TY - GEN
T1 - Learning the CSI Denoising and Feedback Without Supervision
AU - Rizzello, Valentina
AU - Utschick, Wolfgang
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - In this work, we develop a joint denoising and feedback strategy for channel state information in frequency division duplex systems. In such systems, the biggest challenge is the overhead incurred when the mobile terminal has to send the downlink channel state information or corresponding partial information to the base station, where the complete estimates can subsequently be restored. To this end, we propose a novel learning-based framework for denoising and compression of channel estimates. Unlike existing studies, we extend a recently proposed approach and show that based solely on noisy uplink data available at the base station, it is possible to learn an autoencoder neural network that generalizes to downlink data. Subsequently, half of the autoencoder can be offloaded to the mobile terminals to generate channel feedback there as efficiently as possible, without any training effort at the terminals or corresponding transfer of training data. Numerical simulations demonstrate the excellent performance of the proposed method.
AB - In this work, we develop a joint denoising and feedback strategy for channel state information in frequency division duplex systems. In such systems, the biggest challenge is the overhead incurred when the mobile terminal has to send the downlink channel state information or corresponding partial information to the base station, where the complete estimates can subsequently be restored. To this end, we propose a novel learning-based framework for denoising and compression of channel estimates. Unlike existing studies, we extend a recently proposed approach and show that based solely on noisy uplink data available at the base station, it is possible to learn an autoencoder neural network that generalizes to downlink data. Subsequently, half of the autoencoder can be offloaded to the mobile terminals to generate channel feedback there as efficiently as possible, without any training effort at the terminals or corresponding transfer of training data. Numerical simulations demonstrate the excellent performance of the proposed method.
KW - Autoencoders
KW - Deep learning
KW - Denoising
KW - FDD systems
KW - Machine learning
KW - Massive MIMO
UR - http://www.scopus.com/inward/record.url?scp=85122779618&partnerID=8YFLogxK
U2 - 10.1109/SPAWC51858.2021.9593213
DO - 10.1109/SPAWC51858.2021.9593213
M3 - Conference contribution
AN - SCOPUS:85122779618
T3 - IEEE Workshop on Signal Processing Advances in Wireless Communications, SPAWC
SP - 16
EP - 20
BT - 2021 IEEE 22nd International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd IEEE International Workshop on Signal Processing Advances in Wireless Communications, SPAWC 2021
Y2 - 27 September 2021 through 30 September 2021
ER -