Binary Neural Network Aided CSI Feedback in Massive MIMO System
Zhilin Lu, Jintao Wang, Jian Song
Abstract
In massive multiple-input multiple-output (MIMO) system, channel state information (CSI) is essential for the base station (BS) to achieve high performance gain. The CSI matrix needs to be estimated and fed back from user equipment (UE) in frequency division duplexing (FDD) mode. Recently, deep learning is widely used in CSI compression to reduce the feedback overhead. However, applying neural network brings extra memory and computation cost, which is non-negligible especially for the resource limited UE. In this letter, a novel binarization aided feedback network named BCsiNet is introduced to lighten the encoder at UE. The proposed BCsiNet offers over 30× memory saving and around 2× inference acceleration for the encoder compared with CsiNet. Moreover, experiments show that the feedback performance of BCsiNet can be comparable with original CsiNet even with the encoder binarized.