Unsupervised Deep Learning for Massive MIMO Hybrid Beamforming

被引:65
作者
Hojatian, Hamed [1 ]
Nadal, Jeremy [1 ]
Frigon, Jean-Francois [1 ]
Leduc-Primeau, Francois [1 ]
机构
[1] Polytech Montreal, Dept Elect Engn, Montreal, PQ H3T 1J4, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Array signal processing; Massive MIMO; Radio frequency; Wireless communication; Training; Hybrid power systems; Complexity theory; hybrid beamforming; beam training; deep learning; unsupervised learning; CHANNEL ESTIMATION; WIRELESS; DESIGN; SYSTEMS; ANALOG;
D O I
10.1109/TWC.2021.3080672
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Hybrid beamforming is a promising technique to reduce the complexity and cost of massive multiple-input multiple-output (MIMO) systems while providing high data rate. However, the hybrid precoder design is a challenging task requiring channel state information (CSI) feedback and solving a complex optimization problem. This paper proposes a novel RSSI-based unsupervised deep learning method to design the hybrid beamforming in massive MIMO systems. Furthermore, we propose i) a method to design the synchronization signal (SS) in initial access (IA); and ii) a method to design the codebook for the analog precoder. We also evaluate the system performance through a realistic channel model in various scenarios. We show that the proposed method not only greatly increases the spectral efficiency especially in frequency-division duplex (FDD) communication by using partial CSI feedback, but also has near-optimal sum-rate and outperforms other state-of-the-art full-CSI solutions.
引用
收藏
页码:7086 / 7099
页数:14
相关论文
共 41 条
[1]   Wireless Energy Beamforming Using Received Signal Strength Indicator Feedback [J].
Abeywickrama, Samith ;
Samarasinghe, Tharaka ;
Ho, Chin Keong ;
Yuen, Chau .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2018, 66 (01) :224-235
[2]   Contribution of the Zubair source rocks to the generation and expulsion of oil to the reservoirs of the Mesopotamian Basin, Southern Iraq [J].
Al-Khafaji, Amer Jassim ;
Sadooni, Fadhil ;
Hindi, Mohammed Hadi .
PETROLEUM SCIENCE AND TECHNOLOGY, 2019, 37 (08) :940-949
[3]   Channel Estimation and Hybrid Precoding for Millimeter Wave Cellular Systems [J].
Alkhateeb, Ahmed ;
El Ayach, Omar ;
Leus, Geert ;
Heath, Robert W., Jr. .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2014, 8 (05) :831-846
[4]   What Will 5G Be? [J].
Andrews, Jeffrey G. ;
Buzzi, Stefano ;
Choi, Wan ;
Hanly, Stephen V. ;
Lozano, Angel ;
Soong, Anthony C. K. ;
Zhang, Jianzhong Charlie .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2014, 32 (06) :1065-1082
[5]   Massive MIMO: Ten Myths and One Critical Question [J].
Bjornson, Emil ;
Larsson, Erik G. ;
Marzetta, Thomas L. .
IEEE COMMUNICATIONS MAGAZINE, 2016, 54 (02) :114-123
[6]   Optimal Multiuser Transmit Beamforming: A Difficult Problem with a Simple Solution Structure [J].
Bjornson, Emil ;
Bengtsson, Mats ;
Ottersten, Bjorn .
IEEE SIGNAL PROCESSING MAGAZINE, 2014, 31 (04) :142-148
[7]  
Chuan L, 2007, ICNC 2007: THIRD INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, VOL 3, PROCEEDINGS, P823
[8]  
Dereniowski D, 2004, LECT NOTES COMPUT SC, V3019, P985
[9]   Deep CNN-Based Channel Estimation for mmWave Massive MIMO Systems [J].
Dong, Peihao ;
Zhang, Hua ;
Li, Geoffrey Ye ;
Gaspar, Ivan Simoes ;
NaderiAlizadeh, Navid .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2019, 13 (05) :989-1000
[10]   Spatially Sparse Precoding in Millimeter Wave MIMO Systems [J].
El Ayach, Omar ;
Rajagopal, Sridhar ;
Abu-Surra, Shadi ;
Pi, Zhouyue ;
Heath, Robert W., Jr. .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2014, 13 (03) :1499-1513