IEEE Consumer Electronics Magazine - May/June 2023 - 105

smaller and concurrent computations suited to
different levels and capacities of resources in
distributed cloud. AI models should be optimized
for their deployment on ECs by using compression
techniques. Also, advanced networking
solutions are required to support efficient data
acquisition and exchange of AI models within
dynamic distributed cloud networks. Moreover,
novel learning techniques (e.g., federated learning16)
are highly desired for privacy-sensitive EI
applications.
Business Models
In distributed cloud, the establishment of
business models remains unclear. Distributed
cloud is supposed to have the same flexibility of
pay-as-you-go models as conventional centralized
cloud. However, resource monitoring,
accounting, and billing in distributed cloud are
challenging due to the decentralized location,
utilization and distributed ownership of resources,
as well as the mobile nature of users. For
example, when a user moves and the executed
service migrates from one EC to another, how
the involved EC providers can divide the payment
among themselves needs to be determined.
Therefore, various levels of charging
granularity may have to be incorporated.
Security and Privacy
Distributed cloud aims to extend CS to the network
edge; however, ECs are usually not computationally
powerful enough to withhold strong
defense against network attacks. Besides, distributed
cloud is a multivendor environment; hence,
new distributed trust models are required to
ensure the confidentiality of data and applications.
A promising research direction is to integrate
blockchain technology into distributed cloud.17 As
a decentralized distributed ledger, blockchain is
furnishedwith features like immutability, traceability,
and transparency. Blockchain enables a credible
interaction between distributed clouds
involving various vendors. It eliminates the need
for central authority through consensus protocols,
such as proof-of-work (PoW).Moreover, smart contracts
can be implemented on blockchain to automatically
execute operations among distributed
clouds in a secured and trusted manner. However,
traditional PoW consumes extensive storage and
May/June 2023
energy, and has high network latency. Therefore,
lightweight distributed security mechanisms need
to be investigated.Moreover, the integration of distributed
cloud, blockchain, AI, and IoT to develop
privacy-sensitive applications is a promising
research direction.18
CONCLUSION
The distributed cloud, which extends the cloud
footprint beyond the centralized data centers to
multiple locations including the network edge, is in
its infancy. In this article, a snapshot of distributed
cloud is provided, including the concept, architecture,
and enabling technologies. Moreover, a preliminary
evaluation of service deployment and
discovery based on hierarchical SDN-CCN architecture
is conducted, and some open research
challenges are highlighted.
ACKNOWLEDGMENTS
This work was supported by the MSIT (Ministry
of Science and ICT), Korea, under Grant Information
Technology Research Center support program (IITP2022-2020-0-01612)
supervised by the IITP (Institute
for Information&communications Technology Planning
& Evaluation), and Priority Research Centers
Program (2018R1A6A1A03024003) through the
National Research Foundation of Korea (NRF)
funded by the Ministry of Education, Science and
Technology.
&REFERENCES
1. E. Ahmed et al., " Bringing computation closer toward
the user network: Is edge computing the solution ?, "
IEEECommun. Mag., vol. 55, no. 11, pp. 138-144,
Nov. 2017, doi: 10.1109/MCOM.2017.1700120.
2. A. J. Ferrer etal., " Towards the decentralised cloud:
Survey on approaches and challenges formobile, ad
hoc, and edge computing, " ACMComput. Surv.,vol.51,
no. 6, pp. 111:1-111:36, 2019, doi: 10.1145/3243929.
3. Gartner, GartnerTop 10Strategic Technol. Trends for
2021. Accessed: Apr. 15, 2022. [Online]. Available:
https://www.gartner.com/smarterwithgartner/gartnertop-strategic-technology-trends-for-2021
4.
Q. Duan, S.Wang, and N.Ansari, " Convergenceof
networkingandcloud/edgecomputing: Status, challenges,
andopportunities, " IEEENetw., vol. 34, no. 6, pp. 148-155,
Nov./Dec. 2020, doi: 10.1109/MNET.011.2000089.
105

http://dx.doi.org/10.1109/MCOM.2017.1700120 http://dx.doi.org/10.1145/3243929 https://www.gartner.com/smarterwithgartner/gartner-top-strategic-technology-trends-for-2021 https://www.gartner.com/smarterwithgartner/gartner-top-strategic-technology-trends-for-2021 http://dx.doi.org/10.1109/MNET.011.2000089

IEEE Consumer Electronics Magazine - May/June 2023

Table of Contents for the Digital Edition of IEEE Consumer Electronics Magazine - May/June 2023