DNN-based Detectors for Massive MIMO Systems with Low-Resolution ADCs

TL;DR

This paper introduces two deep neural network detectors, OBMNet and FBMNet, designed for low-resolution massive MIMO systems, significantly improving detection accuracy while maintaining low complexity.

Contribution

The paper presents novel model-driven DNN detectors specifically tailored for one-bit and few-bit massive MIMO systems, enhancing detection performance over existing methods.

Findings

OBMNet and FBMNet outperform existing detection methods.

The proposed detectors are efficient to train and implement.

Significant improvement in detection accuracy for low-resolution MIMO systems.

Abstract

Low-resolution analog-to-digital converters (ADCs) have been considered as a practical and promising solution for reducing cost and power consumption in massive Multiple-Input-Multiple-Output (MIMO) systems. Unfortunately, low-resolution ADCs significantly distort the received signals, and thus make data detection much more challenging. In this paper, we develop a new deep neural network (DNN) framework for efficient and low-complexity data detection in low-resolution massive MIMO systems. Based on reformulated maximum likelihood detection problems, we propose two model-driven DNN-based detectors, namely OBMNet and FBMNet, for one-bit and few-bit massive MIMO systems, respectively. The proposed OBMNet and FBMNet detectors have unique and simple structures designed for low-resolution MIMO receivers and thus can be efficiently trained and implemented. Numerical results also show that OBMNet and FBMNet significantly outperform existing detection methods.