockchain
   AI learning models
   in blockchain
   DRL to attain optimal caching at edge nodes
   with minimal computation and federated learn-
   ing for resource management
   Cognitive computing, effective task
   offloading and optimal edge caching
   [140] Knowledge trading for AI-based
   BEoT environment
   Knowledge gaining
   via. ML and DL
   Knowledge chain with sidechains is used
   for decentralized, tamper-resistant, confidential
   and fair pricing of AI-enabled edge nodes
   Aggregated resource management and
   fair knowledge pricing
   [141] Transforming an enormous number
   of contracts in 5G into smart con-
   tracts
   Blockchain for 5G System must ensure scalable transactions in
   handling numerous smart contracts with low
   cost and secured authentication mechanisms
   Scalability and standard regulatory
   compliance for blockchain
   [144] Trust management in SDN enabled
   5G vehicular adhoc network
   5G intelligent
   transportation
   system
   Blockchain assures privacy concerns in 5G
   with 5G with vehicle privacy and secured
   traffic monitoring
   Trust management and malicious
   node detection
   [143] Secure edge services under more
   complex industrial networks
   Blockchain with
   5G in IIoT
   A DRL algorithm is used for edge resource
   management (cross-domain sharing) in 5G be-
   yond IIoT applications
   Cross-domain resource sharing and
   scheduling, tamper-resistant resource
   management
   [146] Extracting untapped value in 5G
   MEC
   5G BEoT in supply
   chains and UA V
   Describes how blockchain absorbs the value
   created by the 5G MEC in the telecommuni-
   cation value chain
   Automated new business value cre-
   ation permanent, verifiable and trans-
   parent transactions
   [145] Privacy protection of MEC Trust management
   in diversified MEC
   Blockchain for ensuring user privacy and net-
   work privacy in multi-server collaboration
   Trusted routing in collaborative net-
   work and privacy in network topology
   [20] S. Garg, A. Singh, K. Kaur, G. S. Aujla, S. Batra, N. Kumar, and
   M. S. Obaidat, “Edge computing-based security framework for big
   data analytics in V ANETs,” IEEE Network, vol. 33, no. 2, pp. 72–81,

[21] S. Yi, Z. Hao, Q. Zhang, Q. Zhang, W. Shi, and Q. Li, “Lavea: Latency-
aware video analytics on edge computing platform,” in Proceedings of
the Second ACM/IEEE Symposium on Edge Computing, 2017, pp. 1–
13.
[22] D. C. Nguyen, P . N. Pathirana, M. Ding, and A. Seneviratne,
“Blockchain for 5G and beyond networks: A state of the art survey,”
Journal of Network and Computer Applications, p. 102693, 2020.
[23] H. Liu, Y . Zhang, and T. Yang, “Blockchain-enabled security in electric
vehicles cloud and edge computing,” IEEE Network, vol. 32, no. 3, pp.
78–83, 2018.
[24] M. A. Ferrag, M. Derdour, M. Mukherjee, A. Derhab, L. Maglaras,
and H. Janicke, “Blockchain technologies for the Internet of Things:
Research issues and challenges,” IEEE Internet of Things Journal,
vol. 6, no. 2, pp. 2188–2204, 2018.
[25] T. M. Fernández-Caramés and P . Fraga-Lamas, “A review on the use
of blockchain for the Internet of Things,” IEEE Access, vol. 6, pp.
32 979–33 001, 2018.
[26] H.-N. Dai, Z. Zheng, and Y . Zhang, “Blockchain for Internet of Things:
A survey,” IEEE Internet of Things Journal, vol. 6, no. 5, pp. 8076–
8094, 2019.
[27] M. Wu, K. Wang, X. Cai, S. Guo, M. Guo, and C. Rong, “A
comprehensive survey of blockchain: From theory to IoT applications
and beyond,” IEEE Internet of Things Journal, vol. 6, no. 5, pp. 8114–
8154, 2019.
[28] Z. Xiong, Y . Zhang, D. Niyato, P . Wang, and Z. Han, “When mobile
blockchain meets edge computing,” IEEE Communications Magazine,
vol. 56, no. 8, pp. 33–39, 2018.
[29] X. Lin, J. Li, J. Wu, H. Liang, and W. Yang, “Making knowledge
tradable in edge-AI enabled IoT: A consortium blockchain-based
efficient and incentive approach,” IEEE Transactions on Industrial
Informatics, vol. 15, no. 12, pp. 6367–6378, 2019.
[30] R. Yang, F. R. Y u, P . Si, Z. Yang, and Y . Zhang, “Integrated blockchain
and edge computing systems: A survey, some research issues and
challenges,” IEEE Communications Surveys & Tutorials, vol. 21, no. 2,
pp. 1508–1532, 2019.
[31] D. Yaga, P . Mell, N. Roby, and K. Scarfone, “Blockchain technology
overview,” National Institute of Standards and Technology, Tech. Rep.,
2018.
[32] K. Gai, Y . Wu, L. Zhu, Z. Zhang, and M. Qiu, “Differential privacy-
based blockchain for industrial internet-of-things,” IEEE Transactions
on Industrial Informatics, vol. 16, no. 6, pp. 4156–4165, 2019.
[33] M. Baza, N. Lasla, M. Mahmoud, G. Srivastava, and M. Abdallah,
“B-ride: Ride sharing with privacy-preservation, trust and fair payment
atop public blockchain,” IEEE Transactions on Network Science and
Engineering, vol. 8, no. 2, pp. 1214–1229, 2019.
[34] Q. Feng, D. He, S. Zeadally, M. K. Khan, and N. Kumar, “A survey
on privacy protection in blockchain system,” Journal of Network and
Computer Applications, vol. 126, pp. 45–58, 2019.
4 IEEE INTERNET OF THINGS JOURNAL
Genesis Block
Stakeholder's can view the data blocks
Public Key
IPFS Hash
Data Hash
Previous Hash
Block 1
Public Key
IPFS Hash
Data Hash
Previous Hash
Block 2
Public Key
IPFS Hash
Data Hash
Previous Hash
Block N
Fig. 2: Blockchain Architecture.
is transparent as all the transactions in the blockchain are
stored in a public blockchain and hence can be viewed by
anyone. To maintain the privacy of the users, instead of storing
their actual names or other information, the encrypted data
will be stored in the public blockchain [32], [33]. The block
in the blockchain contains the hash of the information in it
and also the hash of the block before it. Hence, blockchain is
often referred as a decentralized distributed ledger technology
[34], [35]. The general architecture of a blockchain is depicted
in Fig. 2. If a hacker intends to edit the transaction in a
blockchain, he has to modify hash of not only that block but
also every other hash following it which is nearly impossible.
This security property of blockchain makes it an ideal choice
for usage in many sectors like banking, insurance, government
services, supply chain management, etc. [36].
Unlike traditional systems which require a central authority
to verify and validate the transactions, the transactions in a
blockchain are verified and validated by “consensus protocol”.
A consensus algorithm is a mechanism where all the participat-
ing nodes in the blockchain network agree to the current state
of the blockchain [37]. Whenever a new block is created (by
transactions) it requires a consensus algorithm to be executed
so that all the nodes in the blockchain reach the consensus on
the current state of the blockchain. The consensus algorithm
is also executed when a new node is added to the blockchain.
In this way, consensus algorithms ensure the reliability of the
blockchain and also confirm each node in the blockchain as
trustworthy [38]. Some of the popular consensus algorithms
used today are Proof of Work (PoW), Practical Byzantine Fault
Tolerance, Proof of Stake, Proof of Burn, Proof of Capacity
[39], [40].
To ensure that the transactions meet the predefined terms
and conditions, smart contracts are executed on a blockchain.
A smart contract is a program that spans a few lines of code,
that are used to make sure that all the transactions follow
some kind of pre-agreements. Smart contracts ensure that
the transactions are trustworthy. Smart contracts reduce the
time which is otherwise spent on verifying the transactions.
Accurate decisions can be made quickly because of verifica-
tion of terms and conditions’ verification is automated [41].
The main reasons behind the popularity of blockchain are its
unique properties, including decentralization, immutability and
transparency.
• Decentralization: Before blockchain came into limelight,
a centralized entity used to store all the data and all
the interactions with the data is through this centralized
storage. The centralized systems have several pitfalls like
a single point of failure, vulnerability to attacks, etc.
These drawbacks in centralized systems can be overcome
by decentralized systems as every node in decentralized
system stores the information.
• Immutability: Due to consensus algorithms, the infor-
mation stored in the blockchain network is immutable.
This property of blockchain makes it an ideal solution
for usage in several sectors like finance, supply chain
management sectors, governance, etc. [42].
• Transparency: The technology used in the blockchain
is always open-source. Even the transactions in the
blockchain are transparent. The technology or the transac-
tions are secured even though they are transparent as long
as the majority of the blockchain network’s nodes have
to approve the modifications. User information is hidden
with the help of complex cryptography algorithms [43].
Even though there are many benefits, there are several key
problems with the application of blockchain in distributed
systems like IoT. A critical issue is the extensive energy
consumption and high network latency caused by running
consensus processes such as PoW in the blockchain. This
may hinder the applications of blockchain in distributed
EoT networks with resource-constrained IoT devices. Another
problem is the limited throughput of blockchain systems.
For example, Bitcoin can only process a maximum of four
transactions/second, and the throughput of Ethereum achieved
is about 20 transactions/second, while Visa can process up to
1667 transactions/second [44]. Moreover, security and privacy
are other concerns to be considered when applying blockchain
to EoT networks. For instance, a serious security bottleneck
such as 51% attack can prevent new transactions from gaining
confirmations and halt payments between service providers
and EoT users. Attackers can exploit this vulnerability to
deploy attacks, such as transaction modifications, data breach,
adversarial mining operations, all of which can degrade the
performance of blockchain networks and results in data pri-
vacy leakage issues. Some solutions have been proposed to
provide insights on solving these issues. The work in [45]
provides lightweight consensus mechanisms to enhance the
blockchain performance by compressing consensus storage
and designing lightweight block validation schemes, aiming
to simplify the blockchain mining process to achieve energy
savings and latency improvement. Another study in [46]
introduces a mining pool system called SmartPool to im-
prove transaction verification in blockchain mining to protect
data privacy and mitigate security bottlenecks, such as 51%
vulnerability, ensuring that the ledger cannot be hacked by
increasingly sophisticated attackers.
B. Edge of Things
With the improvement in communication technologies and
affordable hardware, there has been a rapid growth of smart
22 IEEE INTERNET OF THINGS JOURNAL
[35] A. D. Dwivedi, G. Srivastava, S. Dhar, and R. Singh, “A decentralized
privacy-preserving healthcare blockchain for IoT,” Sensors, vol. 19,
no. 2, p. 326, 2019.
[36] N. Deepa, Q.-V . Pham, D. C. Nguyen, S. Bhattacharya, P . B, T. R.
Gadekallu, P . K. R. Maddikunta, F. Fang, P . N. Pathirana et al., “A
survey on blockchain for big data: Approaches, opportunities, and
future directions,” arXiv preprint arXiv:2009.00858, 2020.
[37] J. Kang, Z. Xiong, D. Niyato, D. Ye, D. I. Kim, and J. Zhao, “Toward
secure blockchain-enabled internet of vehicles: Optimizing consensus
management using reputation and contract theory,” IEEE Transactions
on V ehicular Technology, vol. 68, no. 3, pp. 2906–2920, 2019.
[38] G. Kumar, R. Saha, M. K. Rai, R. Thomas, and T.-H. Kim, “Proof-of-
work consensus approach in blockchain technology for cloud and fog
computing using maximization-factorization statistics,” IEEE Internet
of Things Journal, vol. 6, no. 4, pp. 6835–6842, 2019.
[39] Y . Xiao, N. Zhang, W. Lou, and Y . T. Hou, “A survey of distributed
consensus protocols for blockchain networks,” IEEE Communications
Surveys & Tutorials, vol. 22, no. 2, pp. 1432–1465, 2020.
[40] S. Ma, Y . Deng, D. He, J. Zhang, and X. Xie, “An efficient nizk scheme
for privacy-preserving transactions over account-model blockchain,”
IEEE Transactions on Dependable and Secure Computing, vol. 18,
no. 2, pp. 641–651, 2020.
[41] S. Hakak, W. Z. Khan, G. A. Gilkar, M. Imran, and N. Guizani,
“Securing smart cities through blockchain technology: Architecture,
requirements, and challenges,” IEEE Network, vol. 34, no. 1, pp. 8–
14, 2020.
[42] E. Politou, F. Casino, E. Alepis, and C. Patsakis, “Blockchain mu-
tability: Challenges and proposed solutions,” IEEE Transactions on
Emerging Topics in Computing, 2019.
[43] Y . Zhang, C. Xu, J. Ni, H. Li, and X. S. Shen, “Blockchain-assisted
public-key encryption with keyword search against keyword guessing
attacks for cloud storage,” IEEE Transactions on Cloud Computing,
2019.
[44] “Integration of Blockchain and Cloud of Things: Architecture, Appli-
cations and Challenges,” IEEE Communications Surveys & Tutorials,
vol. 22, no. 4, pp. 2521–2549, 2020.
[45] L. Luu, Y . V elner, J. Teutsch, and P . Saxena, “Smartpool: Practical
decentralized pooled mining,” in 26th {USENIX} Security Symposium
({USENIX} Security 17), 2017, pp. 1409–1426.
[46] Y . Liu, K. Wang, Y . Lin, and W. Xu, “Lightchain: A lightweight
blockchain system for industrial Internet of Things,” IEEE Transactions
on Industrial Informatics, vol. 15, no. 6, pp. 3571–3581, 2019.
[47] Q.-V . Pham, F. Fang, V . N. Ha, M. J. Piran, M. Le, L. B. Le, W.-J.
Hwang, and Z. Ding, “A survey of multi-access edge computing in
5G and beyond: Fundamentals, technology integration, and state-of-
the-art,” IEEE Access, vol. 8, pp. 116 974–117 017, Jun. 2020.
[48] W. Z. Khan, E. Ahmed, S. Hakak, I. Yaqoob, and A. Ahmed, “Edge
computing: A survey,” Future Generation Computer Systems, vol. 97,
pp. 219–235, 2019.
[49] M. B. Mollah, M. A. K. Azad, and A. V asilakos, “Secure data sharing
and searching at the edge of cloud-assisted Internet of Things,” IEEE
Cloud Computing, vol. 4, no. 1, pp. 34–42, 2017.
[50] J. Zhao, Q. Li, Y . Gong, and K. Zhang, “Computation offloading
and resource allocation for cloud assisted mobile edge computing
in vehicular networks,” IEEE Transactions on V ehicular Technology,
vol. 68, no. 8, pp. 7944–7956, 2019.
[51] S. Chen, Z. Pang, H. Wen, K. Y u, T. Zhang, and Y . Lu, “Automated
labeling and learning for physical layer authentication against clone
node and sybil attacks in industrial wireless edge networks,” IEEE
Transactions on Industrial Informatics, vol. 17, no. 3, pp. 2041–2051,
2020.
[52] M. Alazab, M. Alazab, A. Shalaginov, A. Mesleh, and A. Awajan,
“Intelligent mobile malware detection using permission requests and
API calls,” Future Generation Computer Systems, vol. 107, pp. 509–
521, 2020.
[53] B. Hussain, Q. Du, B. Sun, and Z. Han, “Deep learning-based DDoS-
attack detection for cyber-physical system over 5G network,” IEEE
Transactions on Industrial Informatics, vol. 17, no. 2, pp. 860–870,
2020.
[54] L. U. Khan, I. Yaqoob, N. H. Tran, S. A. Kazmi, T. N. Dang, and
C. S. Hong, “Edge-computing-enabled smart cities: A comprehensive
survey,” IEEE Internet of Things Journal, vol. 7, no. 10, pp. 10 200–
10 232, 2020.
[55] J. Xie, H. Tang, T. Huang, F. R. Y u, R. Xie, J. Liu, and Y . Liu, “A survey
of blockchain technology applied to smart cities: Research issues and
challenges,” IEEE Communications Surveys & Tutorials, vol. 21, no. 3,
pp. 2794–2830, 2019.
[56] M. B. Mollah, J. Zhao, D. Niyato, Y . L. Guan, C. Y uen, S. Sun, K.-Y .
Lam, and L. H. Koh, “Blockchain for the internet of vehicles towards
intelligent transportation systems: A survey,” IEEE Internet of Things
Journal, vol. 8, no. 6, pp. 4157–4185, 2020.
[57] T. Jiang, H. Fang, and H. Wang, “Blockchain-based Internet of vehi-
cles: distributed network architecture and performance analysis,” IEEE
Internet of Things Journal, vol. 6, no. 3, pp. 4640–4649, 2018.
[58] C. Chen, T. Xiao, T. Qiu, N. Lv, and Q. Pei, “Smart-contract-
based economical platooning in blockchain-enabled urban Internet of
vehicles,” IEEE Transactions on Industrial Informatics, vol. 16, no. 6,
pp. 4122–4133, 2019.
[59] X. Huang, D. Ye, R. Y u, and L. Shu, “Securing parked vehicle assisted
fog computing with blockchain and optimal smart contract design,”
IEEE/CAA Journal of Automatica Sinica, vol. 7, no. 2, pp. 426–441,
2020.
[60] J. Kang, R. Y u, X. Huang, M. Wu, S. Maharjan, S. Xie, and Y . Zhang,
“Blockchain for secure and efficient data sharing in vehicular edge
computing and networks,” IEEE Internet of Things Journal, vol. 6,
no. 3, pp. 4660–4670, 2018.
[61] A. Buzachis, A. Celesti, A. Galletta, M. Fazio, G. Fortino, and M. Vil-
lari, “A multi-agent autonomous intersection management (MA-AIM)
system for smart cities leveraging Edge-of-Things and blockchain,”
Information Sciences, vol. 522, pp. 148–163, 2020.
[62] V . C. Gungor, D. Sahin, T. Kocak, S. Ergut, C. Buccella, C. Cecati, and
G. P . Hancke, “Smart grid technologies: Communication technologies
and standards,” IEEE transactions on Industrial informatics, vol. 7,
no. 4, pp. 529–539, 2011.
[63] M. Alazab, S. Khan, S. S. R. Krishnan, Q.-V . Pham, M. P . K. Reddy,
and T. R. Gadekallu, “A multidirectional lstm model for predicting the
stability of a smart grid,” IEEE Access, vol. 8, pp. 85 454–85 463, 2020.
[64] A. K. Bashir, S. Khan, B. Prabadevi, N. Deepa, W. S. Alnumay, T. R.
Gadekallu, and P . K. R. Maddikunta, “Comparative analysis of machine
learning algorithms for prediction of smart grid stability,” International
Transactions on Electrical Energy Systems, vol. 39, no. 9, p. e12706.
[65] Y . Zhang, W. Chen, and W. Gao, “A survey on the development status
and challenges of smart grids in main driver countries,” Renewable and
Sustainable Energy Reviews, vol. 79, pp. 137–147, 2017.
[66] Q.-V . Pham, M. Liyanage, N. Deepa, M. VVSS, S. Reddy, P . K. R.
Maddikunta, N. Khare, T. R. Gadekallu, W.-J. Hwang et al., “Deep
learning for intelligent demand response and smart grids: A compre-
hensive survey,” arXiv preprint arXiv:2101.08013, 2021.
[67] A. Jindal, G. S. Aujla, and N. Kumar, “Survivor: A blockchain based
edge-as-a-service framework for secure energy trading in SDN-enabled
vehicle-to-grid environment,” Computer Networks, vol. 153, pp. 36–48,
2019.
[68] Z. Zhou, B. Wang, M. Dong, and K. Ota, “Secure and efficient
vehicle-to-grid energy trading in cyber physical systems: Integration
of blockchain and edge computing,” IEEE Transactions on Systems,
Man, and Cybernetics: Systems, vol. 50, no. 1, pp. 43–57, 2019.
[69] J. Wang, L. Wu, K. R. Choo, and D. He, “Blockchain-based anonymous
authentication with key management for smart grid edge computing
infrastructure,” IEEE Transactions on Industrial Informatics, vol. 16,
no. 3, pp. 1984–1992, 2020.
[70] R. Vinayakumar, M. Alazab, S. Srinivasan, Q.-V . Pham, S. K. Padan-
nayil, and K. Simran, “A visualized botnet detection system based deep
learning for the Internet of Things networks of smart cities,” IEEE
Transactions on Industry Applications, vol. 56, no. 4, pp. 4436–4456,
2020.
[71] D. Nagothu, R. Xu, S. Y . Nikouei, and Y . Chen, “A microservice-
enabled architecture for smart surveillance using blockchain technol-
ogy,” in 2018 IEEE International Smart Cities Conference (ISC2),
Kansas City, Missouri, USA, 2018, pp. 1–4.
[72] M. A. Rahman, M. M. Rashid, M. S. Hossain, E. Hassanain, M. F.
Alhamid, and M. Guizani, “Blockchain and IoT-based cognitive edge
framework for sharing economy services in a smart city,” IEEE Access,
vol. 7, pp. 18 611–18 621, 2019.
[73] D. Bruneo, S. Distefano, M. Giacobbe, A. L. Minnolo], F. Longo,
G. Merlino, D. Mulfari, A. Panarello, G. Patanè, A. Puliafito, C. Pu-
liafito, and N. Tapas, “An IoT service ecosystem for smart cities: The
#SmartME project,” Internet of Things, vol. 5, pp. 12 – 33, 2019.
[74] P . K. Sharma and J. H. Park, “Blockchain based hybrid network
architecture for the smart city,” Future Generation Computer Systems,
vol. 86, pp. 650–655, 2018.
[75] I. Makhdoom, I. Zhou, M. Abolhasan, J. Lipman, and W. Ni,
“Privysharing: A blockchain-based framework for privacy-preserving
and secure data sharing in smart cities,” Computers & Security, vol. 88,
p. 101653, 2020.
IEEE INTERNET OF THINGS JOURNAL 5
devices in many areas of daily life and business activities
in the past two decades. As information and communication
technology (ICT) became affordable, there is an enormous
surge in the data generated by mobile phones, IoT devices,
industries. The volume of data generated resulted in the use
of cloud for storage and computational purposes [47]. Storage
and data processing in the cloud have their own challenges
like latency, throughput, security, etc. For instance, storage and
data processing in real time applications like traffic monitoring
in the cloud may not be feasible due to increased latency
[47]. The solution to this problem lies in edge computing,
i.e., offloading the cloud-computing capabilities to the network
edge [47]–[49].
EoT is the integration of edge computing with IoT networks.
In EoT, the data acquired by several sensors is temporarily
stored in the edge node for real time analytics and predictions
[50]. The general architecture of EoT is depicted in Fig. 3.
Typically, the data generated from sensors in several IoT
applications like smart homes/buildings, smart grids, smart
healthcare, smart transportation, industrial IoT, etc. is stored
in edge nodes at regular time intervals. Once the data is
processed in the edge nodes it will be dissipated to the cloud.
Apart from improved latency, EoT offers several other benefits
like reduction of traffic to the cloud, improved reliability by
installation of applications in close proximity to the edge
devices, etc.
C. Motivations of the use of Blockchain in EoT
Even though multi-access edge computing is a promis-
ing solution for improved services of mobile providers, the
security of the data in the edge nodes is a concern [51].
Several applications like connected vehicles, social media
apps, healthcare related applications generate the data which
is very sensitive [52]. The privacy, confidentiality and integrity
of these data have to be strictly maintained. The hackers
can even attack the Multi-access edge computing (MEC)
with several attacks like distributed denial-of-service (DDoS)
attacks, hijacking of cloud servers, ripple attacks, byzantine
attacks, injection attacks, etc. to steal the sensitive data from
the edge or deny services to the users [53]. Several smart
city-based applications such as smart homes, smart grids that
generate sensitive data use edge nodes for real time analytics,
with a fast throughput. Several industry 4.0 applications also
use MEC for analytics in real time [54]. Several applications
based on user location like Google Maps, artificial intelligence
(AI) based Virtual Assistants use MEC for less latency and
predictions/recommendations through machine learning (ML)
based algorithms. All the applications mentioned above gen-
erate sensitive data of the users such as personal data, health,
location, utility services, etc. may possess an elevated risk of
compromised security. The properties of blockchain such as
distributed nature, traceability, immutability make it an ideal
solution to overcome the potential aforementioned problems
by applications based on MEC. Blockchain has the ability to
prevent issues like identity theft, DDoS attacks, tampering of
transactions, user privacy leakages. The use of blockchain in
EoT has the potential to be the next revolution in ICT where
the mobile application providers can provide safe, transparent,
immutable, decentralized applications to the customers with
reduced latency, and real-time analytics/recommendations.
The main motivations behind the use of blockchain in EoT
are summarized as follows:
• The distributed architectures of EoT will provide a better
roof for storing and verifying blockchain transactions.
• By using blockchain, data privacy and security can be
well preserved in blockchain-enabled EoT applications.
• The immutability and traceability features of blockchain
can be leveraged to ensure the reliability of the transac-
tions in industrial applications such as smart grid, smart
transportation, smart health care, government services etc.
• The consensus mechanism of the blockchain guarantees
the trustworthiness and transparency of information trans-
ferred over the BEoT network.
• The application of blockchain in EoT ensures low-latency
response which is increasingly vital for most of the
industrial applications.
III. INDUSTRIAL APPLICATIONS FROM BEOT PARADIGM
This section presents the industrial applications of the BEoT
paradigm highlighting some key benefits. Blockchain with
EoT helps to modernize the large computer networks by
providing smart architecture to various application domains
such as smart transportation, smart grid, smart city, smart
healthcare and smart home. These benefits attained through
BEoT in aforementioned industrial applications are depicted
in Fig. 4.
A. Smart Transportation
The term smart refers to the idea which helps to build
an environment connected with sensors and other computing
facilities for better understanding and controlling the user
environment. Smart vehicles (SV) have garnered significant
attention in recent times due to the advancement of ICT.
Smart transportation system enables SVs to get connected
to the Internet to access the required data and communicate
with each other. The aim of smart transportation system is to
provide convenience and comfort to passengers and drivers. It
also helps to improve the traffic efficiently and ensures road
safety. Vehicles are connected to various network interfaces
like WiMax, Bluetooth, and WiFi to communicate with road
side units and other vehicles in smart transportation system
[55], [56].
Smart transportation systems play a major role in the
development of smart cities to keep track of traffic data
and to avoid congestion, pollution, accidents etc. Due to
the increase in the traffic data, the conventional centralized
approach has faced many non-trivial challenges like storage of
data, server failure, security, intelligent management etc. If the
central server fails, the entire traffic system will be collapsed.
Hence a decentralized solution is highly needed. The work
in [57] solved the problem by proposing a network model
and a blockchain architecture. In this model, the blockchain is
integrated with vehicular networking application to provide
security and distributed storage for large amounts of data.
IEEE INTERNET OF THINGS JOURNAL 23
[76] B. W. Jo, R. M. A. Khan, and Y .-S. Lee, “Hybrid blockchain and
Internet-of-Things network for underground structure health monitor-
ing,” Sensors, vol. 18, no. 12, p. 4268, 2018.
[77] N. Deepa, B. Prabadevi, P . K. Maddikunta, T. R. Gadekallu, T. Baker,
M. A. Khan, and U. Tariq, “An AI-based intelligent system for
healthcare analysis using Ridge-Adaline stochastic gradient descent
classifier,” Journal of Supercomputing, vol. 77, pp. 1998–2017, 2021.
[78] T. R. Gadekallu, N. Khare, S. Bhattacharya, S. Singh, P . K. R.
Maddikunta, and G. Srivastava, “Deep neural networks to predict
diabetic retinopathy,” J. Ambient Intell. Humaniz. Comput, pp. 1–14,
2020.
[79] R. Gupta, S. Tanwar, S. Tyagi, N. Kumar, M. S. Obaidat, and
B. Sadoun, “Habits: Blockchain-based telesurgery framework for
healthcare 4.0,” in 2019 International Conference on Computer , In-
formation and Telecommunication Systems (CITS). IEEE, 2019, pp.
1–5.
[80] A. Islam and S. Y . Shin, “A blockchain-based secure healthcare scheme
with the assistance of unmanned aerial vehicle in Internet of Things,”
Computers & Electrical Engineering, vol. 84, p. 106627, 2020.
[81] R. Ch, G. Srivastava, T. R. Gadekallu, P . K. R. Maddikunta, and
S. Bhattacharya, “Security and privacy of UA V data using blockchain
technology,” Journal of Information Security and Applications, vol. 55,
p. 102670, 2020.
[82] M. A. Rahman, M. S. Hossain, G. Loukas, E. Hassanain, S. S. Rahman,
M. F. Alhamid, and M. Guizani, “Blockchain-based mobile edge
computing framework for secure therapy applications,” IEEE Access,
vol. 6, pp. 72 469–72 478, 2018.
[83] H. Guo, W. Li, M. Nejad, and C.-C. Shen, “Access control for
electronic health records with hybrid blockchain-edge architecture,”
in 2019 IEEE International Conference on Blockchain (Blockchain),
Atlanta, USA, 2019, pp. 44–51.
[84] M. A. Rahman, E. Hassanain, M. M. Rashid, S. J. Barnes, and M. S.
Hossain, “Spatial blockchain-based secure mass screening framework
for children with dyslexia,” IEEE Access, vol. 6, pp. 61 876–61 885,
2018.
[85] Y . Lee, S. Rathore, J. H. Park, and J. H. Park, “A blockchain-based
smart home gateway architecture for preventing data forgery,” Human-
centric Computing and Information Sciences, vol. 10, no. 1, pp. 1–14,
2020.
[86] C. Lin, D. He, N. Kumar, X. Huang, P . Vijaykumar, and K.-K. R. Choo,
“Homechain: A blockchain-based secure mutual authentication system
for smart homes,” IEEE Internet of Things Journal, vol. 7, no. 2, pp.
818–829, 2019.
[87] P . V erma and S. K. Sood, “Fog assisted-IoT enabled patient health
monitoring in smart homes,” IEEE Internet of Things Journal, vol. 5,
no. 3, pp. 1789–1796, 2018.
[88] P . Li, C. Xu, H. Jin, C. Hu, Y . Luo, Y . Cao, J. Mathew, and Y . Ma,
“ChainSDI: A software-defined infrastructure for regulation-compliant
home-based healthcare services secured by blockchains,” IEEE Systems
Journal, vol. 14, no. 2, pp. 2042–2053, 2019.
[89] M. Numan, F. Subhan, W. Z. Khan, S. Hakak, S. Haider, G. T.
Reddy, A. Jolfaei, and M. Alazab, “A systematic review on clone node
detection in static wireless sensor networks,” IEEE Access, vol. 8, pp.
65 450–65 461, 2020.
[90] X. Xu, Q. Liu, Y . Luo, K. Peng, X. Zhang, S. Meng, and L. Qi, “A
computation offloading method over big data for IoT-enabled cloud-
edge computing,” Future Generation Computer Systems, vol. 95, pp.
522–533, 2019.
[91] N. Tariq, M. Asim, F. Al-Obeidat, M. Zubair Farooqi, T. Baker,
M. Hammoudeh, and I. Ghafir, “The security of big data in fog-enabled
IoT applications including blockchain: a survey,” Sensors, vol. 19,
no. 8, p. 1788, 2019.
[92] X. Xu, X. Zhang, H. Gao, Y . Xue, L. Qi, and W. Dou, “Become:
Blockchain-enabled computation offloading for IoT in mobile edge
computing,” IEEE Transactions on Industrial Informatics, vol. 16,
no. 6, pp. 4187–4195, 2019.
[93] N. Neshenko, E. Bou-Harb, J. Crichigno, G. Kaddoum, and N. Ghani,
“Demystifying IoT security: an exhaustive survey on IoT vulnerabilities
and a first empirical look on internet-scale IoT exploitations,” IEEE
Communications Surveys & Tutorials, vol. 21, no. 3, pp. 2702–2733,
2019.
[94] A. Singh, R. M. Parizi, Q. Zhang, K.-K. R. Choo, and A. Dehghan-
tanha, “Blockchain smart contracts formalization: Approaches and
challenges to address vulnerabilities,” Computers & Security, vol. 88,
p. 101654, 2020.
[95] E. Sisinni, A. Saifullah, S. Han, U. Jennehag, and M. Gidlund, “In-
dustrial Internet of Things: Challenges, opportunities, and directions,”
IEEE Transactions on Industrial Informatics, vol. 14, no. 11, pp. 4724–
4734, 2018.
[96] A. Savelyev, “Copyright in the blockchain era: Promises and chal-
lenges,” Computer law & security review, vol. 34, no. 3, pp. 550–561,
2018.
[97] R. Chaudhary, A. Jindal, G. S. Aujla, S. Aggarwal, N. Kumar, and
K.-K. R. Choo, “Best: Blockchain-based secure energy trading in
SDN-enabled intelligent transportation system,” Computers & Security,
vol. 85, pp. 288–299, 2019.
[98] S. Guo, X. Hu, S. Guo, X. Qiu, and F. Qi, “Blockchain meets edge
computing: A distributed and trusted authentication system,” IEEE
Transactions on Industrial Informatics, vol. 16, no. 3, pp. 1972–1983,
2020.
[99] K. Mahmood, X. Li, S. A. Chaudhry, H. Naqvi, S. Kumari, A. K.
Sangaiah, and J. J. Rodrigues, “Pairing based anonymous and secure
key agreement protocol for smart grid edge computing infrastructure,”
Future Generation Computer Systems, vol. 88, pp. 491–500, 2018.
[100] S. Jangirala, A. K. Das, and A. V . V asilakos, “Designing secure
lightweight blockchain-enabled RFID-based authentication protocol for
supply chains in 5G mobile edge computing environment,” IEEE
Transactions on Industrial Informatics, vol. 16, no. 11, pp. 7081–7093,
2019.
[101] H. Liu, P . Zhang, G. Pu, T. Yang, S. Maharjan, and Y . Zhang,
“Blockchain empowered cooperative authentication with data trace-
ability in vehicular edge computing,” IEEE Transactions on V ehicular
Technology, vol. 69, no. 4, pp. 4221–4232, 2020.
[102] H. Liu, Y . Zhang, and T. Yang, “Blockchain-enabled security in electric
vehicles cloud and edge computing,” IEEE Network, vol. 32, no. 3, pp.
78–83, 2018.
[103] J. Kang, R. Y u, X. Huang, M. Wu, S. Maharjan, S. Xie, and Y . Zhang,
“Blockchain for secure and efficient data sharing in vehicular edge
computing and networks,” IEEE Internet of Things Journal, vol. 6,
no. 3, pp. 4660–4670, 2018.
[104] O. Alkadi, N. Moustafa, B. Turnbull, and K.-K. R. Choo, “A deep
blockchain framework-enabled collaborative intrusion detection for
protecting IoT and cloud networks,” IEEE Internet of Things Journal,
vol. 8, no. 12, pp. 9463–9472, 2020.
[105] D. He, N. Kumar, S. Zeadally, A. Vinel, and L. T. Yang, “Efficient
and privacy-preserving data aggregation scheme for smart grid against
internal adversaries,” IEEE Transactions on Smart Grid, vol. 8, no. 5,
pp. 2411–2419, 2017.
[106] K. Gai, Y . Wu, L. Zhu, Z. Zhang, and M. Qiu, “Differential privacy-
based blockchain for industrial internet-of-things,” IEEE Transactions
on Industrial Informatics, vol. 16, no. 6, pp. 4156–4165, 2020.
[107] D. He, N. Kumar, and J.-H. Lee, “Privacy-preserving data aggregation
scheme against internal attackers in smart grids,” Wireless Networks,
vol. 22, no. 2, pp. 491–502, 2016.
[108] K. Gai, Y . Wu, L. Zhu, L. Xu, and Y . Zhang, “Permissioned blockchain
and edge computing empowered privacy-preserving smart grid net-
works,” IEEE Internet of Things Journal, vol. 6, no. 5, pp. 7992–8004,
2019.
[109] J. Wan, J. Li, M. Imran, and D. Li, “A blockchain-based solution for
enhancing security and privacy in smart factory,” IEEE Transactions
on Industrial Informatics, vol. 15, no. 6, pp. 3652–3660, 2019.
[110] G.-Y . Lin, S. He, H. Huang, J.-Y . Wu, and W. Chen, “Access control
security model based on behavior in cloud computing environment,”
Journal of China Institute of Communications, vol. 33, no. 3, pp. 59–
66, 2012.
[111] C. K. Pyoung and S. J. Baek, “Blockchain of finite-lifetime blocks
with applications to edge-based IoT,” IEEE Internet of Things Journal,
vol. 7, no. 3, pp. 2102–2116, 2019.
[112] G. Singh, A. Singh, M. Singh, S. Sharma, N. Kumar, and K.-K. R.
Choo, “BloCkEd: blockchain-based secure data processing framework
in edge envisioned V2X environment,” IEEE Transactions on V ehicular
Technology, vol. 69, no. 6, pp. 5850–5863, 2020.
[113] D. V . Medhane, A. K. Sangaiah, M. S. Hossain, G. Muhammad, and
J. Wang, “Blockchain-enabled distributed security framework for next
generation IoT: An edge-cloud and software defined network integrated
approach,” IEEE Internet of Things Journal, vol. 7, no. 7, pp. 6143–
6149, 2020.
[114] Y . Pu, C. Hu, S. Deng, and A. Alrawais, “Rpeds: A recoverable and
revocable privacy-preserving edge data sharing scheme,” IEEE Internet
of Things Journal, vol. 7, no. 9, pp. 8077–8089, 2020.
[115] L. Nkenyereye, B. Adhi Tama, M. K. Shahzad, and Y .-H. Choi,
“Secure and blockchain-based emergency driven message protocol for
5G enabled vehicular edge computing,” Sensors, vol. 20, no. 1, p. 154,
2020.
6 IEEE INTERNET OF THINGS JOURNAL
Industrial IoT Smart Transportation
Smart HeathcareSmart Buildings
Edge Edge
Edge Edge
Cloud Storage
Analytics Analytics
Analytics
Fig. 3: Architecture of EoT.
Several edge nodes are defined in the vehicle networks such
as roadside vehicle and they form sub-blockchain networks.
Data blocks in IoV are classified to form several blockchain
networks in IoV system.
A platoon driving model was proposed for autonomous
vehicles in an urban heavy traffic scenario to avoid congestion,
accidents, and pollution. This model groups the vehicles by
matching the path successfully in a platoon. Blockchain is
integrated in this model in which smart contract is applied
for payment purposes which helps in overcoming false and
malicious payment transactions. The results proved that the
platoon model performed well for individual vehicle models
with respect to fuel consumption [58]. Parked vehicle assisted
fog computing chain (PVFC) was introduced to accomplish
decentralization using blockchain with smart contracts. Also,
smart contract design was investigated to monitor the requester
and performer behavior with high end privacy and security
[59].
Smart transportation applications such as self driving cars
produce large amounts of data of different types. To ensure
safe driving, sharing of data is required to provide quality
service while travelling. Due to lack of resources, vehicular
network cannot provide huge data storage and data sharing.
A distributed and secure vehicular blockchain was presented
by exploiting blockchain consortium for the management of
secure data in vehicular edge computing and networks [60].
A multi-agent, autonomous, and intelligent management
system was presented in [61] for the safety of the vehicles
passing through an intersection point. The system constructed
using BEoT enables the communication between vehicle-to-
infrastructure and infrastructure-to-vehicle. The system inter-
acts with the vehicles in EoT environment and blockchain
ensures the safety of pedestrians and drivers passing through
the intersection point. The system helps to reduce the waiting
and crossing time of the vehicles and ensures security and re-
liability. Blockchain supports reliability with decentralization
and security by protecting the decisions taken from malicious
attacks. EoT helps in increasing the network performance,
thereby reducing the latency .
B. Smart Grid
Electricity is one of the greatest inventions, without which
today’s digital advancements are impossible. Also, the electric-
ity usage increases steadily causing the production to increase.
Traditional electrical grids use a centralized structure with
millions of components such as power stations, substations,
transmission lines and the distribution lines. It cannot accom-
modate new resource (increasing the load) as it may incur
additional overhead leading to power quality issues, i.e. new
plants have to be deployed whenever the load is increased.
Also, the conventional grid doesn’t have a proper prediction
system on power blackout, slower response time, insufficient
storage and not efficient use of resources. Smart grid overlays
the way for smart utilization of the electricity with fewer power
outages and lower computational overheads [62]–[64]. The
smart grid comprises of smart meters assisted with mobile
apps for real-time monitoring of power consumption, electric
vehicles (EV), on-demand pricing capability, microgrid, stor-
age, decision support systems, and other smart devices. Smart
power grids with its decentralized, distributed framework can
strengthen the electrical power of a country through the
effective utilization of renewable power resources and con-
temporary communication advancements. Consequently, this
24 IEEE INTERNET OF THINGS JOURNAL
[116] Y . Dai, D. Xu, K. Zhang, S. Maharjan, and Y . Zhang, “Deep rein-
forcement learning and permissioned blockchain for content caching
in vehicular edge computing and networks,” IEEE Transactions on
V ehicular Technology, vol. 69, no. 4, pp. 4312–4324, 2020.
[117] M. Zhaofeng, W. Xiaochang, D. K. Jain, H. Khan, G. Hongmin, and
W. Zhen, “A blockchain-based trusted data management scheme in
edge computing,” IEEE Transactions on Industrial Informatics, vol. 16,
no. 3, pp. 2013–2021, 2019.
[118] L. Xiao, Y . Ding, D. Jiang, J. Huang, D. Wang, J. Li, and H. V . Poor,
“A reinforcement learning and blockchain-based trust mechanism for
edge networks,” IEEE Transactions on Communications, vol. 68, no. 9,
pp. 5460–5470, 2020.
[119] L. Cui, S. Yang, Z. Chen, Y . Pan, Z. Ming, and M. Xu, “A decentralized
and trusted edge computing platform for Internet of Things,” IEEE
Internet of Things Journal, vol. 7, no. 5, pp. 3910–3922, 2019.
[120] I.-H. Chuang, S.-H. Huang, W.-C. Chao, J.-S. Tsai, and Y .-H. Kuo,
“TIDES: A trust-aware IoT data economic system with blockchain-
enabled multi-access edge computing,” IEEE Access, vol. 8, pp.
85 839–85 855, 2020.
[121] J. B. Bernabe, J. L. Canovas, J. L. Hernandez-Ramos, R. T. Moreno,
and A. Skarmeta, “Privacy-preserving solutions for blockchain: review
and challenges,” IEEE Access, vol. 7, pp. 164 908–164 940, 2019.
[122] M. Moniruzzaman, S. Khezr, A. Yassine, and R. Benlamri, “Blockchain
for smart homes: Review of current trends and research challenges,”
Computers & Electrical Engineering, vol. 83, p. 106585, 2020.
[123] X. Xu, Z. Zeng, S. Yang, and H. Shao, “A novel blockchain framework
for industrial IoT edge computing,” Sensors, vol. 20, no. 7, p. 2061,
2020.
[124] T. Salman, M. Zolanvari, A. Erbad, R. Jain, and M. Samaka, “Security
services using blockchains: A state of the art survey,” IEEE Commu-
nications Surveys & Tutorials, vol. 21, no. 1, pp. 858–880, 2018.
[125] U. Jayasinghe, G. M. Lee, Á. MacDermott, and W. S. Rhee,
“Trustchain: a privacy preserving blockchain with edge computing,”
Wireless Communications and Mobile Computing, vol. 2019, pp. 1–
17, 2019.
[126] V . Gramoli and M. Staples, “Blockchain standard: Can we reach
consensus?” IEEE Communications Standards Magazine, vol. 2, no. 3,
pp. 16–21, 2018.
[127] M. A. Ferrag, M. Derdour, M. Mukherjee, A. Derhab, L. Maglaras,
and H. Janicke, “Blockchain technologies for the Internet of Things:
Research issues and challenges,” IEEE Internet of Things Journal,
vol. 6, no. 2, pp. 2188–2204, 2018.
[128] C. Xu, K. Wang, and M. Guo, “Intelligent resource management in
blockchain-based cloud datacenters,” IEEE Cloud Computing, vol. 4,
no. 6, pp. 50–59, 2017.
[129] Z. Xiong, Y . Zhang, D. Niyato, P . Wang, and Z. Han, “When mobile
blockchain meets edge computing,” IEEE Communications Magazine,
vol. 56, no. 8, pp. 33–39, 2018.
[130] M. Samaniego and R. Deters, “Hosting virtual IoT resources on edge-
hosts with blockchain,” in 2016 IEEE International Conference on
Computer and Information Technology (CIT). IEEE, 2016, pp. 116–
119.
[131] O. Novo, “Scalable access management in IoT using blockchain: a
performance evaluation,” IEEE Internet of Things Journal, vol. 6, no. 3,
pp. 4694–4701, 2018.
[132] J. Pan, J. Wang, A. Hester, I. AlQerm, Y . Liu, and Y . Zhao, “Edgechain:
An edge-IoT framework and prototype based on blockchain and smart
contracts,” IEEE Internet of Things Journal, vol. 6, no. 3, pp. 4719–
4732, 2018.
[133] M. Alamri, N. Jhanjhi, and M. Humayun, “Blockchain for Internet of
Things (IoT) research issues challenges & future directions: A review.”
Int. J. Comput. Sci. Netw. Secur, vol. 19, pp. 244–258, 2019.
[134] D. C. Nguyen, P . Cheng, M. Ding, D. Lopez-Perez, P . N. Pathirana,
J. Li, A. Seneviratne, Y . Li, and H. V . Poor, “Enabling AI in Future
Wireless Networks: A Data Life Cycle Perspective,” IEEE Communi-
cations Surveys & Tutorials, vol. 23, no. 1, pp. 553–595, 2020.
[135] S. Russell and P . Norvig, Artificial intelligence: a modern approach.
Prentice hall, 2002.
[136] A. Nawaz, T. Gia, J. P . Queralta, and T. Westerlund, “Edge AI and
blockchain for privacy-critical and data-sensitive applications,” in 2019
Twelfth International Conference on Mobile Computing and Ubiquitous
Network (ICMU). IEEE, 2019, pp. 1–2.
[137] J. Xu, S. Wang, A. Zhou, and F. Yang, “Edgence: A blockchain-
enabled edge-computing platform for intelligent iot-based dapps,”
China Communications, vol. 17, no. 4, pp. 78–87, 2020.
[138] R. Yang, F. R. Y u, P . Si, Z. Yang, and Y . Zhang, “Integrated blockchain
and edge computing systems: A survey, some research issues andchallenges,” IEEE Communications Surveys & Tutorials, vol. 21, no. 2,
pp. 1508–1532, 2019.
[139] X. Wang, Y . Han, C. Wang, Q. Zhao, X. Chen, and M. Chen,
“In-edge AI: Intelligentizing mobile edge computing, caching and
communication by federated learning,” IEEE Network, vol. 33, no. 5,
pp. 156–165, 2019.
[140] X. Lin, J. Li, J. Wu, H. Liang, and W. Yang, “Making knowledge
tradable in edge-AI enabled IoT: A consortium blockchain-based
efficient and incentive approach,” IEEE Transactions on Industrial
Informatics, vol. 15, no. 12, pp. 6367–6378, 2019.
[141] A. Chaer, K. Salah, C. Lima, P . P . Ray, and T. Sheltami, “Blockchain for
5G: opportunities and challenges,” in 2019 IEEE Globecom Workshops
(GC Wkshps). IEEE, 2019, pp. 1–6.
[142] E. Chang, K. Y . Chan, P . Clark, and V . Potdar, “Guest editorial:
Blockchain and AI enabled 5G mobile edge computing,” IEEE Trans-
actions on Industrial Informatics, 2020.
[143] K. Zhang, Y . Zhu, S. Maharjan, and Y . Zhang, “Edge intelligence
and blockchain empowered 5G beyond for the industrial Internet of
Things,” IEEE Network, vol. 33, no. 5, pp. 12–19, 2019.
[144] L. Xie, Y . Ding, H. Yang, and X. Wang, “Blockchain-based secure
and trustworthy Internet of Things in SDN-enabled 5G-vanets,” IEEE
Access, vol. 7, pp. 56 656–56 666, 2019.
[145] H. Yang, Y . Liang, J. Y uan, Q. Yao, A. Y u, and J. Zhang, “Distributed
blockchain-based trusted multi-domain collaboration for mobile edge
computing in 5G and beyond,” IEEE Transactions on Industrial Infor-
matics, vol. 16, no. 11, pp. 7094–7104, 2020.
[146] F. Miatton, “Blockchain at the edge: The nexus of capturing new
value in 5G,” in 2020 International Conference on Technology and
Entrepreneurship - Virtual (ICTE-V). IEEE, 2020, pp. 1–6.
IEEE INTERNET OF THINGS JOURNAL 7
Smart contracts for
decision anlysis
Smart
Transportation
Distributed
Storage
Smart contract based
Payment
Decentralized
Parking assistance
Road SafetyInstant traffic data
processing
Secured Data
Transaction
Low latency
real-time traffic
relay
Smart Grid
Privacy in
Energy trading
Task offloading Data Aggregation
Cyber Security
Optimal resource
utilization
Low latency Live
Streaming
Deadlock avoidance
Smart City
Video streaming
with less jitter
Secured financial
transaction
Safe surveillance
data sharing
Scalable to dynamic
application need
Users’ data
Privacy
Reliable data handling
via. multi-gateways
Secured Data
aggregation
Smart Home
Secured Home
care Latency
optimization
Secured Regulatory
Compliance
Secured API
Platform
Group users
privacy
Interoperable
Gateway
Authenticated user
transactions
Optimal energy
management
Industrial
Applications
from BEoT
Smart
Healthcare
Decentralized
medical services
User Privacy
Faster patients
data processing
Secured data
sharing
Access control
system
Secured Structural
health monitoring
Fig. 4: Industrial applications of BEoT paradigm.
will reduce the power outages and ensures faster restoration
of electricity after blackouts.
Smart grid establishes two-way communication between the
producer and consumer thereby focusing on making all the
consumers as prosumers (they can simultaneously produce
and consume electricity). Though smart grid is providing
effective services, it has various challenges to be addressed.
Some of them are protecting power grids from malicious
attacks (integrated security), interoperability in connecting
heterogeneous power systems, predicting the stability of smart
grids, restoration, determining changing demand patterns, on-
demand pricing, lack of regulatory policies, fault detection,
and energy management [65], [66]. To ensure secured transac-
tions and to reduce the overheads involved in data processing,
blockchain and edge computing can be integrated with smart
power grids.
Security concerns of the smart grid network (SGN) include
energy security and data security. EVs offer energy man-
agement solutions in SGNs through effective energy storage
mechanisms. EVs are integrated with the power system and
store the power from the grid and load it back to the grid
whenever required. The energy trading (charging and loading
8 IEEE INTERNET OF THINGS JOURNAL
the EVs) in the SDN-enabled vehicle-to-grid (V2G) infrastruc-
ture is a challenging issue. V2G technology of the smart grid
reduces the level of demand-supply disparity by strengthening
the energy trading capability of EVs. The SURVIVOR-Energy
trading in SDN enabled V2G network using blockchain and
edge computing framework presented in [67], attempts to
cover the tradeoffs in V2G environment. The energy trad-
ing decisions are taken at edge nodes closer to the EV to
reduce the effects of the processing time, thereby reducing
the latency and blockchain is employed to provide security
in energy trading transactions. Though the results proved
that blockchain is lightweight in terms of communicational
and computation cost, content caching, and vehicle mobility
remains to be addressed. Similar to [67], a secure framework
for energy trading between EV and grid (V2G) in cyber-
physical systems was implemented in [68]. Blockchain is used
to secure the transactions in energy trading, followed by a
contract theory based-incentive mechanism for V2G energy
trading. The moderate cost consortium blockchain framework
ensures secure V2G energy trading. An incentive contract
theory based mechanism attains optimal resource utilization
at LEPG. Edge computing is utilized for task offloading with
reduced latency and in turn, increases success rate probability
in block creation, thereby reducing the computational overhead
at local energy aggregators and assists in successful block
creation. Results show that there is a 124.6% increase in the
successful probability of block-creation.
The convergence of blockchain, edge computing, crypto-
graphic algorithm, and other techniques in the smart grid
should not degrade the performance of the SGN. In [69],
a lightweight blockchain consortium was presented to en-
sure the scalability and efficiency of the SGN. Blockchain
smart contract is used for managing the key materials table
(public key identities) anonymously without exploiting the
sensitive information. The security requirements for a smart
grid with edge computing are detailed with Proof of Concept,
and the model can combat known attacks such as replay
attack, stolen verifier attack, and impersonation attack. The
model proposed for key management ensures the efficient
key update with less computational and communication over-
head in comparison to similar models. Henceforth, blockchain
with data aggregation can be utilized in SGN for privacy-
preserving transactions. Edge computing can be recommended
for faster processing or task offloading, thereby providing a
low-latency response. Also, to reduce the computational and
communication cost with blockchain, a lightweight blockchain
framework is recommended. V arious industrial applications
of blockchains integrated with EoT framework are shown in
Table III. It is evident from the literature that BEoT addresses
the crucial requirements of the smart systems. Some of them
are security, low-latency response, optimized resource utiliza-
tion, reliability, scalability, and interoperability. Of the various
industrial applications, conferred smart city is the one that
encompasses the services of other smart systems. For instance,
the smart grid supplies the energy required for the operation
of other intelligent systems as smart grid utilizes the services
of smart transportation for energy trading through EVs. Smart
transportation offers various reliable transport services to smart
home (safe and comfort life) as well as smart healthcare
(instant health services). Blockchain is used for handling all
the transactions among the heterogeneous devices in the smart
systems ensuring the interoperability and security. ES provides
low-latency response in data processing by bypassing the
frequent access to the cloud server for all data processing.
Thus, the BEoT paradigm paves more significant support
in various industrial applications by ensuring interoperable,
secured and privacy-preserving data processing.
C. Smart City
As the global population is increasing, it is challenging to
meet diverse requirements of service provisions from different
users. One of the innovative applications of IoT is the devel-
opment of smart cities worldwide. Smart cities have the ability
to control, monitor, track large volumes of data collected
from various sensors installed in the city and provide essential
services [70].
Smart surveillance system integrated with IoT technology
is one of the vital component of smart city. Some of the
smart surveillance applications are face detection, motion
detection, license plate detection, and threat detection. A smart
surveillance system for smart city was proposed in [71] using
microservice architecture and blockchain. The conventional
surveillance system is based on monolithic architecture which
performs operations such as recording and monitoring whereas
it lacks scalability and mostly relies on centralized architec-
tures, which potentially raises security bottlenecks. The pro-
posed microservice architecture decentralizes the operations
from various distributed edge devices and proposed scalable
solutions to smart surveillance systems.
An architecture was proposed with blockchain to support
spatio-temporal smart contract solutions for sharing economy
parameters in smart cities integrated with IoT environment.
In this architecture, two entities can execute any number
of secure transactions using cognitive systems without the
need of third party while sharing economy related services
using IoT framework for data processing. Cognitive system
thinks like human beings and consists of ML algorithms
for pattern recognition, natural language processing and data
analytics. The cognitive engine is a part of blockchain tech-
nology which reads the available data resources from edge
nodes and acquire knowledge for reliable decision making.
In economy sharing services, transactions are automatic and
managed by intelligent cognitive engine without the human
intervention [72]. A homogeneous ecosystem was proposed,
namely SmartME, in which several applications can be ex-
panded to multinational range by enhancing a shared open ICT
framework built for processing, sensing, storage of resources
in the network. Several technologies such as cloud, fog, IoT,
edge computing, blockchain, ML are required to control the
smart city ecosystem [73]. A secure, scalable, distributed
network architecture was presented to enhance the strength
of evolving blockchain and software defined network (SDN)
technologies in smart cities. The architecture includes the
features of distributed and centralized network architectures.
Edge nodes serve as central server for specific infrastructure
IEEE INTERNET OF THINGS JOURNAL 9
and records the credentials and access rules. The edge network
helps to reduce the bandwidth of the network and obtain
minimum latency. Argon2, a key derivative function based
on PoW method was introduced in the proposed architecture
in order to improve the security, privacy and abstain leaking
information to attackers in distributed smart city network [74].
A framework based on blockchain was presented in [75]
for IoT data sharing and privacy preserving in smart city
applications. In this work, the blockchain network is divided
into various channels and each channel processes the different
type of data obtained from various edge nodes such as finance,
smart car, smart energy, smart healthcare, etc. Each channel
consists of number of certified organizations. Access control
within the channel is managed by smart contracts. Security of
data in each channel is achieved using encryption algorithms.
Thus, BEoT has provided numerous solutions for the decen-
tralization, security and interoperability problems in smart city
based applications. Another study was conducted in [76] by
combining blockchain with IoT in structural health monitoring
(SHM) systems, aiming to improve the operational safety for
underground environments in smart cities. In this blockchain
based IoT network, the centralized and decentralized distribu-
tions are provided by splitting the network into core and edge
networks. These networks provide autonomous monitoring and
control which improves the scalability and efficiency of the
system. Also blockchain based decentralized networks can
be deployed to provide efficient and transparent information
sharing, security and decision making using smart contracts in
SHM.
A BEoT use case on secured SHM in smart city is presented
in Fig. 5. The damages in the building are detected based on
several factors. These factors are determined by data acquired
from an instrumented array of heterogeneous IoT devices
such as fibre optic sensors, temperature sensor, inclinometer
(tiltmeter and slope detector), accelerometer, strain gauge,
vibration sensor, acoustic sensor, smoke detector, transducer,
and linear differential transformer. The data is assimilated in
the cloud server can be retrieved using the cognitive edge
nodes. Cognitive edge nodes are intelligent enough to perform
the mining of the data accumulated and early prediction of
any problems in the structural health of the building. Smart
contracts are used for making decisions, analysis of the type
of problems and sharing the damage index of the miner among
the edge nodes. For each transaction, a block is added in
the distributed ledger assuring authorized access to data and
the access privileges to the user. In turn, the notification on
the structural health of the building (decisions made through
smart contracts) is communicated to various applications and
monitoring centres.
Another BEoT use case on safe surveillance data sharing
is presented in Fig. 6. Most of the decisions in the smart
city environment rely on the surveillance data. Any data
transaction, involving these surveillance systems, should be
done in a very secured manner. There are diversified video
surveillance systems exists in the smart city environment such
as video enabled telephone, private video surveillance, com-
mercial building video surveillance, residential surveillance,
observation surveillance, road traffic surveillance and health
gadget surveillance. Real-time information from many these
surveillance systems is required for taking many important
decisions. For instance, road surveillance video helps to de-
termine the traffic signal. In turn, crowd gathering information
obtained from the commercial building video surveillance
determines the reason for the traffic. Also, the acute health
issues can be evaluated through health gadget surveillance
and more. Videos from these diversified surveillance systems
are processed, analyzed and predicted by the video hubs on
the edge nodes where blockchain-based smart contracts are
deployed for secured and trusted authentication. Furthermore,
to avoid overheads incurred in processing enormous data
stored at blocks in the blockchain, side chains can be used
to segregate unwanted information being stored in the blocks.
This will enhance the efficiency of the overall system.
D. Smart Healthcare
Healthcare sector has succeeded in being one of the leading
domains with respect to employment and income generation
[77], [78]. Even though IoT is contributing to various domains
such as smart home, smart agriculture and smart city, its im-
pact on healthcare sector is remarkable. With the development
of technologies like IoT, AI, 5th Generation (5G) network, mo-
bile Internet, big data and cloud computing, traditional medical
systems are transformed into smart healthcare systems. Using
these advanced technologies, smart healthcare systems reduce
the threat and cost of medical practices and enhances the
progress of telemedicine. Smart healthcare is a medical service
that applies technologies such as IoT, AI, wearable devices and
mobile Internet to acquire information, link people, tools and
organizations associated to healthcare, actively monitors and
responds to medical assistance engaging intelligent system.
Patients can monitor their health status by using wearable
devices, get the medical services through virtual online support
systems and the doctors can predict the diseases. V arious
problems such as security, privacy, transparency, interoper-
ability, decentralization, data storage, and sharing must be
addressed for the deployment of smart healthcare systems.
Blockchain provides better solution to address these issues
in smart healthcare and various research initiatives have been
started by integrating blockchain with edge computing [79].
A secure healthcare scheme namely BHealth based on
blockchain was presented using unmanned aerial vehicle
(UA V) in IoT. The UA V collects medical data from the users
and stores in nearest MEC server. Basic user information
is securely stored in a blockchain using smart contracts.
Blockchain synchronizes the health data, secures the data with
encryption, verifies the users and allows the UAV to store the
data in the server [80], [81].
Blockchain based secure therapy management framework
was presented in [82] using MEC for with disabilities in
various age groups. The framework was developed by leverag-
ing IoT nodes, blockchain and MEC. Blockchain with MEC
provides decentralization, security, low-latency response and
data sharing facilities for therapeutic data. The patient is
allowed to share their data related to therapy with anyone.
The mobile edge network processes the therapy data and
10 IEEE INTERNET OF THINGS JOURNAL
Accelerometer Acoustic Sensor
Fiber Optic Sensor Inclinometer
Smoke Detector Strain gauge
Linear differential
transformer
Motion
Sensor
Temperature sensor Vibrating Wire
Strain Gauge
Vibrating Wire Transducer
Instrumented array of
IoT Sensors
Data Acquisition
Data cleansing
Mining
Data Interpretation
SHM Computation at
Cognitive Edge node
Smart Contracts for decision analysis and
sharing Damage index at each edge
SHM
Applications
Add a block to the
chain
Decisions:
Undamaged
Warning
Alarming
Damaged
Monitoring
Centre
SHM Applications
Privacy Preserving
transaction
Data and Access
Authorization
Fig. 5: BEoT for secured structural health monitoring in smart city.
prevents the limitations caused by high bandwidth. The related
multimedia data such as audio, video and images are stored in
a centralized or distributed storage based on the application.
Providing security and privacy to the patient data collected
from various sources such as sensors, wearable devices etc.,
stored in electronic health records (EHR) database is another
pivotal challenge in smart healthcare systems. A hybrid archi-
tecture using blockchain and edge computing was proposed
to provide access control for the EHR data [83]. All the
access events are verified and stored using a mutual agreement
mechanism before they are included to the blockchain. The
EHR data is stored in edge nodes, which apply access con-
trol policies to provide attribute based access in association
with blockchain. The access control list is executed by the
healthcare providers to obtain one time self destructing URLs
which contain the address of the EHR data. Then EHR data
is accessed by the providers using the URLs. Hence, only
authorized users who have access to attribute based access
control provided by edge nodes can access the EHR data.
A spatial and secure blockchain based mass screening
framework was presented for data storage, sharing and man-
agement of dyslexia data. The framework analyzes the data
and predicts the symptoms of dyslexia. A mobile based
multimedia IoT environment was presented to capture the user
interaction of dyslexia testing data from a smartphone and
share it in the mobile edge network. The edge node applies
auto grading algorithms on the data for predicting dyslexia
symptoms and the final results are stored in the blockchain.
Blockchain provides decentralized data repository for captured
multimedia based IoT test data shared for medical research and
analysis [84].
E. Smart Home
In this world of digital computation, people are committed
towards their work, so it is harder for an individual to be
constantly vigilant on household chores. Smart home, with
ICT assisted devices make the home a safer and better place
to live. One of the critical use cases of a smart city is a smart
home. The smart home uses the Internet, to interconnect all the
household appliances for facilitating seamless communication
between the residents and the home appliances. Some of the
remotely controlled functions in a smart home are closed
circuit television, air conditioners, television, lighting systems,
speaker, thermostat, temperature, refrigerator, doors, and pet
feed. Any appliance with the capability of the remote access
can join the smart home network and can be controlled through
a laptop, PC, a smartphone or a tablet. This interconnection
IEEE INTERNET OF THINGS JOURNAL 11
Genesis Block
Blockchain node
Generate a block in a blockchain network
Download the required content
from edge node
Trusted authentication
Stakeholder's can view the data blocks
Public Key
IPFS Hash
Data Hash
Previous Hash
Block 1
Public Key
IPFS Hash
Data Hash
Previous Hash
Block 2
Public Key
IPFS Hash
Data Hash
Previous Hash
Block N
Commercial building
surveillance
Observation
Surveillance
Residential
Surveillance
Phone
Surveillance
Personal
Surveillance
Road
Surveillance
Health Gadget
surveillance
Diversified Video Surveillance Systems
Live
Streaming
Video analysis
Image
analysis
Surveillance
Forecasting
Operations at Edge
Server (video hubs)
Edge server
Edge server Edge server
Edge server Edge server
Blockchain for secured transactions at Edge
Fig. 6: BEoT for safe surveillance data sharing in smart city.
of objects is possible through IoT devices which makes use
of the Internet to connect all the objects with the ability
to share electronic information. The general types of alerts
raised by these smart household devices are motion detection
in case of theft, automatic control of home appliances upon
its unwanted usage, healthcare of home ridden older people,
kids activity monitoring, etc. The alert system will send alert
notification not only to the home residents but also to the
concerned security providers in case of theft, the fire station in
case of fire, blue cross services in case of animal ill-treatment
and ambulance service for health care issues. Therefore the
primary concern for implementation of smart home system is
security and privacy. Also, this concern paves the way for a lot
of security threats in terms of data theft and cyber-attack, such
as DDoS exploiting all the network bandwidth for hijacking
the environment. Furthermore, application of blockchain in the
smart home helps to protect all the IoT devices in smart homes
and data acquired from these devices for establishing intercon-
nection among heterogenous applications while participating
as an IoT node in the smart city blockchain network.
Data access from the Internet-enabled smart home appli-
ances will be easier for the adept hackers, the users of
technology. So, the work in [85] presented a blockchain-
based gateway architecture to prevent data theft by malicious
users. Multiple security interventions in centralized gateway
architecture of the smart homes are addressed, and severe
network attacks are counterfeited. The data transaction among
various devices in the smart home network are carried out only
for the devices registered in the gateway. The blockchain is
incorporated in this gateway layer of a smart home network
which records and authenticates the devices joining the net-
work through a SHA2 encryption algorithm, thus avoiding the
data theft. The additional computational complexity incurred
by blockchain at the gateway can be reduced by adopting
edge computing for offloading the computation overhead. The
proposed BEoT framework prevents the gateway from the
attacks, namely blockchain 51% attack, patch file forgery
attack and DDoS attack.
A secure authentication system integrating blockchain (for
ensuring reliability in user transactions), group signatures (GS)
(to authenticate different devices in the network) and message
authentication code (for authenticating gateways) was imple-
mented in [86]. This model not only provides a solution for
critical challenges in blockchain applications, but it can also
efficiently trace the footprints of the intruder misbehaviour.
Remote monitoring of patients in a smart home using a fog
assisted IoT based in-house patient monitoring system was
presented in [87]. To avoid the unprecedented delay caused by
processing the data to and from the cloud, the three-layered
model proposes the fog computing services with notification
mechanisms at the network edge (i.e., in the gateway). The
proposed model offers real-time interactive services on event
classification with minimum latency at the fog layer. Fog
assisted IoT model can effectively monitor various behaviors
of the patients and provides real-time notification on the
behavior of the patients with minimum delay in processing.
12 IEEE INTERNET OF THINGS JOURNAL
TABLE II: Unique requirements of blockchain in industrial applications.
S.No Industrial
applications
Common problem Unique requirements of blockchain Challenges in blockchain adoption
1 Smart Trans-
portation
Stabilized network, uninterrupted and
secured data sharing among edge de-
vices and other public vehicles
Blockchain can be utilized for uninter-
rupted and secured data sharing and pri-
vacy to retain the efficiency of ITS
Vulnerable to cybersecurity attacks during
real-time data sharing and optimized re-
source utilization
2 Smart Grid Secured energy trading among pro-
sumers
Blockchain for secured and privacy-
preserving energy trading transaction in
edge computing-based smart grids
Resource optimization (communicational
and computaional resources)
3 Smart City Secure data sharing by users for facili-
tating varied smart applications (multi-
ple trust domains)
Blockchain for secured and transparent
data-sharing among users and multiple
trust domains
Scalability issues when the number of
transactions increased
4 Smart
Healthcare
Distributed authorization of edge nodes,
security and data privacy in healthcare
data records
Blockchain ensures data privacy in more
sensitive health care data transactions and
restricted third party data access
Security issues pertaining to key manage-
ment; Scalability issues when the number
of transactions increases and lack of stan-
dardization
5 Smart home Access control issues to different resi-
dents and visitors
Blockchain can be used for users pri-
vacy requirements and enabling secure
data sharing among non-interoperable
that party service providers
Vulnerable to security attacks while intact
with the consensus process and scalability
issues when the number of applications
increase
The model performs the accurate classification of events based
on the behavior of the patients in the smart home using BBN
with temporal mining.
Furthermore, a ChainSDI (Software Defined Infrastructure)
framework implemented in [88] influences blockchain along
with edge computing to provide a secure sharing and compu-
tation of smart home patients data. The framework attempts
to address the data interoperability and regulatory issues in
emerging SDIs used for healthcare applications. ChainSDI is
an API on SDI that serves as a testbed for any healthcare
application. Though ChainSDI provides better security and
privacy in handling users transactions, the communication and
computation cost is increased.
The industrial applications discussed in this section used
edge computing enabled services for low latency response.
Also, these industrial applications interact with each and
exchange their services. The edge enabled smart environment
faces significant challenges in security and privacy space such
as authentication, access control, intrusion detection as the
ES are heterogeneous and migration of services across these
servers are prone to various security threats. Blockchain with
EoT can address these issues, and the unique requirements of
blockchain in these smart applications are depicted in Table II.
IV. SECURITY REQUIREMENTS FROM BEOT PARADIGM
This section presents the necessary requirements of BEoT
paradigms through some of the key benefits of EoT protection.
Today, modern businesses use a vast, growing systems of
wireless devices and data-intensive applications [89]. As more
devices are added and computing power moves closer to the
device, traditional networks will not be able to maintain the
level of performance required by the businesses [90]. The
nature of the work accomplished by IoT devices creates a
need for much faster connections between the data center
and the devices [91]. Edge computing moves computational
power relatively close to the users, applications and devices
where data is generated and the actions are needed to be
taken. Approaching the data source closer can bring pos-
itive real business impacts such as better user experience,
improved performance, data security, uninterrupted operation
[92]. In today’s increasingly digital world, cybersecurity is
a top concern for business, government and individuals. As
millions of devices connect, hackers find new vulnerabilities
to deliver increasingly sophisticated attacks, making it much
harder for systems to identify, protect and respond to these
threats [93]. In addition to stealing intelligence or disrupting
business activity, hackers now have more entry points allowing
them to damage our physical world and pose serious security
risks to utilities, factories, transportation and other critical
infrastructure. Blockchain technology is one of the solutions
to meet these security requirements in EoT through trans-
parent transactions. The blockchain ledger catalogues each
transaction series from end to end, enabling the reliability,
synchronisation and tracking of all transactions. [94].
A. Access Authentication for Edge of Things
Smart IoT technologies are designed to make our lives
simpler. V arious cellular networks offer seamless connectivity
for billions of things or devices. To protect the exchange
of data, device manufacturers need to provide unique and
reliable digital identities and ensure secure data exchange [95].
Blockchain provides security against hacking, enables end-to-
end encryption of the data they share [96].
Some previous studies employed blockchain technology to
protect EoT applications like smart grids, smart transport,
smart medical devices, smart cities, etc. Some researchers
focused on efficient authentication and data sharing between
different platforms [97]. The work in [98] introduces a method
for improving distributed, trusted authentication services on
blockchains and the EoT. Byzantine error tolerance consensus
algorithm was proposed to develop a blockchain for data
storage and authentication. Edge computing was applied to a
blockchain by providing two edge nodes, a resolution edge
node, and a cache node. Resolution edge nodes provide
name resolution, and the caching node aims to provide edge
authentication using smart contracts and helps to improve the
hit ratio. The asymmetric cryptography model was proposed
to address security challenges between terminals and nodes.
The experimental results show the algorithm’s efficiency in
terms of effective communication and computing costs, while
IEEE INTERNET OF THINGS JOURNAL 13
TABLE III: Survey of industrial applications of BEoT paradigm.
Applications Ref. Contribution Technologies used Key features
Smart
transportation
[58] Platoon driving model for
urban IoVs
Blockchain, IoV , edge
cloud
A vehicle platooning mechanism assists to obtain path information matching,
smart contract based payment mechanism in urban road traffic condition
[59] Parked V ehicle assisted
fog computing chain
Blockchain, smart con-
tract, fog computing
Provides decentralization and security for parked vehicle assistance in vehicular
network using blockchain with smart contracts
[60] V ehicular blockchain Blockchain and edge
computing
Utilizes vehicular blockchain and smart contracts to obtain data storage, sharing
and security in vehicular network
[61] Multi-agent road safety
system Blockchain, EoT Ensures safety and security using blockchain, and enhances network perfor-
mance and latency reduction using EoT
Smart
grid
[67] Energy trading in SDN
enabled V2G network
SDN,Blockchain,Edge
computing and EVs
SDN enabled EVs offer less latency and Lightweight-blockchain with reduced
computational overhead provides security in processing the energy transaction.
[68] Secure V2G energy trad-
ing
Blockchain, Edge and
contract theory
Blockchain ensures secure V2G energy trading, contract theory optimal re-
source utilization and EC ensures task offloading with low latency
[69] Mutual authentication
system in SGN
Blockchain and edge
computing
Almost all the security requirements of the edge enabled SGN was met with
lower computation and communication costs for key management
Smart
city
[72] Sharing economy
services in smart city
BIoT, cognitive edge
nodes assisted with AI
Financial transactions are automatic and managed by intelligent cognitive
engine in Blockchain without the involvement of human using edge computing
[73] SmartME Fog, BEoT and ML SmartME scales up the applications to wide range by enhancing open sharable
ICT and applies edge, fog, blockchain to control the smart city ecosystem
[74] Hybrid network architec-
tural framework BEoT and SDN Offers the features of both distributed and centralized architectures. Edge node
serve as central server and records the credentials thereby reducing the latency
[75] Secure framework for
IoT data sharing
Blockchain, IoT, edge
computing
The framework divides the network into multiple channels and each channel
secures the data related to specific application collected from edge devices
Smart
healthcare
[80] BHealth Blockchain, smart con-
tract and MEC
The scheme synchronizes the health data, secures the data with encryption,
verifies the users and allows the UAV to store the data in the ES
[82] Therapy management
framework BIoT and MEC The framework for the differently abled people provide decentralized, secured,
low-latency response and therapeutic data sharing facilities
[84] Blockchain based mass
screening framework
BEoT in mobile and
auto-grading algorithms
Provides decentralized data repository for captured multimedia based IoT test
data shared for medical research and analysis.
Smart
home [88] ChainSDI, regulatory
compliance
SDI, Edge Computing
and Blockchain
Provides secured specification for regulatory compliant requirement in data
processing and a low-latency response in health care-related data processing
the proposed model outperforms existing models by reducing
the delay rate of 6%-12% and increasing the hit rate 8%-14%.
However, the proposed model can be enhanced by reducing
latency while transferring large data packets to the destination.
In a real-time environment, achieving minimal latency with
high security is a challenging task. In [69], the authors
proposed an authenticated blockchain model with an effective
key agreement protocol for the smart grid edge-computing
systems. Experimental results promise security improvements
with minimal latency for smart grid growth. The proposed
model focused more on providing better security, although
the computing cost can be minimized by maintaining the ES
cache nodes. In a similar wok in [99], the authors proposed
a secure key agreement protocol using blockchain for smart
grid edge computing systems. The main requirement of this
proposed model is that the smart meter sometimes fails to
check the authenticity of the electrical power control, and
therefore, the authentication process is not achieved at a better
rate. Transferring goods safely from source to destination
using supply chains requires high bandwidth, which can be
achieved with 5G enabled EoT. In [100], the authors proposed
blockchain-based authentication technology integrated with
the RFID supply chain system in 5G enabled EoT for efficient
computing and communication costs. The proposed authenti-
cated model works on cryptographic hash and bitwise XOR
rotation. Initially, the authors considered N blocks, and each
block has the privilege of a reader tag. The reader tag must
prove its identity by transferring the authentication message
to the supply chain. The supply chain validates the received
message and ensures acknowledgment. Experimental results
achieve a higher security rate with effective communication
costs compared to existing models. In addition, the proposed
model can be extended further to focus on a real-time problem.
The rapid growth of vehicular edge computing (VEC) in
smart transport has intensified the implementations on traffic
systems. Accessibility of communication channels, authenti-
cation of privacy and trust management in automobiles have
made VEC highly prevalent. In [101], the authors proposed
a VEC blockchain model based on trackable map directions
using dynamic route hash chain. This model’s vision is to
build a decentralized, secure system with low communication
overhead. Moreover, the proposed model does not achieve
better latency and communication overhead for a 256-bit
data message, thus inhibiting its usefulness in VEC. Another
interesting work to provide authentication in electric vehi-
cles integrated with cloud infrastructure and edge computing
[102], the authors proposed blockchain-based data coins and
energy coins on a decentralized network. During this process,
blockchain technology enhances authenticated data processing
and security mechanisms for energy transmission. However,
the proposed model does not specify how data manipulation,
identification are carried out, thus limiting its use in the VEC.
Another application of blockchain for efficient data sharing
in VEC can be found in [103], where the data can’t be
shared without proper authorization. The vehicular blockchain
model uses smart contracts to accomplish effective and reliable
information storage on roadside units (RSUs) and information
sharing within automobiles. The reputation-based access con-
trol technique is used to make sure the transmission of reliable
information between vehicles. The experimental results for the
detection of abnormal vehicles at a trust threshold of 0.35 is
100% for the proposed model, while the other existing model
is only 50%.
14 IEEE INTERNET OF THINGS JOURNAL
B. Data Privacy for Edge of Things
Data privacy is one of the key requirements that protect
data from malicious access. A number of data privacy mech-
anisms available include encryption, decryption, perturbation-
based, and blockchain. Data is securely transmitted in the
blockchain by maintaining timestamps and hash functions.
Shared information is distributed across multiple sites using a
distributed ledger [104], [105]. In [106], researchers propose
a privacy-preserving method by assigning tasks to the edge
nodes using smart contracts, in which each block keeps the
assigned task information. All edge nodes connected to a
decentralized network and the information is distributed using
alias function in the blockchain. Edge nodes need to perform
the assigned task and calculate time and energy consumption.
Experimentation performed on a variety of privacy methods
to prevent the storage of block information from multiple
data mining threats. Moreover, the proposed model achieved
a satisfactory privacy rate; however, it can be improved by fo-
cusing more on optimizing energy consumption at edge nodes.
The successful development of the smart grid depends on
the transformation of secure communication technologies, as
the smart grid offers multiple options for collecting electrical
data [107]. However, smart grid applications face challenges
like energy security and privacy protection. In [108], the
authors proposed preserving BEoT ’s privacy for smart grid
applications. In this process, electricity consumption can easily
be traced without disclosing end-user information to identify
inappropriate energy-using behaviors by raising alarms using
blockchain. Few supernodes are deployed in the blockchain
responsible for resource allocations that validate the edge
nodes. Here edge nodes are considered smart meters, power
sensors. These edge nodes distribute the energy to the end-
user, which reduces the burden on the central system and
helps to improve the computing process. The edge node is
validated using the covert channel authorization scheme, and
the access control scheme. V alidation is designed to ensure that
a 51% attack ensures that the majority of participants are good.
Optimal allocation of energy resources will be made through
a smart contract, covering three elements, including energy
consumption, latency, and security of communication. The
work in [109], introduces a distributed IIoT model for smart
factory using blockchain. In order to ensure proper privacy,
the authors introduced the bell-la padula (BLP) approach,
which is integrated with the biba model [110]. Experimental
findings show that the proposed model provides enhanced
security and privacy features. However, the proposed model
failed to achieve proper resource allocation strategies, thereby
reducing its usefulness. In [111], the authors proposed an
innovative blockchain model for edge-based IoT architectures
called LiTichain with multiple blocks, each with a finite
lifespan. The block will be removed from the chain if the life
of the transaction expires. LiTichain is created by merging
two different graphs. One graph represents the life of the
transaction, and the second graph represents the formation of
a block in the chain. As the number of transactions increases
the height of the chain, the authors have introduced a K-
height block method to restrict the height of the chain. The
experimental results are obtained by taking New Y ork taxi
IoT data, which transmits sensed data to the ES. The ES will
collect and process the data. The proposed blockchain model
is used on ES to ensure sensed IoT data privacy.
C. Attack Detection for Edge of Things
Due to the proliferation in IoT sensing technology, attackers
can attack and steal sensitive and vital data. Some applications,
such as smart grids, smart cities, supply chains, healthcare,
etc., are often used to generate sensitive IoT data and there
is a high probability of attacking these data. Cyber attack-
ers are exploring different vulnerabilities to exploit highly
sophisticated attacks, making it extremely difficult for sys-
tems to identify, protect, and respond to such attacks. The
attack detection system is one of the requirement to monitor
the communication system and to protect against malicious
attacks [112]. Recently, the authors in [113] introduced a
new blockchain architecture by integrating edge, cloud and
SDN to achieve confidentiality and strengthen the security
mechanism by preventing IoT devices from various types
of malicious attacks. During this process, IoT sensors from
different locations capture the data and transfer the cap-
tured data to the edge-cloud for pre-processing. The SDN-
enabled blockchain process allows dynamic network traffic
management and detects malicious attacks. In the cloud layer,
most attacks are identified and eliminated, which reduces
storage space and increases the rate of latency while reaching
the edge layer; therefore, the rate of attack is drastically
reduced, increasing the performance in terms of throughput
and delay. Experimental results obtained by deploying 100
nodes in the 3000 m × 3000 m search area, taking into
account energy consumption, packet delivery ratio, throughput
and delay as performance metrices. The results promise that
the proposed security model will consume less energy and
improve the transfer of packets with better throughput and
delay. In addition, the proposed model does not produce any
results for the detection of attacks, thus limiting its utility in
the blockchain model. Another blockchain framework can be
observed in [114], where the economic denial of sustainability
(EDoS) are prevented from malicious attackers. Secret sharing
scheme (SSS) is introduced to provide security whenever the
ES fails. Sometimes, whenever the ES is down due to some
malicious attack by an attacker, the proposed model uses a
binary search mechanism to identify and locate the afflicted
ES. The results reveal that the proposed model uses 128-
bit ciphertext data, 256-bit Diffie-Hellman key, requires 0.004
ms for encryption, and 0.0039 ms for decryption. The total
computational time taken by the proposed model for uploading
and accessing data is 14.1199 ms. In addition to computational
performance, the proposed model achieves a better attack
prevention rate. Event-driven messages (EDMs) in vehicle
networks will be generated during the occurrence of accidents,
road slipping. EDMs consists of photos, videos, etc. and faces
several challenges, such as security and latency, during the
transmission of these messages. The work in [115] introduces
a reliable blockchain platform with 5G-enabled vehicle edge
computing to transfer EDMs to end-users by optimizing com-
munication costs. During this process, EDMs are transferred
IEEE INTERNET OF THINGS JOURNAL 15
to nearby ES in order to reduce the response time. Blockchain
technology is used at the edge nodes to track messages
and protect messages from a variety of attacks. The results
show that the proposed model protects EDMs from different
types of attacks, like impersonation attacks, DDoS attacks,
Masquerade attacks, and reduces communication overheads.
Another interesting work related to VEC [116], the authors
integrated deep reinforcement learning (DRL) and blockchain
into vehicle networks aim of providing smart and reliable
caching content. During this process, initially the proposed
blockchain model ensures a decentralized data caching system
in which the vehicles perform data caching and maintains an
authorized blockchain at the nearby fixed base stations. Later
DRL is used to develop an optimal data caching model by
considering mobility as one of the metrics. Finally, to enhance
the process of block verification, the authors used the new
Block Verifier Selection Method, proof-of-utility (PoU).
D. Trust Management for Edge of Things
Due to the rapid growth of technical advances, large
amounts of data are gathered from edge nodes or IoT devices,
but data protection, trust management and privacy are very
important requirements on ES, particularly when the collected
data is malicious and can cause serious problems. The work in
[117] introduces a blockchain-based, trusted data management
system (BlockTDM) in edge computing. In this process, the
blockchain model is designed to ensure mutual authentication,
smart contract and flexible consensus. The proposed Block-
TDM ensures the privacy of data through the provision of a
multi-channel data segment. The data is encrypted using user-
defined encryption techniques just before the transaction is
stored in the blockchain. Decryption and transaction of data
in a secure blockchain is carried out using hyperledger as a
smart contract. Another exciting blockchain application can be
found in [118], which preserves MEC from fake service record
threats and malicious edge threats. The authors proposed an
RL algorithm to decrease computational latency, optimize
energy consumption, and reduce the resource allocation time
of the edge devices. The experimental results show that the
authors used the blockchain model on Ethereum, PoW protocol
is used to promtly build service records in the blockchain. The
proposed model reduces the malicious attack rate by 66.4%,
optimizes energy consumption by 10.5%, and reduces latency
by 67.4%. In [119], the authors introduced a decentralized,
trustworthy blockchain model in edge computing. The domain
name server sends the user request to the appropriate ES,
which reduces the propagation delay. To achieve trustwor-
thiness and security, all participants involved in transactions
must share their block information and transaction details.
Participants contributing to the network will earn blockchain
tokens. The experimental results show that the proposed model
provides 12.54% optimal latency rate compared to the other
existing model. Another interesting work in [120] suggests
a trust-aware IoT data economic system (TIDES) to provide
safe, precise, and intelligent IoT data trading systems for the
end-users. In the first step, the trustworthiness mechanism
obviates malicious distributors to ensure secure transmission
of data. In the second phase, the game-theory based pricing
method facilitates win-win transactions where suppliers get
better quality information at a reasonable rate and distributors
get huge returns. In the third phase, if the candidate has
accidentally made a transaction to a malicious distributor, the
payment of the transaction will be reflected automatically. In
the final phase, TIDES uses an MEC model to reduce latency
and overhead storage. The experimental results show that
TIDES accomplishes better results in terms of trading time,
reduced latency, better security and communication costs.
E. Summary
In this section, we examined the security requirements of
the BEoT paradigm and benefits of blockchain in providing es-
sential security services to EoT, such as access authentication,
data privacy, attack detection, and trust management. In to-
day’s world of advancements in Internet, wireless technology,
and data-intensive applications, we have seen significant tech-
nological changes in data communication and networking ap-
plications. Edge computing is a trending technology designed
to improve latency and increase computational performance.
As millions of devices connect, hackers find new vulnera-
bilities to exploit sensitive and confidential data. Blockchain
technology can remove all these security problems through
transparent transactions. We summarize security opportunities
from the BEoT Paradigm in Table IV.
V. RESEARCH CHALLENGES AND FUTURE DIRECTIONS
This section presents the key research challenges and future
directions related to the BEoT paradigm.
A. Research Challenges
BEoT has the potential to spot its avenues in almost all
kinds of digital applications. BEoT paradigm is an integration
of three giant technologies, namely blockchain, Edge com-
puting, and IoT. It offers significant benefits combating many
issues in the performance of deploying each other separately.
Therefore the issues concerned with these technologies should
be addressed.Some of the challenges of the BEoT paradigm
are discussed here.

1. Security in blockchain: Blockchain is a shared, secured,
   immutable, decentralized, and valid ledger, which records and
   tracks the transactions done on digital resources without the
   necessity of centralized authority in various domains such as
   smart healthcare and smart cities. It enables two users to ex-
   change and communicate in a peer-to-peer network where the
   distributed decisions are taken by considering the majority vote
   instead of a single centralized administration. Blockchain has
   demonstrated its ability in many applications which involves
   a centralized ledger. Some of the promising applications of
   blockchain are monitoring the network and providing security
   services which includes privacy, confidentiality, and integrity.
   Despite several potential applications of blockchain in various
   domains, it still has many open-ended challenges. The various
   security, privacy, and scalability challenges of blockchain are
   cryptokey management, data privacy in chain management,
   16 IEEE INTERNET OF THINGS JOURNAL
   TABLE IV: Review of security requirements of the BEoT paradigm.
   Security
   services Ref. Application
   Domain Contributions Challenges
   Access
   authentication
   [98] IoT
   system
   Edge nodes provide name resolution, and the caching node provides
   edge authentication using smart contracts
   Poor latency and delay while transferring
   large data packets
   [69] smart grid

1. The key agreement protocol ensures secure communication be-
   tween the end user and the ES
   Results limited to authentication did not
   show computation cost results
2. Smart contract ensures secure transaction, identity verification,
   recording of the public key
   [99] smart grid
   The key agreement protocol enables smart meters to acquire reliable
   power services from distribution control through a single private key
   Smart meter sometimes fails to check
   the authenticity of the electrical power
   control
   [100] service
   system
   Cryptographic hash and bitwise XOR rotation are used for authen-
   tication.The reader tag must prove its identity by transferring the
   authentication message to the supply chain
   Proposed method not investigated on a
   real-time issue
   [101] vehicular
   network
   Trackable map directions using dynamic route hash chain and
   to build a decentralized, secure system with low communication
   overhead
   The model does not achieve better latency
   and communication overhead for a 256-
   bit message
   [102] vehicular
   network
   Authenticated data processing and security mechanisms for energy
   transmission
   Proposed model does not specify how
   data manipulation, identification are car-
   ried out
   [103] vehicular
   network
   Smart contracts are used to accomplish effective and reliable infor-
   mation storage on roadside units
   Resource allocation at edge nodes is ex-
   cluded
   Data
   privacy
   [106] IoT
   network
   Edge nodes connected to a decentralized network and the info is
   distributed using alias function in the blockchain
   Proposed model can optimize the energy
   consumption at edge nodes
   [108] smart grid Few supernodes are deployed in the blockchain responsible for
   resource allocations that validate the edge nodes
   The model does not specify traffic load
   and resource allocation as the network
   size increases
   [109] IIoT BLP approach integrated with the Biba model [110] to ensure data
   privacy
   Proposed model failed to achieve proper
   resource allocation strategies
   [111] IoT
   network
   LiTichain blockchain model is created by merging two different
   graphs. One graph represents the life of the transaction, and the
   second graph represents the formation of a block in the chain
   Poor latency and delay while the number
   of transactions increases
   Attack
   detection
   [113] IIoT The SDN-enabled blockchain process allows dynamic network traf-
   fic management and detects malicious attacks
   Proposed model does not produce any
   results for the detection of attacks
   [114] service
   system
   EDoS are prevented from malicious attackers, SSS is to provide
   security whenever the ES fails
   Proposed method not investigated on a
   real-time issue
   [115] vehicular
   network
   Reliable blockchain platform with 5G-enabled vehicle edge com-
   puting to transfer EDMs to end-users by optimizing communication
   costs
   System design does not focus on
   anonymity
   [116] vehicular
   network
   DRL-blockchain aims to provide smart and reliable caching content
   on vehicle networks Proposed model uses tiny dataset
   Trust
   management
   [117] IoT
   network
3. BlockTDM ensures the privacy of data through the provision of
   a multi-channel data-segment
   The system design does not reduce com-
   munication overhead
4. Data encryption is carried out using user-defined encryption
   techniques and decryption is done by hyperledger as a smart contract
   [118] Mobile
   computing
5. RL algorithm to decrease computational latency time, optimize
   energy consumption, and reduce the resource allocation time of the
   edge devices
   The proposed model does not specify
   resource allocation as the size of the net-
   work increases
6. PoW protocol is used to build service records in the blockchain
   quickly
   [119] Storage
   network
7. The domain name server sends the user’s request to the ES to
   reduce the propagation delay
   Results did not show computation cost
   results
8. To achieve trustworthiness and security, all participants share their
   block information and transaction details
   [120] IoT
   network
9. Game-theory based pricing method facilitates win-win transac-
   tions Not effective for large real-time data2. TIDES uses MEC model to reduce latency and overhead storage
   transaction linkage, and compliance with regulations with
   respect to data privacy. Several research works have been
   carried out on the privacy of the users in various digital
   scenarios. Blockchain technology was developed to deploy
   the Bitcoin cryptocurrency and resolves the double spending
   issue. The solution for this problem is bitcoin in which all
   the transactions are made public in the ledger. Any node
   can track and watch the transactions which are spent. But
   the problem is the complete anonymity is not guaranteed in
   bitcoin [121]. In the distributed EoT, ES are distributed at the
   network edge, making the ES vulnerable to security attacks.
   The conventional cryptographic techniques are difficult to be
   accommodated in ES as they are resource-constrained. This
   challenge in EoT opens up a need for a secured lightweight
   authentication where the ES can authenticate the end devices
   at a faster pace. Furthermore, the edge server needs a trust
   management mechanism to ensure reliable trust computation
   between end nodes and various ES as these servers cannot
   carry trust among other servers.

2. Standardization: Blockchain was originated as an infras-
   tructure to provide solutions for the digital cash problem. Also,
   it allows payment across borders irrespective of the constraints
   in the geographical area over the Internet. Whereas it takes
   many days to transfer funds between various banks located
   IEEE INTERNET OF THINGS JOURNAL 17
   in different countries using the conventional banking system.
   This open nature of blockchain technology makes it further
   expanded to address many commercial problems in several
   financial applications, Industrial sectors, IoT, supply chain,
   etc. But the speed and extent of implementation of blockchain
   technology are obstructed by its interoperability challenges.
   These challenges are not only due to the representation of
   various digital tokens and cryptocurrencies but also the vital
   differences in the behavior of transaction management. This
   makes blockchain difficult to combine with other conventional
   enterprise systems and interoperate. This eventually creates
   issues for the regulatory acceptance of blockchains, thereby
   raising a need for standardization.
3. Resource management in BEoT: The decentralized
   blockchain framework empowers the robustness and scalability
   of the system by utilizing the optimal resources from all the
   nodes, thereby reducing the latency in the data processing
   as well as making the resource-restricted IoT platform a
   robust resource utilization framework. On the other hand, IoT
   encompasses the devices with restricted bandwidth, whereas
   blockchain consumes more bandwidth. BEoT, a distributed
   platform where the heterogeneous data (distributed in different
   areas) from heterogeneous nodes are accumulated and pro-
   cessed in a distributed environment. Therefore, the various
   distributed resources like data centres for storage, robust
   machines for complex computation, interoperable middleware
   services, user details can be managed effectively. The dis-
   tributed ledger at every node in blockchain alleviates the need
   for a centralized server by storing the device credentials and
   transactions. As the number of IoT devices is increasing,
   the number of transactions in the ES also increases rapidly.
   Therefore higher processing capability and computational net-
   work resources are required to ensure the increased processing
   capability and low latency responses.
   The storage overhead incurred due to this massive pro-
   cessing requirement of blockchain in processing real-time
   data streaming, can be reduced by segregating the metadata
   required from the original data stream and minimizing the
   contents to be stored on the blocks. Though lightweight
   blockchain serves this purpose, its scalability will decrease
   with an increase in the number of network nodes. There-
   fore, sidechains can be used with blockchain as a control
   layer [122]. The major problem in the integration of IoT
   and blockchain is storage constraint, i.e., a combination
   of resource-constrained IoT with high resource-consuming
   blockchains. Resource-constrained edge devices with limited
   computing resources are not efficient in handling numerous
   transactions when integrated with huge resource consuming
   blockchain frameworks. The decentralized blockchain frame-
   work trust mechanisms will ensure trustworthiness in data
   from edge nodes [123].
4. Scalability: Scalability is a more significant issue in
   the data storage of cloud-centric IoT devices. As the
   blockchain grows with the number of users or transac-
   tions, it is difficult for the IoT devices to store the ledgers
   as it increases in size. Furthermore, IoT devices range
   from low-power to high-end servers. So, depending on
   the resource capability of the IoT device, designing
   a device-specific blockchain is a trending challenge.
   This includes the security algorithms, efficient mining
   process, and appropriate metadata segregation from the
   ledger.
5. Intelligence: The BEoT paradigm offers various ser-
   vices like secure and privacy-preserving data sharing
   with low latency response for various industrial ap-
   plications. It still lacks intelligence in processing and
   prediction the future behaviour of the applications. For
   instance, earlier prediction of disease in smart healthcare
   based on the information accumulated in the edge,
   demand response prediction and EVs lifetime prediction
   in smart grids, traffic data prediction in intelligent trans-
   portation systems, resource demand prediction in smart
   cities and predictive maintenance of home appliances
   requires intelligent agents to enable predictive analytics
   in almost all industrial applications of BEoT.
   The resource management issues concerned with various
   applications of Blockchain, IoT, and edge computing indi-
   vidually as well as in combination is presented in Table V.
   It is evident that resource management directly impacts the
   acceptability, scalability, robustness, interoperability, load pro-
   visioning, long-term sustainability, faster data processing (with
   low-latency response), and task offloading. Henceforth, to
   design a scalable and secured BEoT environment hosting of
   the resources, metadata segregation in blocks, faster (higher
   bandwidth) and controlled access to the resources must be
   enforced.
   B. Future Directions
   This section presents the various solutions and future direc-
   tions in BEoT with AI and 5G networks.
6. Solutions to Research Challenges: V arious research so-
   lutions in the literature had addressed the challenges in the
   BEoT environment.
   • Security Frameworks: The work in [124] discusses
   various security problems and services provided by
   blockchains. One of the advantages of blockchain is
   its pseudo-user anonymity feature, but there is a threat
   that the user information can be exposed to hackers.
   The users are not anonymous, in which blockchain-based
   access control lists(ACL) associate the ACL with the
   users directly. The same problem occurs in blockchain-
   based provenance and key management. The anonymity
   problem of blockchain is solved by bitcoin in which
   the public key of the user is their identification. A
   trust enabled blockchain framework called trustchain for
   privacy preserving transactions in EoT was proposed in
   [125]. Trustchain, lightweight permissioned blockchain
   (consent violation) ensures privacy preservation among its
   prosumers and avoids unprecedented delays in distributed
   networks. Furthermore, as the edge computing moves
   computing resources closer to the end users, the privacy
   of data should be ensured in distributed computing envi-
   ronments.
   • Standardization bodies: An initiative for standardization
   has been started on blockchain through a professional