Channel Estimation for RIS-Assisted Time-Varying MIMO System: An Attention-Based Learning Approach

IF 5.3 2区 计算机科学 Q1 TELECOMMUNICATIONS
Ziwei Qi;Da Liu;Jingbo Zhang
{"title":"Channel Estimation for RIS-Assisted Time-Varying MIMO System: An Attention-Based Learning Approach","authors":"Ziwei Qi;Da Liu;Jingbo Zhang","doi":"10.1109/TGCN.2024.3410049","DOIUrl":null,"url":null,"abstract":"The challenges of time-varying channel estimation in reconfigurable intelligent surface (RIS)-based MIMO systems are focused on in this paper. We propose a scheme based on deep learning, which includes RIS element selection model (RESM) and a full channel estimation model (FCEM). Firstly, The RESM is designed for choosing the optimal subset of all RIS elements to reduce system overhead. A convolutional network based scorer is established to evaluate relationship between optimal partial channels and full channels, and the differential Top-N operation is used to select the optimal subset of RIS elements, where perturbed maximum method is utilized to ensure end-to-end learning is feasible. Then, the FCEM is developed to realize accurate time-varying channel estimation by exploiting the strong nonlinear fitting capability of attention based deep networks. We develop network structures including improved transformers and residual blocks in the FCEM to counteract the channels’ stochastic characteristic, so as to recover the full channels corresponding to the optimal subset. The numerical results demonstrate the proposed scheme outperforms the benchmark schemes under various comparison conditions and is suitable for high-speed mobile scenarios.","PeriodicalId":13052,"journal":{"name":"IEEE Transactions on Green Communications and Networking","volume":"9 1","pages":"140-151"},"PeriodicalIF":5.3000,"publicationDate":"2024-06-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Green Communications and Networking","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10549947/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"TELECOMMUNICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

The challenges of time-varying channel estimation in reconfigurable intelligent surface (RIS)-based MIMO systems are focused on in this paper. We propose a scheme based on deep learning, which includes RIS element selection model (RESM) and a full channel estimation model (FCEM). Firstly, The RESM is designed for choosing the optimal subset of all RIS elements to reduce system overhead. A convolutional network based scorer is established to evaluate relationship between optimal partial channels and full channels, and the differential Top-N operation is used to select the optimal subset of RIS elements, where perturbed maximum method is utilized to ensure end-to-end learning is feasible. Then, the FCEM is developed to realize accurate time-varying channel estimation by exploiting the strong nonlinear fitting capability of attention based deep networks. We develop network structures including improved transformers and residual blocks in the FCEM to counteract the channels’ stochastic characteristic, so as to recover the full channels corresponding to the optimal subset. The numerical results demonstrate the proposed scheme outperforms the benchmark schemes under various comparison conditions and is suitable for high-speed mobile scenarios.
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Green Communications and Networking
IEEE Transactions on Green Communications and Networking Computer Science-Computer Networks and Communications
CiteScore
9.30
自引率
6.20%
发文量
181
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信