边缘计算中拥塞感知的接入网络与副本联合选择策略  

Congestion-aware joint access network and replica selection strategy in edge computing

作　　者：田荣倜 胡志刚[1] Tian Rongti;Hu Zhigang(School of Computer Science&Engineering,Central South University,Changsha 410083,China)

机构地区：[1]中南大学计算机学院,长沙410083

出　　处：《计算机应用研究》2023年第4期1178-1183,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(62172442)。

摘　　要：针对边缘计算中服务副本选择过程中多用户资源争用导致的服务质量降低的难题,提出了一种网络接入点选择和服务副本选择联合优化方法。首先,依据用户所在位置,贪心地为每条用户请求选择合适的网络接入点,以避免大量用户同时选择同一个基站而造成网络拥塞。其次,网络中存在多个服务副本,在服务副本选择阶段,依据每个副本的负载以及用户的移动路径,基于改进的免疫遗传算法为每条用户请求选择合适的服务副本,以期提高整个系统的运行效率。仿真实验结果表明,相比于已有方案,该策略能有效提高用户服务质量。This paper proposed a joint optimization method of network access point selection and service replica selection to address the challenge of service quality degradation caused by multi-user resource contention in edge computing.Firstly,it greedily selected the appropriate network access point for each user request depending on the user’s location.So as to avoid network congestion caused by a large number of users selecting the same access network simultaneously.Secondly,there were multiple service replicas in the network.In the service replica selection stage,it determined the appropriate service replica for each user request according to the load of each replica and the user’s mobility path,based on an improved immune genetic algorithm.Thus,it improved the operational efficiency of the whole system.The simulation experimental results demonstrate that the method can effectively improve the user service quality compared with the existing solutions.

关 键 词：副本选择 接入网络选择 移动性感知 拥塞感知 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]