华南理工大学学报（自然科学版）2026，Vol.54Issue(4)：110-118,9.DOI:10.12141/j.issn.1000-565X.250238
动态电磁环境下RIS辅助的DRL抗干扰优化
DRL-Based Anti-Jamming Optimization Aided by RIS in Dynamic Electromagnetic Environments
摘要
Abstract
In complex electromagnetic environments,tactical wireless communication links face severe jamming threats,which can easily lead to communication disruption and adversely affect the stability and reliability of mis-sion execution.To improve the anti-jamming capability of wireless communication systems in dynamic interference scenarios,this paper proposes an adaptive anti-jamming architecture that integrates reconfigurable intelligent sur-face(RIS)with deep reinforcement learning(DRL).The proposed architecture improves the robustness of the com-munication link and the intelligence of decision-making from two dimensions:enhancing the strength of useful sig-nals and generating dynamic anti-jamming strategies.In terms of methodology,the system first leverages the beam-forming capability of RIS to actively manipulate the wireless propagation environment,thereby improving the chan-nel signal-to-noise ratio,effectively suppressing the interference,and accelerating the convergence of learning strat-egies.Next,frequency selection and power control are modeled as a Markov decision process.A greedy action se-lection strategy incorporating historical value estimation is introduced,thus forming a reinforcement learning frame-work based on double deep Q-networks with prioritized experience replay.The RIS-enhanced signal improves the stability of the learning strategy and significantly shortens the training period.Simulation results demonstrate that,in such typical jamming scenarios as wideband frequency sweeping,random pulse jamming and intelligent adver-sarial games,the proposed architecture achieves a certain degree of improvement in average communication success rate,as compared with the solutions that rely solely on deep reinforcement learning or RIS.These results validate the strong robustness and broad adaptability of the proposed architecture in highly dynamic environments.关键词
战术通信/抗干扰/深度强化学习/可重构智能超表面Key words
tactical communication/anti-jamming/deep reinforcement learning/reconfigurable intelligent surface分类
信息技术与安全科学引用本文复制引用
林玮,魏强,熊俊,周毅,蒋觉慧,郑天航,刘颢..动态电磁环境下RIS辅助的DRL抗干扰优化[J].华南理工大学学报（自然科学版）,2026,54(4):110-118,9.基金项目
国家自然科学基金项目(62071192) （62071192）
国家重点研发计划项目(2024YFE0103800) （2024YFE0103800）
山东省自然科学基金项目(ZR2022LZH006) Supported by the National Natural Science Foundation of China(62071192),the National Key Research and Development Program of China(2024YFE0103800)and the Natural Science Foundation of Shandong Province(ZR2022LZH006) （ZR2022LZH006）
