Deep Learning for Beamspace Channel Estimation in Millimeter-Wave Massive MIMO Systems

被引:134
作者
Wei, Xiuhong [1 ,2 ]
Hu, Chen [1 ,2 ]
Dai, Linglong [1 ,2 ]
机构
[1] Tsinghua Univ, Beijing Natl Res Ctr Informat Sci & Technol BNRis, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
基金
中国国家自然科学基金;
关键词
Millimeter-wave (mmWave); massive MIMO; beamspace channel estimation; approximate message passing (AMP); deep learning; SPARSE; ARCHITECTURE;
D O I
10.1109/TCOMM.2020.3027027
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
Millimeter-wave massive multiple-input multiple-output (MIMO) can use a lens antenna array to considerably reduce the number of radio frequency (RF) chains, but channel estimation is challenging due to the number of RF chains is much smaller than that of antennas. By exploiting the sparsity of beamspace channels, the beamspace channel estimation can be formulated as a sparse signal recovery problem, which can be solved by the classical iterative algorithm named approximate message passing (AMP), and its corresponding version learned AMP (LAMP) realized by a deep neural network (DNN). However, these existing schemes cannot achieve satisfactory estimation accuracy. To improve the channel estimation performance, we propose a prior-aided Gaussian mixture LAMP (GM-LAMP) based beamspace channel estimation scheme in this paper. Specifically, based on the prior information that beamspace channel elements can be modeled by the Gaussian mixture distribution, we first derive a new shrinkage function to refine the AMP algorithm. Then, by replacing the original shrinkage function in the LAMP network with the derived Gaussian mixture shrinkage function, a prior-aided GM-LAMP network is developed to estimate the beamspace channel more accurately. Simulation results by using both the theoretical channel model and the ray-tracing based channel dataset show that, the proposed GM-LAMP network can achieve better channel estimation accuracy than existing schemes.
引用
收藏
页码:182 / 193
页数:12
相关论文
共 42 条
[11]  
Donoho D. L., 2010, P IEEE INF THEOR WOR, P1
[12]   Stable recovery of sparse overcomplete representations in the presence of noise [J].
Donoho, DL ;
Elad, M ;
Temlyakov, VN .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2006, 52 (01) :6-18
[13]   Structured Compressed Sensing: From Theory to Applications [J].
Duarte, Marco F. ;
Eldar, Yonina C. .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2011, 59 (09) :4053-4085
[14]   On sparse representations in arbitrary redundant bases [J].
Fuchs, JJ .
IEEE TRANSACTIONS ON INFORMATION THEORY, 2004, 50 (06) :1341-1344
[15]   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
[16]   Energy-Efficient Hybrid Analog and Digital Precoding for MmWave MIMO Systems With Large Antenna Arrays [J].
Gao, Xinyu ;
Dai, Linglong ;
Han, Shuangfeng ;
I, Chih-Lin ;
Heath, Robert W., Jr. .
IEEE JOURNAL ON SELECTED AREAS IN COMMUNICATIONS, 2016, 34 (04) :998-1009
[17]   Near-Optimal Beam Selection for Beamspace MmWave Massive MIMO Systems [J].
Gao, Xinyu ;
Dai, Linglong ;
Chen, Zhijie ;
Wang, Zhaocheng ;
Zhang, Zhijun .
IEEE COMMUNICATIONS LETTERS, 2016, 20 (05) :1054-1057
[18]   COMPRESSIVE SENSING TECHNIQUES FOR NEXT-GENERATION WIRELESS COMMUNICATIONS [J].
Gao, Zhen ;
Dai, Linglong ;
Han, Shuangfeng ;
I, Chih-Lin ;
Wang, Zhaocheng ;
Hanzo, Lajos .
IEEE WIRELESS COMMUNICATIONS, 2018, 25 (03) :144-153
[19]   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
[20]   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