Data Augmentation of Bridging the Delay Gap for DL-based Massive MIMO CSI Feedback

TL;DR

This paper introduces novel data augmentation techniques, bubble-shift and random-generation, to improve the robustness of deep learning-based CSI feedback in massive MIMO systems under domain gaps caused by delay and environmental complexity.

Contribution

It proposes two new data augmentation methods to address domain gaps and overfitting in DL-based CSI feedback for massive MIMO systems, enhancing real-world robustness.

Findings

Bubble-shift improves robustness against delay variations.

Random-generation alleviates overfitting in outdoor scenarios.

Proposed methods outperform baseline models in simulations.

Abstract

In massive multiple-input multiple-output (MIMO) systems under the frequency division duplexing (FDD) mode, the user equipment (UE) needs to feed channel state information (CSI) back to the base station (BS). Though deep learning approaches have made a hit in the CSI feedback problem, whether they can remain excellent in actual environments needs to be further investigated. In this letter, we point out that the real-time dataset in application often has the domain gap from the training dataset caused by the time delay. To bridge the gap, we propose bubble-shift (B-S) data augmentation, which attempts to offset performance degradation by changing the delay and remaining the channel information as much as possible. Moreover, random-generation (R-G) data augmentation is especially proposed for outdoor scenarios due to the complex distribution of its channels. It generalizes the characteristics of the channel matrix and alleviates the over-fitting problem. Simulation results show that the proposed data augmentation boosts the robustness of networks in both indoor and outdoor environments. The open source codes are available at https://github.com/zhanghy23/CRNet-Aug.