Deep Learning Model for Demodulation Reference Signal based Channel Estimation

TL;DR

This paper introduces a novel deep learning model called DLR-SSC for improved channel estimation using DMRS signals, which effectively reduces noise and enhances reliability across different wireless environments, outperforming existing models.

Contribution

The paper presents a new DLR-SSC model combining a denoise, interpolate, and refine pipeline with a cost-sensitive learning method for robust wireless channel estimation.

Findings

Reduced NMSE by up to 27.2dB at 0dB SNR

Outperformed ChannelNet in accuracy

Achieved second place in WAIC competition

Abstract

In this paper, we propose a deep learning model for Demodulation Reference Signal (DMRS) based channel estimation task. Specifically, a novel Denoise, Linear interpolation and Refine (DLR) pipeline is proposed to mitigate the noise propagation problem during channel information interpolation and to restore the nonlinear variation of wireless channel over time. At the same time, the Small-norm Sample Cost-sensitive (SSC) learning method is proposed to equalize the qualities of channel estimation under different kinds of wireless environments and improve the channel estimation reliability. The effectiveness of the propose DLR-SSC model is verified on WAIC Dataset. Compared with the well know ChannelNet channel estimation model, our DLR-SSC model reduced normalized mean square error (NMSE) by 27.2dB, 22.4dB and 16.8dB respectively at 0dB, 10dB, and 20dB SNR. The proposed model has won the second place in the 2nd Wireless Communication Artificial Intelligence Competition (WAIC). The code is about to open source.