MEC动态联合服务缓存和请求调度优化算法  

Dynamic joint optimization algorithm of service cache and request scheduling in mobile edge computing

作　　者：徐正超 黎作鹏 XU Zheng-chao;LI Zuo-peng(School of Information and Electrical Engineering,Hebei University of Engineering,Handan 056038,China)

机构地区：[1]河北工程大学信息与电气工程学院,河北邯郸056038

出　　处：《计算机工程与设计》2024年第5期1451-1457,共7页Computer Engineering and Design

基　　金：河北省高等学校科学技术研究基金项目(ZD2020171);江苏省博士后科研计划基金项目(1601085C)。

摘　　要：针对移动边缘计算(MEC)中边缘服务器资源有限,服务提供商面临如何充分利用稀缺的边缘资源最大化系统性能的问题,提出一种基于李雅普诺夫优化的动态优化算法。建立服务缓存和请求调度模型,得到在满足服务缓存成本的长期预算约束时最小化系统延迟的优化函数模型;利用李雅普诺夫优化技术将长期优化问题转化为多个连续时隙的实时优化问题,设计对偶分解算法求解实时优化问题。通过仿真实验验证了所提算法的有效性。Aiming at the limited edge server resources in mobile edge computing,service providers face the problem that how to make full use of scarce edge resources to maximize system performance,a dynamic optimization algorithm based on Lyapunov optimization was proposed.The model of service cache and request scheduling was established,and the optimization function model was obtained to minimize the system delay while satisfying the long-term budget constraint of service cache cost.Lyapunov optimization technique was used to transform the long-term optimization problem into a real-time optimization problem with multiple continuous time slots,and a dual decomposition algorithm was designed to solve the real-time optimization problem.The effectiveness of the proposed algorithm was verified by simulation experiments.

关 键 词：移动边缘计算 服务缓存 请求调度 协同计算 联合优化 李雅普诺夫函数 对偶分解算法 

分 类 号：TN929.5[电子电信—通信与信息系统] TP301.6[电子电信—信息与通信工程]