Vector Approximate Message Passing based Channel Estimation for MIMO-OFDM Underwater Acoustic Communications

TL;DR

This paper introduces an EM-VAMP-based channel estimation method for MIMO-OFDM underwater acoustic communications, improving accuracy and complexity tradeoff over existing methods.

Contribution

It develops a novel EM-VAMP channel estimation scheme using a Bernoulli-Gaussian prior and learns hyperparameters via EM, tailored for UWA MIMO-OFDM systems.

Findings

Outperforms existing methods in simulations

Validated with real at-sea data

Achieves better performance-complexity balance

Abstract

Accurate channel estimation is critical to the performance of orthogonal frequency-division multiplexing (OFDM) underwater acoustic (UWA) communications, especially under multiple-input multiple-output (MIMO) scenarios. In this paper, we explore Vector Approximate Message Passing (VAMP) coupled with Expected Maximum (EM) to obtain channel estimation (CE) for MIMO OFDM UWA communications. The EM-VAMP-CE scheme is developed by employing a Bernoulli-Gaussian (BG) prior distribution for the channel impulse response, and hyperparameters of the BG prior distribution are learned via the EM algorithm. Performance of the EM-VAMP-CE is evaluated through both synthesized data and real data collected in two at-sea UWA communication experiments. It is shown the EM-VAMP-CE achieves better performance-complexity tradeoff compared with existing channel estimation methods.