TY - GEN
T1 - A novel compression CSI feedback based on deep learning for FDD massive MIMO systems
AU - Wang, Yuting
AU - Zhang, Yibin
AU - Sun, Jinlong
AU - Gui, Guan
AU - Ohtsuki, Tomoaki
AU - Adachi, Fumiyuki
N1 - Funding Information:
This work is supported by the open research fund of the Key Laboratory of Dynamic Cognitive System of Electromagnetic Spectrum Space, Ministry of Industry and Information Technology under grant KF20202106.
Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Accurate channel state information (CSI) is necessary for frequency-division duplexing (FDD) massive multi-input multi-output (MIMO) systems. Existing deep learning-based CSI feedback methods, e.g., CSI sensing and recovery neural network (CsiNet), designed based on an autoencoder architecture, achieves higher feedback accuracy and reconstruction speed. However, this network needs to be retrained due to different communication scenarios and channel conditions, which is costly in practical deployment. To solve this problem, this paper proposes a deep learning-based modular adaptive multiple-rate (MAMR) compression CSI feedback framework. Extra padding modules are added at the base station to pad compressed CSI into different compression rates into the same dimensions, thereby realizing a general autoencoder performing variable-rate compression. Simulation results are given to confirm the effectiveness of the proposed method in terms of normalized mean square error.
AB - Accurate channel state information (CSI) is necessary for frequency-division duplexing (FDD) massive multi-input multi-output (MIMO) systems. Existing deep learning-based CSI feedback methods, e.g., CSI sensing and recovery neural network (CsiNet), designed based on an autoencoder architecture, achieves higher feedback accuracy and reconstruction speed. However, this network needs to be retrained due to different communication scenarios and channel conditions, which is costly in practical deployment. To solve this problem, this paper proposes a deep learning-based modular adaptive multiple-rate (MAMR) compression CSI feedback framework. Extra padding modules are added at the base station to pad compressed CSI into different compression rates into the same dimensions, thereby realizing a general autoencoder performing variable-rate compression. Simulation results are given to confirm the effectiveness of the proposed method in terms of normalized mean square error.
KW - CSI feedback
KW - Compression
KW - Deep learning
KW - General autoencoder
KW - Modular adaptive multiple-rate
UR - http://www.scopus.com/inward/record.url?scp=85119351412&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85119351412&partnerID=8YFLogxK
U2 - 10.1109/WCNC49053.2021.9417115
DO - 10.1109/WCNC49053.2021.9417115
M3 - Conference contribution
AN - SCOPUS:85119351412
T3 - IEEE Wireless Communications and Networking Conference, WCNC
BT - 2021 IEEE Wireless Communications and Networking Conference, WCNC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Wireless Communications and Networking Conference, WCNC 2021
Y2 - 29 March 2021 through 1 April 2021
ER -