通信学报2024，Vol.45Issue(3)：244-257,14.DOI:10.11959/j.issn.1000-436x.2024058
移动边缘计算中基于图到序列深度强化学习的复杂任务部署策略
Graph-to-sequence deep reinforcement learning based complex task deployment strategy in MEC
摘要
Abstract
With the help of mobile edge computing(MEC)and network virtualization technology,the mobile terminals can offload the computing,storage,transmission and other resource required for executing various complex applications to the edge service nodes nearby,so as to obtain more efficient service experience.For edge service providers,the opti-mal energy consumption decision-making problem when deploying complex tasks was comprehensively investigated.Firstly,the problem of deploying complex tasks to multiple edge service nodes was modeled as a mixed integer pro-gramming(MIP)model,and then a deep reinforcement learning(DRL)solution strategy that integrated graph to se-quence was proposed.Potential dependencies between multiple subtasks through a graph-based encoder design were ex-tracted and learned,thereby automatically discovering common patterns of task deployment based on the available re-source status and utilization rate of edge service nodes,and ultimately quickly obtaining the deployment strategy with the optimal energy consumption.Compared with representative benchmark strategies in different network scales,the experi-mental results show that the proposed strategy is significantly superior to the benchmark strategies in terms of task de-ployment error ratio,total power consumption of MEC system,and algorithm solving efficiency.关键词
移动边缘计算/任务部署/深度强化学习/图神经网络Key words
mobile edge computing/task deployment/deep reinforcement learning/graph neural network分类
信息技术与安全科学引用本文复制引用
陈卓,操民涛,周致圆,黄欣,李彦..移动边缘计算中基于图到序列深度强化学习的复杂任务部署策略[J].通信学报,2024,45(3):244-257,14.基金项目
国家自然科学基金资助项目(No.62071077,No.61671096) The National Natural Science Foundation of China(No.62071077,No.61671096) （No.62071077,No.61671096）
