{"title":"DRL-Based Secure Beamforming for Hybrid-RIS Aided Satellite Downlink Communications","authors":"Q. Ngo, Khoa T. Phan, Abdun Mahmood, Wei Xiang","doi":"10.1109/COMNETSAT56033.2022.9994309","DOIUrl":null,"url":null,"abstract":"In this paper, a secure multiuser MISO satellite downlink communication system is considered with the assist of a hybrid reconfigurable intelligent surface (RIS). A robust satellite and RIS beamforming joint design is formulated to maximize the overall system secrecy rate. The RIS active and passive elements are optimized considering practical models of the outdated channel state information and power consumption. Deep reinforcement learning is leveraged to solve the highly dynamic and multidimensional beamforming design problem. Simulation results confirm the beamforming design effectiveness and the performance gains when exploiting hybrid-RIS over conventional passive RIS.","PeriodicalId":221444,"journal":{"name":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-11-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE International Conference on Communication, Networks and Satellite (COMNETSAT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/COMNETSAT56033.2022.9994309","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In this paper, a secure multiuser MISO satellite downlink communication system is considered with the assist of a hybrid reconfigurable intelligent surface (RIS). A robust satellite and RIS beamforming joint design is formulated to maximize the overall system secrecy rate. The RIS active and passive elements are optimized considering practical models of the outdated channel state information and power consumption. Deep reinforcement learning is leveraged to solve the highly dynamic and multidimensional beamforming design problem. Simulation results confirm the beamforming design effectiveness and the performance gains when exploiting hybrid-RIS over conventional passive RIS.
京公网安备 11010802042870号
京ICP备2023020795号-1
分享
求助内容：
应助结果提醒方式：
扫码关注我们
