移动通信2024，Vol.48Issue(6)：69-74,6.DOI:10.3969/j.issn.1006-1010.20240423-0002
基于强化学习的STAR-RIS辅助的通信抗干扰方法
STAR-RIS-assisted anti-Jamming Communication Based on Smooth Q-learning of Similar Action
摘要
Abstract
As one of the potential key technologies for the sixth generation(6G)mobile networks,simultaneously transmitting and reflecting reconfigurable intelligent surface(STAR-RIS)can simultaneously transmit and reflect incoming signals,achieving full-space coverage.This paper proposes a reinforcement learning-based anti-jamming method for STAR-RIS-assisted communication,utilizing the smooth Q-learning of similar action(SQSA)to jointly optimize the transmit power of base stations,active beamforming,and the passive beamforming of the STAR-RIS,significantly enhancing the anti-jamming performance of wireless transmission systems.Simulation results validate that the proposed SQSA method outperforms the conventional Q-learning algorithms in terms of the learning convergence speed and anti-jamming performance.关键词
通信抗干扰/可重构智能表面/强化学习/波束成形Key words
anti-jamming/STAR-RIS/reinforcement learning/beamforming分类
信息技术与安全科学引用本文复制引用
叶子绿,许魁,夏晓晨,邓诚,魏琛,谢威..基于强化学习的STAR-RIS辅助的通信抗干扰方法[J].移动通信,2024,48(6):69-74,6.基金项目
国家自然科学基金"通信定位一体去蜂窝大规模MIMO智能传输方法研究"(62071485),"面向低空空域的无定形大规模MIMO一体化感知与通信方法研究"(62271503) （62071485）
江苏省基础研究计划"天地融合卫星移动通信组网理论与技术"(BK20192002) （BK20192002）
江苏省自然科学基金"基于无定形网络的低空空域融合感知与通信方法研究"(BK20231485) （BK20231485）
