Research Article
An Edge Server Placement Method with Cyber-Physical-Social Systems in 5G
@INPROCEEDINGS{10.1007/978-3-030-72795-6_11, author={Xing Zhang and Jielin Jiang and Lianyong Qi and Xiaolong Xu}, title={An Edge Server Placement Method with Cyber-Physical-Social Systems in 5G}, proceedings={Simulation Tools and Techniques. 12th EAI International Conference, SIMUtools 2020, Guiyang, China, August 28-29, 2020, Proceedings, Part II}, proceedings_a={SIMUTOOLS PART 2}, year={2021}, month={4}, keywords={CPSS Server placement Evolutionary algorithm Edge computing}, doi={10.1007/978-3-030-72795-6_11} }- Xing Zhang
Jielin Jiang
Lianyong Qi
Xiaolong Xu
Year: 2021
An Edge Server Placement Method with Cyber-Physical-Social Systems in 5G
SIMUTOOLS PART 2
Springer
DOI: 10.1007/978-3-030-72795-6_11
Abstract
Recently, cyber-physical-social systems (CPSS), an advanced information system, have been introduced to promote the development of the smart society. It makes the control of machines in all walks of life more intelligent in an efficient, convenient, and stable way. Besides, with the maturity of edge computing, the task requests emitted by users in CPSS are tent to be transmitted edge servers for immediate processing. Nevertheless, some problems, i.e., high latency and low utilization, exist in current network placement. It leads to the problem that users in the CPSS are unable to enjoy instant and efficient processing. Given these problems, this paper designs an edge server placement method (ESPM) to alleviate this situation. To be specific, a system model designed according to this scenario is presented firstly. Then, the multi-objective evolutionary algorithm, i.e., improving the strength pareto evolutionary algorithm (SPEA2), is applied in this paper to optimize the access delay and load balance variance with the propose of enhancing the service experience of users. Furthermore, the normalization methods, i.e., the technique for order preference by similarity to an ideal solution (TOPSIS) and multi-criteria decision-making (MCDM) are selected to produce the standard data and optimal strategy. Finally, the experimental results show the effectiveness of ESPM.
