Deep Plug-and-Play Prior for Multitask Channel Reconstruction in Massive MIMO Systems

TL;DR

This paper introduces an unsupervised deep plug-and-play prior approach that efficiently handles multiple channel reconstruction tasks in massive MIMO systems using a single model, reducing training and storage costs.

Contribution

The paper presents a novel unified DL model for three channel reconstruction tasks in massive MIMO, eliminating the need for task-specific fine-tuning and significantly reducing overhead.

Findings

The proposed method converges effectively on the DeepMIMO dataset.

It achieves competitive performance across all three tasks.

The approach reduces model training and storage overhead.

Abstract

Scalability is a major concern in implementing deep learning (DL) based methods in wireless communication systems. Given various channel reconstruction tasks, applying one DL model for one specific task is costly in both model training and model storage. In this paper, we propose a novel unsupervised deep plug-and-play prior method for three channel reconstruction tasks in the downlink of massive multiple-input multiple-output (MIMO) systems, including channel estimation, antenna extrapolation and channel state information (CSI) feedback. The proposed method corresponding to these three channel reconstruction tasks employs a common DL model, which greatly reduces the overhead of model training and storage. Unlike general multi-task learning, the DL model of the proposed method does not require further fine-tuning for specific channel reconstruction tasks. Extensive experiments are conducted on the DeepMIMO dataset to demonstrate the convergence, performance, and storage overhead of the proposed method for the three channel reconstruction tasks.