Intelligent Resource Allocation for Multiaccess Edge Computing in 5G Ultra-Dense Slicing Network Using Federated Multiagent DDPG Algorithm
简介：Nowadays,advances in communication te-chnology and cloud computing have spawned a va-riety of smart mobile devices,which will generate a great amount of computing-intensive businesses,and require corresponding resources of computation and communication.Multiaccess edge computing(MEC)can offload computing-intensive tasks to the nearby edge servers,which alleviates the pressure of de-vices.Ultra-dense network(UDN)can provide effec-tive spectrum resources by deploying a large number of micro base stations.Furthermore,network slicing can support various applications in different commu-nication scenarios.Therefore,this paper integrates the ultra-dense network slicing and the MEC technology,and introduces a hybrid computing offloading strategy in order to satisfy various quality of service(QoS)of edge devices.In order to dynamically allocate limited resources,the above problem is formulated as multi-agent distributed deep reinforcement learning(DRL),which will achieve low overhead computation offload-ing strategy and real-time resource allocation deci-sions.In this context,federated learning is added to train DRL agents in a distributed manner,where each agent is dedicated to exploring actions composed of offloading decisions and allocating resources,so as to jointly optimize system delay and energy consump-tion.Simulation results show that the proposed learn-ing algorithm has better performance compared with other strategies in literature.展开
学者：GongYuPengweiJIANGHeXieWENWangChenxiXUPeijun
关键词：federated learningmultiaccess edge com-putingmutiagent deep reinforcement learningre-source allocationultra-dense slicing network
在线出版日期：2026-03-17 （网站首发日期）
