Linear MIMO Precoders Design for Finite Alphabet Inputs via Model-Free Training

被引:0
作者
Cao, Chen [1 ]
Feng, Biqian [1 ]
Wu, Yongpeng [1 ]
Ng, Derrick Wing Kwan [2 ]
Zhang, Wenjun [1 ]
机构
[1] Shanghai Jiao Tong Univ, Dept Elect Engn, Shanghai 200240, Peoples R China
[2] Univ New South Wales, Sch Elect Engn & Telecommun, Sydney, NSW 2052, Australia
来源
2022 IEEE GLOBAL COMMUNICATIONS CONFERENCE (GLOBECOM 2022) | 2022年
基金
美国国家科学基金会; 国家重点研发计划;
关键词
Autoencoders; deep learning; finite alphabet; linear precoders; MIMO; OPTIMIZATION; SIGNALS;
D O I
10.1109/GLOBECOM48099.2022.10001528
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
This paper investigates a novel method for designing linear precoders with finite alphabet inputs based on autoencoders (AE) without the knowledge of the channel model. By model-free training of the autoencoder in a multiple-input multiple-output (MIMO) system, the proposed method can effectively solve the optimization problem to design the precoders that maximize the mutual information between the channel inputs and outputs, when only the input-output information of the channel can be observed. Specifically, the proposed method regards the receiver and the precoder as two independent parameterized functions in the AE and alternately trains them using the exact and approximated gradient, respectively. Compared with previous precoders design methods, it alleviates the limitation of requiring the explicit channel model to be known. Simulation results show that the proposed method works as well as those methods under known channel models in terms of maximizing the mutual information and reducing the bit error rate.
引用
收藏
页码:2407 / 2412
页数:6
相关论文
共 13 条
[1]   Model-Free Training of End-to-End Communication Systems [J].
Aoudia, Faycal Ait ;
Hoydis, Jakob .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2019, 37 (11) :2503-2516
[2]   Deep Learning Based Communication Over the Air [J].
Doerner, Sebastian ;
Cammerer, Sebastian ;
Hoydis, Jakob ;
ten Brink, Stephan .
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2018, 12 (01) :132-143
[3]   Massive MIMO Linear Precoding: A Survey [J].
Fatema, Nusrat ;
Hua, Guang ;
Xiang, Yong ;
Peng, Dezhong ;
Natgunanathan, Iynkaran .
IEEE SYSTEMS JOURNAL, 2018, 12 (04) :3920-3931
[4]   Linear MIMO Precoders With Finite Alphabet Inputs via Stochastic Optimization and Deep Neural Networks (DNNs) [J].
Jing, Shusen ;
Xiao, Chengshan .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2021, 69 :4269-4281
[5]   Zero-Forcing Per-Group Precoding for Robust Optimized Downlink Massive MIMO Performance [J].
Ketseoglou, Thomas ;
Ayanoglu, Ender .
IEEE TRANSACTIONS ON COMMUNICATIONS, 2019, 67 (10) :6816-6828
[6]  
Kingma DP, 2014, ADV NEUR IN, V27
[7]   Optimum power allocation for parallel Gaussian channels with arbitrary input distributions [J].
Lozano, Angel ;
Tulino, Antonia M. ;
Verdu, Sergio .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (07) :3033-3051
[8]   Linear Precoder Design for SWIPT in MIMO Broadcasting Systems With Discrete Input Signals: Manifold Optimization Approach [J].
Lu, An-An ;
Gao, Xiqi ;
Zheng, Yahong Rosa ;
Xiao, Chengshan .
IEEE TRANSACTIONS ON COMMUNICATIONS, 2017, 65 (07) :2877-2888
[9]   An Introduction to Deep Learning for the Physical Layer [J].
O'Shea, Timothy ;
Hoydis, Jakob .
IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING, 2017, 3 (04) :563-575
[10]   On optimal precoding in linear vector Gaussian channels with arbitrary input distribution [J].
Payaro, Miguel ;
Palomar, Daniel P. .
2009 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY, VOLS 1- 4, 2009, :1085-1089