Deep Learning-Based Channel Estimation for High-Dimensional Signals

TL;DR

This paper introduces a deep learning-based channel estimator for high-dimensional signals that outperforms traditional methods, requires no prior statistical knowledge, and significantly reduces pilot tone requirements in OFDM systems.

Contribution

A novel deep neural network approach for channel estimation that adapts without prior statistics and exploits correlations for improved performance.

Findings

Outperforms LS estimation with similar complexity

Approaches MMSE performance within 1 dB

Reduces pilot tones in LTE scenarios by up to 98%

Abstract

We propose a novel deep learning-based channel estimation technique for high-dimensional communication signals that does not require any training. Our method is broadly applicable to channel estimation for multicarrier signals with any number of antennas, and has low enough complexity to be used in a mobile station. The proposed deep channel estimator can outperform LS estimation with nearly the same complexity, and approach MMSE estimation performance to within 1 dB without knowing the second order statistics. The only complexity increase with respect to LS estimator lies in fitting the parameters of a deep neural network (DNN) periodically on the order of the channel coherence time. We empirically show that the main benefit of this method accrues from the ability of this specially designed DNN to exploit correlations in the time-frequency grid. The proposed estimator can also reduce the number of pilot tones needed in an OFDM time-frequency grid, e.g. in an LTE scenario by 98% (68%) when the channel coherence time interval is 73ms (4.5ms).