Modified EP MIMO Detection Algorithm with Deep Learning Parameters Selection

TL;DR

This paper introduces MEPD, a modified EP MIMO detection algorithm that uses deep learning to optimize parameters, resulting in improved performance and robustness over traditional methods.

Contribution

It proposes a deep learning-based parameter selection scheme for EP MIMO detection, enhancing performance and robustness.

Findings

MEPD outperforms original EP MIMO detector in various scenarios.

Deep learning-based parameter tuning improves robustness in practical applications.

Simulation results validate the effectiveness of MEPD with trained parameters.

Abstract

Expectation Propagation (EP)-based Multiple-Input Multiple-Output (MIMO) detector is regarded as a state-of-the-art MIMO detector because of its exceptional performance. However, we find that the EP MIMO detector cannot guarantee to achieve the optimal performance due to the empirical parameter selection, including initial variance and damping factors. According to the influence of the moment matching and parameter selection for the performance of the EP MIMO detector, we propose a modified EP MIMO detector (MEPD). In order to obtain the optimal initial variance and damping factors, we adopt a deep learning scheme, in which we unfold the iterative processing of MEPD to establish MEPNet for parameters training. The simulation results show that MEPD with off-line trained parameters outperforms the original one in various MIMO scenarios. Besides, the proposed MEPD with deep learning parameters selection is more robust than EPD in practical scenarios.