Multi-agent reinforcement learning for edge information sharing in vehicular networks
作者机构：School of Communication and Information EngineeringChongqing University of Posts and TelecommunicationsChongqing400065China Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of ChinaChongqing400065China Key Laboratory of Ubiquitous Sensing and Networking in ChongqingChongqing400065China Peter the Great St.Petersburg Polytechnic UniversityPolytechnicheskaya29St.Petersburg195251Russia
出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)
年 卷 期：2022年第8卷第3期
页 面：267-277页
核心收录：
学科分类：0810[工学-信息与通信工程] 080904[工学-电磁场与微波技术] 0808[工学-电气工程] 0809[工学-电子科学与技术（可授工学、理学学位）] 0839[工学-网络空间安全] 08[工学] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 0835[工学-软件工程] 081001[工学-通信与信息系统] 0812[工学-计算机科学与技术（可授工学、理学学位）]
基 金：supported in part by the National Natural Science Foundation of China under grants 61901078,61771082,61871062,and U20A20157 in part by the Science and Technology Research Program of Chongqing Municipal Education Commission under grant KJQN201900609 in part by the Natural Science Foundation of Chongqing under grant cstc2020jcyj-zdxmX0024 in part by University Innovation Research Group of Chongqing under grant CXQT20017 in part by the China University Industry-University-Research Collaborative Innovation Fund(Future Network Innovation Research and Application Project)under grant 2021FNA04008
主 题：Vehicular networks Edge information sharing Delay guarantee Multi-agent reinforcement learning Proximal policy optimization
摘 要：To guarantee the heterogeneous delay requirements of the diverse vehicular services,it is necessary to design a full cooperative policy for both Vehicle to Infrastructure(V2I)and Vehicle to Vehicle(V2V)*** paper investigates the reduction of the delay in edge information sharing for V2V links while satisfying the delay requirements of the V2I ***,a mean delay minimization problem and a maximum individual delay minimization problem are formulated to improve the global network performance and ensure the fairness of a single user,respectively.A multi-agent reinforcement learning framework is designed to solve these two problems,where a new reward function is proposed to evaluate the utilities of the two optimization objectives in a unified ***,a proximal policy optimization approach is proposed to enable each V2V user to learn its policy using the shared global network *** effectiveness of the proposed approach is finally validated by comparing the obtained results with those of the other baseline approaches through extensive simulation experiments.
维普期刊数据库