Deep Learning for Multi-User MIMO Systems: Joint Design of Pilot, Limited Feedback, and Precoding

被引:20
作者
Jang, Jeonghyeon [1 ]
Lee, Hoon [2 ,3 ]
Kim, Il-Min [4 ]
Lee, Inkyu [1 ]
机构
[1] Korea Univ, Sch Elect Engn, Seoul 02841, South Korea
[2] Pukyong Natl Univ, Dept Smart Robot Convergence & Applicat Engn, Busan 48513, South Korea
[3] Pukyong Natl Univ, Dept Informat & Commun Engn, Busan 48513, South Korea
[4] Queens Univ, Dept Elect & Comp Engn, Kingston, ON K7L 3N6, Canada
基金
加拿大自然科学与工程研究理事会; 新加坡国家研究基金会;
关键词
Deep learning; MU-MIMO; precoder; limited feedback; ROBUST TRANSCEIVER OPTIMIZATION; BLOCK DIAGONALIZATION; CHANNEL INVERSION; MISO SYSTEMS; PART I; COMMUNICATION; MMSE; RECOVERY;
D O I
10.1109/TCOMM.2022.3209887
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
In conventional multi-user multiple-input multiple-output (MU-MIMO) systems with frequency division duplexing (FDD), channel acquisition and precoder optimization processes have been designed separately although they are highly coupled. This paper studies an end-to-end design of downlink MU-MIMO systems which include pilot sequences, limited feedback, and precoding. To address this problem, we propose a novel deep learning (DL) framework which jointly optimizes the feedback information generation at users and the precoder design at a base station (BS). Each procedure in the MU-MIMO systems is replaced by intelligently designed multiple deep neural networks (DNN) units. At the BS, a neural network generates pilot sequences and helps the users obtain accurate channel state information. At each user, the channel feedback operation is carried out in a distributed manner by an individual user DNN. Then, another BS DNN collects feedback information from the users and determines the MIMO precoding matrices. A joint training algorithm is proposed to optimize all DNN units in an end-to-end manner. In addition, a training strategy which can avoid retraining for different network sizes for a scalable design is proposed. Numerical results demonstrate the effectiveness of the proposed DL framework compared to classical optimization techniques and other conventional DNN schemes.
引用
收藏
页码:7279 / 7293
页数:15
相关论文
共 46 条
[1]  
3GPP NR, 2021, 38214V1660 3GPP
[2]   Limited Feedback Hybrid Precoding for Multi-User Millimeter Wave Systems [J].
Alkhateeb, Ahmed ;
Leus, Geert ;
Heath, Robert W., Jr. .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2015, 14 (11) :6481-6494
[3]  
Barshan E., 2015, Feature Extraction: Modern Questions and Challenges, P49
[4]   Robust Transceiver Optimization for Downlink Multiuser MIMO Systems [J].
Bogale, Tadilo Endeshaw ;
Chalise, Batu Krishna ;
Vandendorpe, Luc .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2011, 59 (01) :446-453
[5]   Joint User Selection, Power Allocation, and Precoding Design With Imperfect CSIT for Multi-Cell MU-MIMO Downlink Systems [J].
Choi, Jiwook ;
Lee, Namyoon ;
Hong, Song-Nam ;
Caire, Giuseppe .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2020, 19 (01) :162-176
[6]   A transmit preprocessing technique for multiuser MIMO systems using a decomposition approach [J].
Choi, LU ;
Murch, RD .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2004, 3 (01) :20-24
[7]   Weighted Sum-Rate Maximization using Weighted MMSE for MIMO-BC Beamforming Design [J].
Christensen, Soren Skovgaard ;
Agarwal, Rajiv ;
de Carvalho, Elisabeth ;
Cioffi, John M. .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2008, 7 (12) :4792-4799
[8]   Deep Learning-Based Channel Estimation for Massive MIMO Systems [J].
Chun, Chang-Jae ;
Kang, Jae-Mo ;
Kim, Il-Min .
IEEE WIRELESS COMMUNICATIONS LETTERS, 2019, 8 (04) :1228-1231
[9]   Multiple Antenna MMSE Based Downlink Precoding with Quantized Feedback or Channel Mismatch [J].
Dabbagh, Amir D. ;
Love, David J. .
IEEE TRANSACTIONS ON COMMUNICATIONS, 2008, 56 (11) :1859-1868
[10]   A Rate Splitting Strategy for Massive MIMO With Imperfect CSIT [J].
Dai, Mingbo ;
Clerckx, Bruno ;
Gesbert, David ;
Caire, Giuseppe .
IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2016, 15 (07) :4611-4624