典型文献
Joint Access Point Selection and Resource Allocation in MEC-Assisted Network:A Reinforcement Learning Based Approach
文献摘要：
A distributed reinforcement learning(RL)based resource management framework is proposed for a mobile edge computing(MEC)system with both latency-sensitive and latency-insensitive services.We investigate joint optimization of both computing and radio resources to achieve efficient on-demand matches of multi-dimensional resources and diverse requirements of users.A multi-objective integer programming problem is formulated by two sub-problems,i.e.,access point(AP)selection and subcar-rier allocation,which can be solved jointly by our pro-posed distributed RL-based approach with a heuristic iteration algorithm.The proposed algorithm allows for the reduction in complexity since each user needs to consider only its own selection of AP without know-ing full global information.Simulation results show that our algorithm can achieve near-optimal perfor-mance while reducing computational complexity sig-nificantly.Compared with other algorithms that only optimize either of the two sub-problems,the proposed algorithm can serve more users with much less power consumption and content delivery latency.
文献关键词：
中图分类号：
作者姓名：
Zexu Li;Chunjing Hu;Wenbo Wang;Yong Li;Guiming Wei
作者机构：
Key Laboratory of Universal Wireless Communications,Beijing University of Posts and Telecommunications,Beijing 100876,China;China Academy of Information and Communications Technology,Beijing 100191,China
文献出处：
引用格式：
[1]Zexu Li;Chunjing Hu;Wenbo Wang;Yong Li;Guiming Wei-.Joint Access Point Selection and Resource Allocation in MEC-Assisted Network:A Reinforcement Learning Based Approach)[J].中国通信（英文版）,2022(06):205-218
A类：
subcar
B类：
Joint,Access,Point,Selection,Resource,Allocation,MEC,Assisted,Network,Reinforcement,Learning,Based,Approach,distributed,reinforcement,learning,RL,management,framework,proposed,mobile,edge,computing,system,both,latency,insensitive,services,We,investigate,optimization,radio,resources,achieve,efficient,demand,matches,multi,dimensional,diverse,requirements,users,objective,integer,programming,formulated,by,problems,access,point,AP,selection,rier,allocation,which,be,solved,jointly,approach,heuristic,iteration,allows,reduction,complexity,since,each,needs,consider,only,its,own,without,know,full,global,information,Simulation,results,show,that,near,optimal,perfor,mance,while,reducing,computational,sig,nificantly,Compared,other,algorithms,optimize,either,serve,more,much,less,power,consumption,content,delivery
AB值：
0.655713
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
