智能系统学报2025，Vol.20Issue(2)：344-354,11.DOI:10.11992/tis.202312023
基于深度强化学习的电力线与无线双模通信MAC层接入算法
Adaptive MAC layer access algorithm for power line and wireless dual-mode communication based on deep reinforcement learning
摘要
Abstract
Aiming to address the issue of channel competition in hybrid networks of PLC and WC,this study proposes a MAC access algorithm based on deep reinforcement learning for dual-mode communication over power lines and wire-less channels.Dual-mode nodes adaptively access the dual-medium channel based on data such as network broadcast in-formation and channel usage.First,a dual-mode node data collection model is established based on interactions and stat-istical information from dual-mode communication networks.Then,the DRL state space,action space,and rewards are defined based on collaborative information,and an adaptive access algorithm is developed using a dual deep Q-network.This algorithm incorporates a node decision-making process that combines the α-fairness utility function with the P-per-sistent access mechanism.Finally,simulations and comparative analyses of the algorithm's performance are performed.Simulation results show that the proposed access algorithm effectively improves the access performance of dual-mode communication nodes while ensuring fairness in dual-mode network and channel access.关键词
电力线通信/无线通信/双模节点/深度强化学习/双深度Q网络/MAC层接入/公平效用函数/P坚持接入Key words
power line communication/wireless communication/dual-mode nodes/deep reinforcement learning/double deep Q-network/MAC layer access/fairness utility function/P-persistent access分类
信息技术与安全科学引用本文复制引用
陈智雄,詹学滋,左嘉烁..基于深度强化学习的电力线与无线双模通信MAC层接入算法[J].智能系统学报,2025,20(2):344-354,11.基金项目
国家自然科学基金青年基金项目(61601182) （61601182）
中央高校科研业务费专项资金项目(2023MS113). （2023MS113）
