IEEE Consumer Electronics Magazine - May/June 2023 - 60

Edge Computing
this information across the whole system. However,
in the far-Edge environment, (i) redundancy
may not be applicable, (ii) such powerful
machines may not be present, and (iii) partitions
are likely to happen. The state information is
crucial for the system as all the intelligence and
decisions are based on them.
Therefore, distributing the state information
across nodes participating in the system should
be considered since (i) it reduces the burden of
having a single information storage requiring
large-memory quantities by distributing the
memory needs across the nodes composing the
system and (ii) enables partitioning while providing
availability.
It is clear that this approach needs to be handled
by design as it may require a change in the
consistency model of the system, which must be
taken into account when designing the management
algorithms.
CONCLUSIONS
Recent years saw the advent of different Edge
solutions, each one focusing on a different
aspect of the Edge. This work presents an analysis
of the differences between Cloud and Edge
infrastructure and the most prominent current
solutions for controlling edge resources, an evaluation
on the scalability properties is also provided.
Results show the following:
i) the amount of information stored in the controller
is dominated by infrastructure
information;
ii) infrastructure monitoring relies on a constant
stream of information that may be
incompatible with far-Edge connectivity;
iii) scheduling decisions can lead to overprovisioned
nodes, leaving part of the infrastructure
unused;
iv) existing solutions support only containerized
applications workloads, whereas with farEdge,
an heterogeneous approach is needed.
As next steps, we plan to investigate the
proposed areas, in particular, the modeling of
a decentralized, heterogeneous, mobile, and volatile
infrastructure and management solutions
that do not require centralized controllers.
60
ACKNOWLEDGMENTS
This work was supported in part by the
H2020 collaborative Europe/Taiwan Research
Project 5G-DIVE under Grant 589881 and in part
by the H2020 European Collaborative Research
Project DAEMON under Grant 101017109.
&REFERENCES
1. S. Liu, L. Liu, J. Tang, B. Yu, Y. Wang, and W. Shi,
" Edge computing for autonomous driving:
Opportunities and challenges, " Proc. IEEE, vol. 107,
no. 8, pp. 1697-1716, Aug. 2019, doi: 10.1109/
JPROC.2019.2915983.
2. ETSI, " Multi-access edge computing (MEC);
terminology, " Eur. Telecommun. Standards Inst.,
Sophia Antipolis, France, ETSI GS MEC 001 V2.1.1
(2019-01), Jan. 2019.
3. ETSI, " Network functions virtualisation (NFV); use cases, "
Eur. Telecommun. Standards Inst., Sophia Antipolis,
France, Group Rep. NFV 001 v1.2.1, May 2017.
4. IEEEStandard for Adoption ofOpenFog Reference
Architecture forFog Computing, IEEE 1934-2018, Jul.
2018.
5. Networld2020, " Smart networks in the context of NGI, "
Networld2020, White Paper, Apr.2018.
6. I. Goiri, K. Le, J. Guitart, J. Torres, and R. Bianchini,
" Intelligent placement of datacenters for internet
services, " in Proc. 31st Int. Conf. Distrib. Comput.
Syst., Jun. 2011, pp. 131-142, doi: 10.1109/
ICDCS.2011.19.
7. S. Ramneek et al., " Boosting edge computing
performance through heterogeneous manycore
systems, " in Proc. Int. Conf. Inf. Commun. Technol.
Convergence, Oct. 2018, pp. 922-924, doi: 10.1109/
ICTC.2018.8539604.
8. C. Hong and B. Varghese, " Resource management in
fog/edge computing: A survey, " 2018,
arXiv:1810.00305, doi: 10.1145/3326066.
9. NIST, " The NIST definition of cloud computing, "
Nat. Inst. Standards Technol., Gaithersburg, MD,
USA, Tech. Rep. NIST Special Pub. 800-145, Oct.
2011.
10. C. Wang, K. Schwan, V. Talwar, G. Eisenhauer, L. Hu,
and M. Wolf, " A flexible architecture integrating
monitoring and analytics for managing large-scale
data centers, " in Proc. 8th ACMInt. Conf. Autonomic
Comput., 2011, pp. 141-150, doi: 10.1145/
1998582.1998605.
IEEE Consumer Electronics Magazine

http://dx.doi.org/10.1109/JPROC.2019.2915983 http://dx.doi.org/10.1109/JPROC.2019.2915983 http://dx.doi.org/10.1109/ICDCS.2011.19 http://dx.doi.org/10.1109/ICDCS.2011.19 http://dx.doi.org/10.1109/ICTC.2018.8539604 http://dx.doi.org/10.1109/ICTC.2018.8539604 http://dx.doi.org/10.1145/3326066 http://dx.doi.org/10.1145/1998582.1998605 http://dx.doi.org/10.1145/1998582.1998605

IEEE Consumer Electronics Magazine - May/June 2023

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