移动边缘计算中基于深度强化学习的任务迁移研究  

Research on Task Transfer Based on Deep Reinforcement Learning in Mobile Edge Computing

作　　者：李志强 朱晓娟[1] Li Zhiqiang;Zhu Xiaojuan(School of Computer Science and Engineering,Anhui University of Science and Technology,Huainan,Anhui 232001,China)

机构地区：[1]安徽理工大学计算机科学与工程学院,安徽淮南232001

出　　处：《黑龙江工业学院学报（综合版）》2024年第9期69-74,共6页Journal of Heilongjiang University of Technology(Comprehensive Edition)

基　　金：安徽高校省级自然科学研究重点项目(项目编号:KJ2020A0300)。

摘　　要：移动边缘计算将云计算能力推广至网络边缘,在移动用户周围提供服务。为了解决因用户移动与边缘节点覆盖范围有限而引起的服务中断问题,提出一种融合优先经验回放的深度确定性策略梯度的任务迁移算法。将任务处理时延与能耗作为优化目标,任务迁移与资源分配问题建模为马尔科夫决策过程,智能体根据提出的策略做出资源分配与迁移决策方案。仿真实验结果表明,设计的任务迁移策略在任务执行成功率和时延与能耗方面有着优越的表现。Mobile edge computing extends cloud computing capabilities to the edge of the network to deliver services around mobile users.In order to solve the problem of service interruption caused by user movement and limited coverage of edge nodes,this paper proposes a task migration algorithm that integrates the depth deterministic policy gradient of priority experience playback.In this paper,the task processing delay and energy consumption are taken as the optimization objectives,and the task migration and resource allocation problem are modeled as a Markov Decision Process,and the intelligent body makes the resource allocation and migration decision-making scheme according to the proposed policy.The results of simulation experiments show that the designed task migration strategy has superior performance in terms of task execution success rate and delay and energy consumption.

关 键 词：深度强化学习 边缘计算 移动性 任务迁移 

分 类 号：TN929.5[电子电信—通信与信息系统] TP18[电子电信—信息与通信工程]