TY - GEN
T1 - Deep learning based antenna selection and CSI extrapolation in massive MIMO systems
AU - Lin, Bo
AU - Gao, Feifei
AU - Zhang, Shun
AU - Zhou, Ting
AU - Alkhateeb, Ahmed
N1 - Funding Information:
ACKNOWLEDGMENT This work was supported in part by the National Natural Science Foundation of China under Grant 61831013 and Grant 61771274, and in part by Program of Shanghai Academic/Technology Research Leader and the Youth Innovation Promotion Association of Chinese Academy of Sciences (CAS).
Publisher Copyright:
© 2021 IEEE.
PY - 2021/7/28
Y1 - 2021/7/28
N2 - A critical bottleneck of massive multiple-input multiple-output (MIMO) system is the huge training overhead caused by downlink transmission, like channel estimation, downlink beamforming and covariance observation. In this paper, we propose to use the channel state information (CSI) of a small number of antennas to extrapolate the CSI of the other antennas and reduce the training overhead. Specifically, we design a deep neural network that we call an antenna domain extrapolation network (ADEN) that can exploit the correlation function among antennas. We then propose a deep learning (DL) based antenna selection network (ASN) that can select a limited antennas for optimizing the extrapolation, which is conventionally a type of combinatorial optimization and is difficult to solve. We trickly designed a constrained degradation algorithm to generate a differentiable approximation of the discrete antenna selection vector such that the back-propagation of the neural network can be guaranteed. Numerical results show that the proposed ADEN outperforms the traditional fully connected one, and the antenna selection scheme learned by ASN is much better than the trivially used uniform selection.
AB - A critical bottleneck of massive multiple-input multiple-output (MIMO) system is the huge training overhead caused by downlink transmission, like channel estimation, downlink beamforming and covariance observation. In this paper, we propose to use the channel state information (CSI) of a small number of antennas to extrapolate the CSI of the other antennas and reduce the training overhead. Specifically, we design a deep neural network that we call an antenna domain extrapolation network (ADEN) that can exploit the correlation function among antennas. We then propose a deep learning (DL) based antenna selection network (ASN) that can select a limited antennas for optimizing the extrapolation, which is conventionally a type of combinatorial optimization and is difficult to solve. We trickly designed a constrained degradation algorithm to generate a differentiable approximation of the discrete antenna selection vector such that the back-propagation of the neural network can be guaranteed. Numerical results show that the proposed ADEN outperforms the traditional fully connected one, and the antenna selection scheme learned by ASN is much better than the trivially used uniform selection.
UR - http://www.scopus.com/inward/record.url?scp=85119329074&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119329074&partnerID=8YFLogxK
U2 - 10.1109/ICCC52777.2021.9580209
DO - 10.1109/ICCC52777.2021.9580209
M3 - Conference contribution
AN - SCOPUS:85119329074
T3 - 2021 IEEE/CIC International Conference on Communications in China, ICCC 2021
SP - 962
EP - 966
BT - 2021 IEEE/CIC International Conference on Communications in China, ICCC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE/CIC International Conference on Communications in China, ICCC 2021
Y2 - 28 July 2021 through 30 July 2021
ER -