多边缘服务器协作环境下基于时延感知的服务选择算法

Service Selection Algorithm Based on Latency-Aware in a Multiple Edge Server Cooperation Environment

移动边缘计算可为用户提供低时延的服务.然而,随着用户的需求变得日益复杂多样,单个边缘服务器难以满足其需求.因此,多边缘服务器协作环境下的服务选择问题成为服务计算领域的热点难题.本文首先将该问题建模成带约束的最优化问题,然后提出了一种启发式的服务选择算法-LLMES算法.该算法是在边缘服务器网络中根据迪杰斯特拉算法求解当前本地服务器的邻居节点作为候选服务器,并基于低时延多有效服务的贪心选择策略选择为用户提供有效服务最多且时延最小的服务器作为当前最优服务器.从而选择出一组相互协作的边缘服务器集合共同为用户提供服务,即选中一组满足用户需求的服务.最后,实验结果表明本文提出的LLMES算法性能明显优于其他3种具有代表性的算法.

Mobile edge computing can provide low latency services for users.However,as the requirements of users become increasingly complex and diverse,it is difficult for a single edge server to meet their needs.Therefore,the service selection problem in a multiple edge server cooperation environment has become a hot issue in the field of service computing.In this paper,the problem is modeled as a constrained optimization problem,and then a heuristic service selection algorithm named the LLMES algorithm is proposed.The algorithm selects the neighbor nodes of the current local server as candidate servers according to the Dijkstra algorithm in the edge server network,chooses an edge server that provides the most effective services with the least latency for users as the current optimal server based on the greedy selection strategy of low latency and multiple effective services.Thus,a group of cooperative edge servers is selected to provide services for users,that is,a group of services that meet the requirement of users is selected.Finally,experimental results show that the performance of the LLMES algorithm proposed in this paper outperforms significantly three representative approaches.