Learning to Estimate RIS-Aided mmWave Channels

被引:21
作者
He, Jiguang [1 ,2 ]
Wymeersch, Henk [3 ]
Di Renzo, Marco [4 ]
Juntti, Markku [1 ]
机构
[1] Univ Oulu, Ctr Wireless Commun, Oulu 90014, Finland
[2] Macau Univ Sci & Technol, Int Inst Next Generat Internet, Taipa 999078, Macao, Peoples R China
[3] Chalmers Univ Technol, Dept Elect Engn, S-41296 Gothenburg, Sweden
[4] Univ Paris Saclay, Lab Signaux & Syst, Cent Supelec, CNRS, F-91192 Gif Sur Yvette, France
基金
芬兰科学院; 欧盟地平线“2020”;
关键词
Channel estimation; Training; Phase control; MIMO communication; Radio frequency; Optimization; Neural networks; Deep unfolding; reconfigurable intelligent surface; cascaded channel estimation; deep neural network; RECONFIGURABLE INTELLIGENT SURFACES;
D O I
10.1109/LWC.2022.3147250
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Inspired by the remarkable learning and prediction performance of deep neural networks (DNNs), we apply one special type of DNN framework, known as model-driven deep unfolding neural network, to reconfigurable intelligent surface (RIS)-aided millimeter wave (mmWave) single-input multiple-output (SIMO) systems. We focus on uplink cascaded channel estimation, where known and fixed base station combining and RIS phase control matrices are considered for collecting observations. To boost the estimation performance and reduce the training overhead, the inherent channel sparsity of mmWave channels is leveraged in the deep unfolding method. It is verified that the proposed deep unfolding network architecture can outperform the least squares (LS) method with a relatively smaller training overhead and online computational complexity.
引用
收藏
页码:841 / 845
页数:5
相关论文
共 15 条
[1]   Wireless Communications Through Reconfigurable Intelligent Surfaces [J].
Basar, Ertugrul ;
Di Renzo, Marco ;
De Rosny, Julien ;
Debbah, Merouane ;
Alouini, Mohamed-Slim ;
Zhang, Rui .
IEEE ACCESS, 2019, 7 :116753-116773
[2]   Harnessing Structures in Big Data via Guaranteed Low-Rank Matrix Estimation Recent theory and fast algorithms via convex and nonconvex optimization [J].
Chen, Yudong ;
Chi, Yuejie .
IEEE SIGNAL PROCESSING MAGAZINE, 2018, 35 (04) :14-31
[3]   Smart Radio Environments Empowered by Reconfigurable Intelligent Surfaces: How It Works, State of Research, and The Road Ahead [J].
Di Renzo, Marco ;
Zappone, Alessio ;
Debbah, Merouane ;
Alouini, Mohamed-Slim ;
Yuen, Chau ;
de Rosny, Julien ;
Tretyakov, Sergei .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2020, 38 (11) :2450-2525
[4]   Smart radio environments empowered by reconfigurable AI meta-surfaces: an idea whose time has come [J].
Di Renzo, Marco ;
Debbah, Merouane ;
Dinh-Thuy Phan-Huy ;
Zappone, Alessio ;
Alouini, Mohamed-Slim ;
Yuen, Chau ;
Sciancalepore, Vincenzo ;
Alexandropoulos, George C. ;
Hoydis, Jakob ;
Gacanin, Haris ;
de Rosny, Julien ;
Bounceur, Ahcene ;
Lerosey, Geoffroy ;
Fink, Mathias .
EURASIP JOURNAL ON WIRELESS COMMUNICATIONS AND NETWORKING, 2019, 2019 (1)
[5]   Deep Channel Learning for Large Intelligent Surfaces Aided mm-Wave Massive MIMO Systems [J].
Elbir, Ahmet M. ;
Papazafeiropoulos, Anastasios ;
Kourtessis, Pandelis ;
Chatzinotas, Symeon .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2020, 9 (09) :1447-1451
[6]  
Gregor K., 2010, P 27 INT C INT C MAC, P399
[7]  
He J., 2020, PROC IEEE 91 VEH TEC, P1
[8]   Channel Estimation for RIS-Aided mmWave MIMO Systems via Atomic Norm Minimization [J].
He, Jiguang ;
Wymeersch, Henk ;
Juntti, Markku .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2021, 20 (09) :5786-5797
[9]   Fairness-Aware Multiuser Scheduling for Finite-Resolution Intelligent Reflecting Surface-Assisted Communication [J].
Li, Dong .
IEEE COMMUNICATIONS LETTERS, 2021, 25 (07) :2395-2399
[10]   Using Any Surface to Realize a New Paradigm for Wireless Communications [J].
Liaskos, Christos ;
Tsiollaridou, Ageliki ;
Pitsillides, Andreas ;
Ioannidis, Sotiris ;
Akyildiz, Ian .
COMMUNICATIONS OF THE ACM, 2018, 61 (11) :30-33