Security Isolation Algorithm of 5G Network Slice Based on Particle Swarm Optimization

被引:0
|
作者
Su, Yang [1 ,2 ]
Cao, Yang [1 ]
Tao, Wenwei [1 ]
Zhang, Wenzhe [1 ]
机构
[1] Power Dispatching and Control Center, China Southern Power Grid, Guangdong, Guangzhou,510000, China
[2] School of Computer Science and Engineering, South China University of Technology, Guangdong, Guangzhou,510000, China
来源
Engineering Intelligent Systems | 2024年 / 32卷 / 04期
关键词
5G mobile communication systems - Mobile security - Particle swarm optimization (PSO) - Queueing networks - Resource allocation;
D O I
暂无
中图分类号
学科分类号
摘要
Network slicing, an important feature of 5G (Fifth Generation of Mobile Communications Technology), is widely used in various business scenarios, and it has become increasingly important to address the accompanying security isolation problem. Different network slicing needs to handle different types of data traffic, and there are strict requirements for the security guarantee of each network slicing. In this paper, a 5G network slice security isolation algorithm based on particle swarm optimization, is proposed. This study analyzed the security requirements of different vertical industries for network slicing, including resource isolation and communication privacy protection, and designed a resource allocation model suitable for 5G network slicing, taking into account the security isolation requirements and resource competition relationships of different slicing. Finally, based on the communication strategy optimization method using particle swarm optimization, a 5G network slice test was carried out on a front-line intelligent city system to ensure the communication privacy and security between slices. The experimental results showed that the average bandwidth utilization rate of the 5G network slice security isolation algorithm based on particle swarm optimization was 85%; the effect benefit ratio was 90%, and the average delay was 20 milliseconds. The average bandwidth utilization without optimization scheme was 70%; the cost-effectiveness ratio was 69%, and the average delay was 36 milliseconds. These results showed that particle swarm optimization provided 5G network slice security isolation algorithm with better security performance, faster response speed, lower resource consumption, and stronger robustness and resilience. This algorithm can effectively improve the security and performance of a 5G network slice, and provide users with more reliable services. © 2024 CRL Publishing Ltd.
引用
收藏
页码:319 / 328
相关论文
共 50 条
  • [31] Traffic analysis for 5G network slice based on machine learning
    Xie, Feng
    Wei, Dongxue
    Wang, Zhencheng
    EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING, 2021, 2021 (01)
  • [32] A Blockchain-Based Network Slice Broker for 5G Services
    Nour, Boubakr
    Ksentini, Adlen
    Herbaut, Nicolas
    Frangoudis, Pantelis A.
    Moungla, Hassine
    IEEE Networking Letters, 2019, 1 (03): : 99 - 102
  • [33] MEC Application Slice and Its collaboration with 5G network slice
    Zhu, Hongmei
    Liu, Jie
    Lin, Yilin
    Wang, Qingyang
    2022 IEEE INTERNATIONAL SYMPOSIUM ON BROADBAND MULTIMEDIA SYSTEMS AND BROADCASTING (BMSB), 2022,
  • [34] Security Analysis of 5G Network
    Khan, John A.
    Chowdhury, Minhaz
    2021 IEEE INTERNATIONAL CONFERENCE ON ELECTRO INFORMATION TECHNOLOGY (EIT), 2021, : 1 - 6
  • [35] Road network matching method based on particle swarm optimization algorithm
    Yang, Lin
    Fang, Fang
    Dai, Songling
    Wan, Bo
    Zuo, Zejun
    Open Cybernetics and Systemics Journal, 2014, 8 (01): : 1286 - 1292
  • [36] Distribution network reconfiguration based on modified particle swarm optimization algorithm
    Wang, Cui-Ru
    Zhang, Yun-E
    PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2006, : 2076 - +
  • [37] Transmission network expansion planning based on the particle swarm optimization algorithm
    Ren, P
    Li, N
    Gao, LQ
    Lin, ZL
    Li, Y
    Proceedings of 2005 International Conference on Construction & Real Estate Management, Vols 1 and 2: CHALLENGE OF INNOVATION IN CONSTRUCTION AND REAL ESTATE, 2005, : 1413 - 1416
  • [38] An improved particle swarm optimization based training algorithm for neural network
    Zhao, FQ
    Hong, Y
    Yu, DM
    Yang, YH
    ICMIT 2005: INFORMATION SYSTEMS AND SIGNAL PROCESSING, 2005, 6041
  • [39] Electric power communication network based on particle swarm optimization algorithm
    Xiaomeng P.
    International Journal of Simulation: Systems, Science and Technology, 2016, 17 (17): : 8.1 - 8.5
  • [40] New network congestion control algorithm based on particle swarm optimization
    Lu, Jin-Jun
    Wang, Zhi-Quan
    Tien Tzu Hsueh Pao/Acta Electronica Sinica, 2007, 35 (08): : 1446 - 1451