移动边缘网络中的多目标缓存优化方法  

Research on Multi-objective Cache Optimization Method in Mobile Edge Network

作　　者：吴越 薛钊煜 郭婉婉 崔志华[1] WU Yue;XUE Zhaoyu;GUO Wanwan;CUI Zhihua(College of Computer Science and Technology,Taiyuan University of Technology,Taiyuan 030024,China)

机构地区：[1]太原科技大学计算机科学与技术学院,太原030024

出　　处：《小型微型计算机系统》2024年第4期894-901,共8页Journal of Chinese Computer Systems

基　　金：国家自然科学基金青年科学基金项目(61806138)资助;中央引导地方科技发展项目(YDZJSX2021A038)资助;中国高校产学研创新基金-未来网络创新研究与应用项目(2021FNA04014)资助;山西省研究生教育创新项目(2022Y697)资助;太原科技大学研究生教育创新项目(SY2022061)资助.

摘　　要：随着5G时代的到来,各类移动应用蓬勃发展,用户量快速增长,大量的通信流量对移动边缘网络造成了巨大的压力,缓存资源紧张的问题逐渐凸显.为此,本文提出了一种基于多目标优化算法的移动边缘网络缓存放置策略,考虑包含一个宏基站和若干小基站的边缘网络,通过分析边缘网络缓存中不同利益相关方的需求,即用户平均延迟、缓存成本和传输功耗,以及缓存空间有限的约束条件,构建了多目标优化模型,为了求解模型,提出了一种基于最远交配和淘汰策略的多目标进化算法(MOEA-FMES).通过模拟仿真实验与其他常见多目标优化算法进行了对比,结果表明MOEA-FMES优于对比算法,能够给出一组质量较高、收敛性较好且分布均匀的解,证明了所提出方法的有效性.With the arrival of the 5G era,all kinds of mobile applications are booming and the number of users is growing rapidly.A large amount of communication traffic has caused huge pressure on the mobile edge network,and the shortage of cache resources has gradually become prominent.Therefore,this paper proposes a cache placement strategy for mobile edge networks based on a multi-objective optimization algorithm.Considering the edge network containing one macro station and several small base stations,a multi-objective optimization model is constructed by analyzing the demands of different stakeholders in edge network cache,namely,the average user delay,cache cost and transmission power consumption,and the constraint conditions of limited cache space.To solve the model,a multi-objective evolutionary algorithm(MOEA-FMES)based on the farthest mating and elimination strategy is proposed.The simulation results show that MOEA-FMES is superior to other common multi-objective optimization algorithms,and can give a set of solutions with higher quality,better convergence,and uniform distribution,which proves the effectiveness of the proposed method.

关 键 词：多目标 移动边缘计算 缓存策略 进化算法 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]