CsiNet-Plus Model with Truncation and Noise on CSI Feedback

Feng LIU  Xuecheng HE  Conggai LI  Yanli XU  

Publication
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E103-A   No.1   pp.376-381
Publication Date: 2020/01/01
Online ISSN: 1745-1337
DOI: 10.1587/transfun.2019EAL2123
Type of Manuscript: LETTER
Category: Communication Theory and Signals
Keyword: 
massive MIMO,  CSI feedback,  truncation,  channel noise,  deep learning,  

Full Text: FreePDF

Summary: 
For the frequency-division-duplex (FDD)-based massive multiple-input multiple-output (MIMO) systems, channel state information (CSI) feedback plays a critical role. Although deep learning has been used to compress the CSI feedback, some issues like truncation and noise still need further investigation. Facing these practical concerns, we propose an improved model (called CsiNet-Plus), which includes a truncation process and a channel noise process. Simulation results demonstrate that the CsiNet-Plus outperforms the existing CsiNet. The performance interchangeability between truncated decimal digits and the signal-to-noise-ratio helps support flexible configuration.