IEEE Computational Intelligence Magazine - May 2022 - 98

dynamic optimization problems, the
transfer learning technique can be used
to analyze the algorithm data in the current
and the past environments for generating
useful knowledge that can help
EC algorithms adapt to the next environment
and enhance the search efficiency
[195]. Moreover, the transfer
learning technique can also be used
when using EC algorithms to solve several
instances of the same optimization
problem. In detail, the search experience
of EC algorithms on solved instances
can be analyzed by the transfer learning
technique for generating useful knowledge
to drive the EC algorithms more
efficiently when solving a new instance.
E. EC-Optimized Cloud-Edge
Collaboration Framework
Intelligent transportation in smart cities
relies on massive IoT devices. These devices
generate a large amount of data to be
processed. Sending all these data to the
data center (e.g., cloud server) will result in
unacceptable response time due to limited
network bandwidth. With the development
of edge computing, the cloud-edge
collaboration framework is a promising
approach to address this problem. In the
cloud-edge collaboration framework, simple
computational tasks can be processed
at the edge of the network, which can
reduce the amount of data required to be
sent to the cloud server. The cloud server,
which has a high computational capacity,
will manage complex computational tasks.
Thus, the cloud-edge collaboration framework
can reduce the pressure of network
transmission, reduce the network bandwidth
requirement, and enhance the computational
efficiency to achieve a shorter
response time.
However, the configuration of the
cloud-edge collaboration framework is a
challenging optimization problem. The
key issue is determining which tasks to
be processed at the edge of the network,
which data to be sent to the cloud
server, and which tasks to be processed
in the cloud server. This optimization
problem involves a large amount of data
and complex features, and EC algorithms
have great potential to solve this
problem efficiently.
F. Broader Application Scenes
The construction of smart cities is now
in its infancy. An increasing number of
optimization problems will emerge with
the construction of smart cities. First, the
three transportation modes (land, air, and
sea) are interrelated. EC algorithms can
be used to optimize the configuration of
an integrated transportation management
system that incorporates two or
three transportation modes. Second, the
integration of intelligent transportation
and other applications in smart cities will
yield many new optimization problems,
where EC algorithms can be promising
solvers. Indeed, many applications in
smart cities rely on the support of intelligent
transportation, such as intelligent
logistics and supply chain systems. Third,
self-driving technology has developed
rapidly in recent years, and many selfdriving
vehicles may be put into use in
the future. EC algorithms can be used to
solve traffic optimization problems in the
self-driving vehicle scenario.
VII. Conclusion
In this paper, a comprehensive survey of
the application of EC for intelligent
transportation in smart cities is conducted.
Related studies are classified by a
two-layer
taxonomy. The first
layer
includes three categories (i.e., land, air,
and sea transportation), which are based
on the application scene of the optimization
problem. In the second layer,
related studies from the perspectives of
government, business, and citizens based
on the objective of the optimization
problem are further classified. The related
studies in each category are discussed
in detail, showing that EC algorithms
are efficient for solving the optimization
problems of intelligent transportation in
smart cities. Several future research
directions and open issues are also presented.
This paper hopes to provide
researchers with a comprehensive overview
of EC for intelligent transportation
in smart cities and inspire researchers'
future work.
VIII. Acknowledgment
This work was supported in part by the
National Key Research and Develop98
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE | MAY 2022
ment Program of China under Grant
2019YFB2102102, in part by the
National Natural Science Foundations
of China under Grant 62176094 and
Grant 61873097, in part by the KeyArea
Research and Development of
Guangdong Province under Grant
2020B010166002, in part by the
Guangdong Natural Science Foundation
Research Team under Grant
2018B030312003, in part by the
National Research Foundation of Korea
(NRF-2021H1D3A2A01082705), and
in part by the Hong Kong GRF-RGC
General Research Fund under Grant
11209819 (CityU 9042816) and Grant
11203820 (CityU 9042598).
References
[1] H. Ritchie, " Urbanization, " OurWorldInData.org.
Accessed: Jan. 28, 2021. [Online]. Available: https://
ourworldindata.org/urbanization
[2] X. J. Yang, " China's rapid urbanization, " Science, vol.
342, no. 6156, p. 310, Oct. 2013.
[3] R. Du, P. Santi, M. Xiao, A. V. Vasilakos, and C.
Fischione, " The sensable city: A survey on the deployment
and management for smart city monitoring, " IEEE
Commun. Surveys Tuts., vol. 21, no. 2, pp. 1533-1560, 2nd
Quarterly 2019, doi: 10.1109/COMST.2018.2881008.
[4] H. Zhang, S. J. Moura, Z. Hu, and Y. Song, " PEV
fast-charging station siting and sizing on coupled transportation
and power networks, " IEEE Trans. Smart Grid,
vol. 9, no. 4, pp. 2595-2605, Jul. 2018, doi: 10.1109/
TSG.2016.2614939.
[5] J. K. Suhr and H. G. Jung, " Dense stereo-based robust
vertical road profile estimation using Hough transform
and dynamic programming, " IEEE Trans. Intell. Transp.
Syst., vol. 16, no. 3, pp. 1528-1536, Jun. 2015, doi:
10.1109/TITS.2014.2369002.
[6] " The world's cities, " United Nations, 2018. [Online].
Available: https://www.un.org/en/events/citiesday/assets/
pdf/the_worlds_cities_in_2018_data_booklet.pdf
[7] Z. H. Zhan, L. Shi, K. C. Tan, and J. Zhang, " A survey
on evolutionary computation for complex continuous
optimization, " Artif. Intell. Rev., to be published, doi:
10.1007/s10462-021-10042-y.
[8] L. Chen, K. Deb, and H. Liu, " Explicit control of
implicit parallelism in decomposition-based evolutionary
many-objective optimization algorithms, " IEEE Comput.
Intell. Mag., vol. 14, no. 4, pp. 52-64, Nov. 2019, doi:
10.1109/MCI.2019.2937612.
[9] K. C. Tan, L. Feng, and M. Jiang, " Evolutionary transfer
optimization: A new frontier in evolutionary computation
research, " IEEE Comput. Intell. Mag., vol. 16, no. 1,
pp. 22-33, Feb. 2021, doi: 10.1109/MCI.2020.3039066.
[10] J. Holland, " Genetic algorithm, " Sci. Amer., vol. 267,
no. 1, pp. 66-72, Jul. 1992, doi: 10.1038/scientificamerican
0792-66.
[11] R. Storn and K. V. Price, " Differential evolution-A
simple and efficient heuristic for global optimization over
continuous spaces, " J. Glob. Optim., vol. 11, no. 4, pp.
341-359, 1997.
[12] J. Kennedy and R. Eberhart, " Particle swarm optimization, "
in Proc. Int. Conf. Neural Netw., 1995, pp. 1942-1948.
[13] M. Dorigo, M. Birattari, and T. Stützle, " Ant colony
optimization, " IEEE Comput. Intell. Mag., vol. 1, no. 4,
pp. 28-39, Nov. 2006, doi: 10.1109/CI-M.2006.248054.
[14] E. Ahmed and H. Gharavi, " Cooperative vehicular
networking: A survey, " IEEE Trans. Intell. Transp. Syst.,
vol. 19, no. 3, pp. 996-1014, Mar. 2018, doi: 10.1109/
TITS.2018.2795381.
[15] C. Lin and D. Deng, " Optimal two-lane placement
for hybrid VANET-sensor networks, " IEEE Trans. Ind.
http://www.OurWorldInData.org http://www.ourworldindata.org/urbanization http://www.ourworldindata.org/urbanization https://www.un.org/en/events/citiesday/assets/pdf/the_worlds_cities_in_2018_data_booklet.pdf https://www.un.org/en/events/citiesday/assets/pdf/the_worlds_cities_in_2018_data_booklet.pdf
IEEE Computational Intelligence Magazine - May 2022

Table of Contents for the Digital Edition of IEEE Computational Intelligence Magazine - May 2022
