Unfolded Deep Neural Network (UDNN) for High Mobility Channel Estimation

TL;DR

This paper introduces UDNN, a deep neural network inspired by ISTA, for rapid and accurate high mobility channel estimation in OFDM systems, outperforming traditional methods.

Contribution

The paper proposes a novel unfolded deep neural network that learns parameters end-to-end for fast high mobility channel estimation, improving over traditional compressed sensing algorithms.

Findings

UDNN outperforms ISTA in accuracy for high mobility channel estimation.

UDNN achieves faster computation than traditional iterative algorithms.

Experiments validate the effectiveness of UDNN in B5G/6G scenarios.

Abstract

High mobility channel estimation is crucial for beyond 5G (B5G) or 6G wireless communication networks. This paper is concerned with channel estimation of high mobility OFDM communication systems. First, a two-dimensional compressed sensing problem is formulated by approximately linearizing the channel as a product of an overcomplete dictionary with a sparse vector, in which the Doppler effect caused by the high mobility channel is considered. To solve the problem that the traditional compressed sensing algorithms have too many iterations and are time consuming, we propose an unfolded deep neural network (UDNN) as the fast solver, which is inspired by the structure of iterative shrinkage-thresholding algorithm (ISTA). All the parameters in UDNN (e.g. nonlinear transforms, shrinkage thresholds, measurement matrices, etc.) are learned end-to-end, rather than being hand-crafted. Experiments demonstrate that the proposed UDNN performs better than ISTA for OFDM high mobility channel estimation, while maintaining extremely fast computational speed.