Changeable Rate and Novel Quantization for CSI Feedback Based on Deep Learning

TL;DR

This paper introduces a deep learning framework with changeable feedback rates and a novel quantization scheme to enhance CSI feedback efficiency and reduce storage needs in massive MIMO systems.

Contribution

It proposes a unified DL-based framework that reuses network layers for variable feedback rates and a new quantization method to improve encoding efficiency and storage savings.

Findings

Reduces storage space by about 50% with changeable-rate scheme.

Improves encoding efficiency through a novel quantization module.

Achieves efficient CSI feedback adaptable to bandwidth variations.

Abstract

Deep learning (DL)-based channel state information (CSI) feedback improves the capacity and energy efficiency of massive multiple-input multiple-output (MIMO) systems in frequency division duplexing mode. However, multiple neural networks with different lengths of feedback overhead are required by time-varying bandwidth resources. The storage space required at the user equipment (UE) and the base station (BS) for these models increases linearly with the number of models. In this paper, we propose a DL-based changeable-rate framework with novel quantization scheme to improve the efficiency and feasibility of CSI feedback systems. This framework can reutilize all the network layers to achieve overhead-changeable CSI feedback to optimize the storage efficiency at the UE and the BS sides. Designed quantizer in this framework can avoid the normalization and gradient problems faced by traditional quantization schemes. Specifically, we propose two DL-based changeable-rate CSI feedback networks CH-CsiNetPro and CH-DualNetSph by introducing a feedback overhead control unit. Then, a pluggable quantization block (PQB) is developed to further improve the encoding efficiency of CSI feedback in an end-to-end way. Compared with existing CSI feedback methods, the proposed framework saves the storage space by about 50% with changeable-rate scheme and improves the encoding efficiency with the quantization module.