TypeII-CsiNet: CSI Feedback with TypeII Codebook

TL;DR

This paper introduces TypeII-CsiNet, a deep learning autoencoder that enhances CSI feedback by effectively utilizing port correlations and angular-delay structures, significantly improving sum rate performance over existing methods.

Contribution

The paper develops a novel autoencoder with specialized modules and a two-stage loss function to better leverage TypeII codebook correlations for improved CSI feedback accuracy.

Findings

TypeII-CsiNet outperforms traditional TypeII codebook methods.

The proposed model achieves higher sum rate performance.

Simulation results validate the effectiveness of the approach.

Abstract

The latest TypeII codebook selects partial strongest angular-delay ports for the feedback of downlink channel state information (CSI), whereas its performance is limited due to the deficiency of utilizing the correlations among the port coefficients. To tackle this issue, we propose a tailored autoencoder named TypeII-CsiNet to effectively integrate the TypeII codebook with deep learning, wherein three novel designs are developed for sufficiently boosting the sum rate performance. Firstly, a dedicated pre-processing module is designed to sort the selected ports for reserving the correlations of their corresponding coefficients. Secondly, a position-filling layer is developed in the decoder to fill the feedback coefficients into their ports in the recovered CSI matrix, so that the corresponding angular-delay-domain structure is adequately leveraged to enhance the reconstruction accuracy. Thirdly, a two-stage loss function is proposed to improve the sum rate performance while avoiding the trapping in local optimums during model training. Simulation results verify that our proposed TypeII-CsiNet outperforms the TypeII codebook and existing deep learning benchmarks.