AE-DENet: Enhancement for Deep Learning-based Channel Estimation in OFDM Systems

TL;DR

This paper introduces AE-DENet, an autoencoder-based data enhancement network that improves deep learning-based OFDM channel estimation by exploiting the correlation between real and imaginary signal components, leading to better accuracy and robustness.

Contribution

AE-DENet is a novel autoencoder-based method that enriches input data for DL-based channel estimation by extracting and fusing interaction features from real and imaginary parts.

Findings

Enhances the performance of state-of-the-art DL estimators in terms of MSE.

Provides robustness to channel variations and high user mobility.

Adds negligible computational complexity.

Abstract

Deep learning (DL)-based methods have demonstrated remarkable achievements in addressing orthogonal frequency division multiplexing (OFDM) channel estimation challenges. However, existing DL-based methods mainly rely on separate real and imaginary inputs while ignoring the inherent correlation between the two streams, such as amplitude and phase information that are fundamental in communication signal processing. This paper proposes AE-DENet, a novel autoencoder(AE)-based data enhancement network to improve the performance of existing DL-based channel estimation methods. AE-DENet focuses on enriching the classic least square (LS) estimation input commonly used in DL-based methods by employing a learning-based data enhancement method, which extracts interaction features from the real and imaginary components and fuses them with the original real/imaginary streams to generate an enhanced input for better channel inference. Experimental findings in terms of the mean square error (MSE) results demonstrate that the proposed method enhances the performance of all state-of-the-art DL-based channel estimators with negligible added complexity. Furthermore, the proposed approach is shown to be robust to channel variations and high user mobility.