Quantum Deep Learning for Massive MIMO User Scheduling

2025/08/05 by Huang, Xingyu, Fan, Ruining, Chakraborty, Mouli +2
#FOS: Electrical engineering #Signal Processing (eess.SP) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2508.03327

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.

Citations

• Hybrid Quantum-Classical Neural Networks for Downlink Beamforming Optimization
• Dealing with CSI Compression to Reduce Losses and Overhead: An\n Artificial Intelligence Approach
• Advances in Quantum Deep Learning: An Overview

Related

• Hybrid Quantum Convolutional Neural Network-Aided Pilot Assignment in Cell-Free Massive MIMO Systems
• D2D Power Allocation via Quantum Graph Neural Network
• Quantum Computing for Large-scale Network Optimization: Opportunities and Challenges
• Hybrid Quantum-Classical Neural Networks for Downlink Beamforming Optimization
• A Hybrid Quantum-Classical Autoencoder Framework for End-to-End Communication Systems