ACCsiNet: Asymmetric Convolution-based Autoencoder Framework for Massive MIMO CSI Feedback

Channel state information (CSI) is a critical part for massive multiple-input multiple-output (MIMO) system. However, it is a big challenge to send a large amount of CSI from the receiver to the transmitter with limited channel resources. In this letter, we propose asymmetric convolution-based autoencoder framework (ACCsiNet) to handle the CSI compression and decompression problem. Specifically, asymmetric convolution block (AC-Block) is used to enhance the feature extraction ability of convolution. Further, a lightweight method is applied, which can greatly reduce the storage space at the receiver. Considering the practical deployment, multi-model fusion schemes including multi-rate and multi-scenario fusion are also discussed to strengthen the generalization ability of the network. Experimental results show that the proposed ACCsiNet can improve the NMSE and cosine similarity ρ performance, especially for outdoor scenario. The results also verify that both the lightweight and multi-model fusion schemes can reach a near-optimal performance of the proposed ACCsiNet, but further significantly reduce the parameter amount by more than 83% and 90%, respectively.