Deep Learning Based Joint Pilot Design and Channel Estimation for Multiuser MIMO Channels

TL;DR

This paper introduces a deep learning framework for joint pilot design and channel estimation in multiuser MIMO systems, significantly improving estimation accuracy over traditional methods.

Contribution

It presents a novel joint deep learning-based pilot design and channel estimation scheme, incorporating neural networks and interference cancellation for multiuser MIMO channels.

Findings

Outperforms traditional LMMSE channel estimation methods.

Uses neural networks for joint pilot design and channel estimation.

Employs SIC to reduce multiuser interference.

Abstract

In this paper, we propose a joint pilot design and channel estimation scheme based on the deep learning (DL) technique for multiuser multiple-input multiple output (MIMO) channels. To this end, we construct a pilot designer using two-layer neural networks (TNNs) and a channel estimator using deep neural networks (DNNs), which are jointly trained to minimize the mean square error (MSE) of channel estimation. To effectively reduce the interference among the multiple users, we also use the successive interference cancellation (SIC) technique in the channel estimation process. The numerical results demonstrate that the proposed scheme considerably outperforms the state-of-the-art linear minimum mean square error (LMMSE) based channel estimation scheme.