An AMP-Based Network With Deep Residual Learning for mmWave Beamspace Channel Estimation

被引：43

作者：

Wei, Yi ^{[1
]}

Zhao, Ming-Min ^{[1
]}

Zhao, Minjian ^{[1
]}

Lei, Ming ^{[1
]}

Yu, Quan ^{[2
]}

机构：

[1] Zhejiang Univ, Coll Informat Sci & Elect Engn, Hangzhou 310027, Zhejiang, Peoples R China

[2] Inst China Elect Equipment Syst Engn Corp, Beijing 100141, Peoples R China

来源：

IEEE WIRELESS COMMUNICATIONS LETTERS | 2019年 / 8卷 / 04期

关键词：

AMP; beamspace channel estimation; deep residual learning; massive MIMO; mmWave communication; MILLIMETER-WAVE MIMO; SYSTEMS;

D O I：

10.1109/LWC.2019.2916786

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Beamspace channel estimation in millimeter-wave (mmWave) massive MIMO system is a very challenging task, especially when the number of radio-frequency chains is limited. To address this problem, we present a novel approximate message passing (AMP)-based network with deep residual learning, referred to as LampResNet. It mainly consists of two components: 1) a learned AMP (LAMP) network and 2) a deep residual learning network (ResNet). The former utilizes the sparsity property of beamspace channel matrix and is employed to obtain a preliminary estimation result, while the latter is designed to reduce the impact of channel noise and further refine the coarse estimation obtained by the LAMP network. Simulation results validate the efficiency of the proposed network.

引用

页码：1289 / 1292

页数：4

共 17 条

[1]

[Anonymous], 2017, ARXIV170205743

[2] Compressed Channel Sensing: A New Approach to Estimating Sparse Multipath Channels [J].

Bajwa, Waheed U. ;

Haupt, Jarvis ;

Sayeed, Akbar M. ;

Nowak, Robert .

PROCEEDINGS OF THE IEEE, 2010, 98 (06) :1058-1076

[3]

Borgerding M, 2016, IEEE GLOB CONF SIG, P227, DOI 10.1109/GlobalSIP.2016.7905837

[4] Reliable Beamspace Channel Estimation for Millimeter-Wave Massive MIMO Systems with Lens Antenna Array [J].

Gao, Xinyu ;

Dai, Linglong ;

Han, Shuangfeng ;

Chih-Lin, I ;

Wang, Xiaodong .

IEEE TRANSACTIONS ON WIRELESS COMMUNICATIONS, 2017, 16 (09) :6010-6021

[5] Large-Scale Antenna Systems with Hybrid Analog and Digital Beamforming for Millimeter Wave 5G [J].

Han, Shuangfeng ;

Chih-Lin, I ;

Xu, Zhikun ;

Rowell, Corbett .

IEEE COMMUNICATIONS MAGAZINE, 2015, 53 (01) :186-194

[6] Deep Learning-Based Channel Estimation for Beamspace mmWave Massive MIMO Systems [J].

He, Hengtao ;

Wen, Chao-Kai ;

Jin, Shi ;

Li, Geoffrey Ye .

IEEE WIRELESS COMMUNICATIONS LETTERS, 2018, 7 (05) :852-855

[7]

He KM, 2015, PROC CVPR IEEE, P5353, DOI 10.1109/CVPR.2015.7299173

[8]

Jayanthi PN, 2016, 2016 IEEE INTERNATIONAL CONFERENCE ON RECENT TRENDS IN ELECTRONICS, INFORMATION & COMMUNICATION TECHNOLOGY (RTEICT), P1060, DOI 10.1109/RTEICT.2016.7807993

[9] ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements [J].

Kulkarni, Kuldeep ;

Lohit, Suhas ;

Turaga, Pavan ;

Kerviche, Ronan ;

Ashok, Amit .

2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :449-458

[10] MIMO OFDM Channel Estimation via Block Stagewise Orthogonal Matching Pursuit [J].

Lee, Dongjae .

IEEE COMMUNICATIONS LETTERS, 2016, 20 (10) :2115-2118

← 1 2 →