高云波,班宇豪,谢健骊,王宇哲,吕千惠

• 1:兰州交通大学自动化与电气工程学院
• 2:兰州交通大学电子与信息工程学院

摘要(Abstract)：

针对高速铁路环境中完美信道状态信息难以获取，导致可重构智能反射面(RIS)辅助的毫米波MIMO波束赋形算法性能恶化的问题，提出结合多普勒频移补偿的波束赋形方案。首先，利用列车轨道的可预测性，采用自适应卡尔曼滤波算法，获取视距路径的多普勒频移，以此设计RIS相移完成补偿；其次，将优化问题建模为频谱效率(SE)最大化问题，考虑列车运行数据的时间相关性，将算法的环境状态和动作的历史信息纳入算法的输入中，使用改进的双延迟深度确定性策略梯度(TD3)算法求解。仿真结果表明，所提方案能够有效降低多普勒频移对信号传输产生的不利影响，与TD3、流行优化和无RIS的高速铁路通信系统相比，SE分别提升9.83%、23.75%和39.15%。

关键词(KeyWords)： 高速铁路;可重构智能表面;波束赋形;深度强化学习;多普勒频移补偿

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(62161016);; 甘肃省自然科学基金(24JRRA227)

作者(Author): 高云波,班宇豪,谢健骊,王宇哲,吕千惠

参考文献(References)：

• [1] 王同军，李平，王万齐.智能高速铁路“模数驱动、轴面协同”理论研究及应用[J].铁道学报，2025,47(1):1-10.WNAG Tongjun,LI Ping,WNAG Wanqi.Research and Application of “Model-data Driven,Axial-plane Coordinated” Theory in Intelligent High-speed Railways[J].Journal of the China Railway Society,2025,47(1):1-10.
• [2] YANG B Q,YU Z Q,LAN J,et al.Digital Beamforming-based Massive MIMO Transceiver for 5G Millimeter-wave Communications [J].IEEE Transactions on Microwave Theory and Techniques,2018,66(7):3403-3418.
• [3] 李南希，朱剑驰，郭婧，等.可重构智能表面技术：研究进展、原型机及挑战 [J].无线电通信技术，2022,48(2):305-310.LI Nanxi,ZHU Jianchi,GUO Jing,et al.Reconfigurable Intelligent Surface:Research Progress,Prototypes and Challenges [J].Radio Communications Technology,2022,48(2):305-310.
• [4] 赵亚军，章嘉懿，艾渤.智能超表面技术在智能高铁通信场景的应用探讨 [J].中兴通讯技术，2021,27(4):36-43.ZHAO Yajun,ZHANG Jiayi,AI Bo.Applications of Reconfigurable Intelligent Surface in Smart High-speed Railway Communications [J].ZTE Technology Journal,2021,27(4):36-43.
• [5] 张泽鹏，李翠然，谢健骊，等.基于深度强化学习的高速铁路RIS-MIMO隐蔽波束赋形算法[J].铁道学报，2025,47(6):102-112.ZHANG Zepeng,LI Cuiran,XIE Jianli,et al.Research on RIS-MIMO Covert Beamforming Algorithm for High-speed Railways Based on Deep Reinforcement Learning[J].Journal of the China Railway Society,2025,47(6):102-112.
• [6] 马红兵，张平，杨帆，等.智能超表面技术展望与思考 [J].中兴通讯技术，2022,28(3):70-77.MA Hongbing,ZHANG Ping,YANG Fan,et al.Reflections on Reconfigurable Intelligent Surface Technology [J].ZTE Technology Journal,2022,28(3):70-77.
• [7] YUAN X J,ZHANG Y A,SHI Y M,et al.Reconfigurable-intelligent-surface Empowered Wireless Communications:Challenges and Opportunities [J].IEEE Wireless Communications,2021,28(2):136-143.
• [8] ZHOU G,PAN C H,REN H,et al.Robust Beamforming Design for Intelligent Reflecting Surface Aided MISO Communication Systems [J].IEEE Wireless Communications Letters,2020,9(10):1658-1662.
• [9] 孙艳华，乔兰，王朱伟，等.智能反射面辅助MIMO系统混合波束赋形算法 [J].北京邮电大学学报，2023,46(3):7-12.SUN Yanhua,QIAO Lan,WANG Zhuwei,et al.Hybrid Beamforming for Intelligent Reflecting Surface Assisted MIMO System [J].Journal of Beijing University of Posts and Telecommunications,2023,46(3):7-12.
• [10] ZHANG S W,ZHANG R.Capacity Characterization for Intelligent Reflecting Surface Aided MIMO Communication [J].IEEE Journal on Selected Areas in Communications,2020,38(8):1823-1838.
• [11] ZHANG K P,LIU C,WANG H,et al.An IRS-aided mmWave Massive MIMO Systems Based on Genetic Algorithm [C]//2020 IEEE 20th International Conference on Communication Technology (ICCT).Piscataway:IEEE,2020:288-293.
• [12] WU Q Q,ZHANG R.Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamforming [J].IEEE Transactions on Wireless Communications,2019,18(11):5394-5409.
• [13] 王长江，傅友华.IRS辅助毫米波MIMO系统波束赋形优化的低复杂度方案 [J].信号处理，2022,38(9):1965-1974.WANG Changjiang,FU Youhua.A Low-complexity Scheme for Beamforming Optimization of IRS-assisted mmWave MIMO System [J].Journal of Signal Processing,2022,38(9):1965-1974.
• [14] BAHINGAYI E E,LEE K.Low-complexity Beamforming Algorithms for IRS-aided Single-user Massive MIMO mmWave Systems [J].IEEE Transactions on Wireless Communications,2022,21(11):9200-9211.
• [15] 朱政宇，徐金雷，孙钢灿，等.基于IRS辅助的SWIPT物联网系统安全波束成形设计 [J].通信学报，2021,42(4):185-193.ZHU Zhengyu,XU Jinlei,SUN Gangcan,et al.Secure Beamforming Design for IRS-assisted SWIPT Internet of Things System [J].Journal on Communications,2021,42(4):185-193.
• [16] 郭海燕，杨震，邹玉龙，等.基于主被动波束成形联合优化的双RIS辅助抗干扰通信方法 [J].通信学报，2022,43(7):21-30.GUO Haiyan,YANG Zhen,ZOU Yulong,et al.Double-RIS Assisted Anti-jamming Communication Method Based on Joint Active and Passive Beamforming Optimization [J].Journal on Communications,2022,43(7):21-30.
• [17] GAO M L,AI B,NIU Y,et al.IRS-Assisted High-Speed Train Communications:Outage Probability Minimization with Statistical CSI [C]//ICC 2021 - IEEE International Conference on Communications.Piscataway:IEEE,2021:1-6.
• [18] GAO Y B,WANG Y Z,LI C R,et al.Research on Joint Beamforming of High-speed Railway Millimeter-wave MIMO Communication with Reconfigurable Intelligent Surface [J].Alexandria Engineering Journal,2023,74:317-326.
• [19] 张思伟，袁德成，王国刚.基于深度学习的智能表面毫米波MIMO信道估计 [J].无线电工程，2024,54(4):892-899.ZHANG Siwei,YUAN Decheng,WANG Guogang.Deep Learning-based Intelligent Surface Millimeter-wave MIMO Channel Estimation [J].Radio Engineering,2024,54(4):892-899.
• [20] HUANG H,XIA W C,XIONG J,et al.Unsupervised Learning-based Fast Beamforming Design for Downlink MIMO [J].IEEE Access,2018,7:7599-7605.
• [21] HUANG C W,MO R H,YUEN C.Reconfigurable Intelligent Surface Assisted Multiuser MISO Systems Exploiting Deep Reinforcement Learning [J].IEEE Journal on Selected Areas in Communications,2020,38(8):1839-1850.
• [22] YANG H L,XIONG Z H,ZHAO J,et al.Deep Reinforcement Learning-based Intelligent Reflecting Surface for Secure Wireless Communications [J].IEEE Transactions on Wireless Communications,2021,20(1):375-388.
• [23] XU J P,AI B.When mmWave High-speed Railway Networks Meet Reconfigurable Intelligent Surface:a Deep Reinforcement Learning Method [J].IEEE Wireless Communications Letters,2022,11(3):533-537.
• [24] ZHANG W L.A Beamforming Scheme with Doppler Suppression for High-mobility Wireless Communications [J].IEEE Wireless Communications Letters,2020,9(10):1768-1772.
• [25] BASAR E.Reconfigurable Intelligent Surfaces for Doppler Effect and Multipath Fading Mitigation [J].Frontiers in Communications and Networks,2021,2:672857.
• [26] WU W,WANG H,WANG W N,et al.Doppler Mitigation Method Aided by Reconfigurable Intelligent Surfaces for High-speed Channels [J].IEEE Wireless Communications Letters,2022,11(3):627-631.
• [27] WANG Y R,WANG G P,HE R S,et al.Doppler Shift and Channel Estimation for Intelligent Transparent Surface Assisted Communication Systems on High-speed Railways [J].IEEE Transactions on Communications,2023,71(7):4204-4215.
• [28] XU J P,AI B.Experience-driven Power Allocation Using Multi-agent Deep Reinforcement Learning for Millimeter-Wave High-speed Railway Systems [J].IEEE Transactions on Intelligent Transportation Systems,2022,23(6):5490-5500.
• [29] MENG F,LIU S H,HUANG Y M,et al.Learning-aided Beam Prediction in mmWave MU-MIMO Systems for High-speed Railway [J].IEEE Transactions on Communications,2022,70(1):693-706.
• [30] AKHLAGHI S,ZHOU N,HUANG Z Y.Adaptive Adjustment of Noise Covariance in Kalman Filter for Dynamic State Estimation [C]//2017 IEEE Power & Energy Society General Meeting.Piscataway:IEEE,2017:1-5.
• [31] GUO X F,CHEN Y B,WANG Y.Learning-based Robust and Secure Transmission for Reconfigurable Intelligent Surface Aided Millimeter Wave UAV Communications [J].IEEE Wireless Communications Letters,2021,10(8):1795-1799.