Quantum Deep Learning for Massive MIMO User Scheduling

TL;DR

This paper proposes a hybrid quantum-classical neural network architecture for user scheduling in massive MIMO systems, improving scalability and spectral efficiency by leveraging quantum computing and statistical CSI.

Contribution

It introduces a novel quantum neural network model that outperforms classical CNNs in wireless user scheduling tasks, addressing scalability and noise robustness.

Findings

Quantum neural network outperforms classical CNNs in scheduling accuracy.

Model reduces computational overhead in massive MIMO systems.

Robust performance maintained in noisy channel conditions.

Abstract

We introduce a hybrid Quantum Neural Networks (QNN) architecture for the efficient user scheduling in 5G/Beyond 5G (B5G) massive Multiple Input Multiple Output (MIMO) systems, addressing the scalability issues of traditional methods. By leveraging statistical Channel State Information (CSI), our model reduces computational overhead and enhances spectral efficiency. It integrates classical neural networks with a variational quantum circuit kernel, outperforming classical Convolutional Neural Networks (CNNs) and maintaining robust performance in noisy channels. This demonstrates the potential of quantum-enhanced Machine Learning (ML) for wireless scheduling.