Joint Power Control and Precoding for Cell-Free Massive MIMO Systems With Sparse Multi-Dimensional Graph Neural Networks

2025-07-02

AI Summary

To address the high computational complexity arising from joint power control and precoding optimization in cell-free massive MIMO systems, this paper proposes a Sparse Multi-Dimensional Graph Neural Network (SP-MDGNN) framework. SP-MDGNN explicitly models and sparsifies the channel association structure between access points and users, preserving essential topological information while significantly reducing model parameters and inference overhead. It is co-designed with the WMMSE algorithm to enable end-to-end trainable joint optimization. Experiments demonstrate that, compared to a fully connected MDGNN, the proposed method reduces computational complexity by over 60% while degrading total spectral efficiency by less than 1.5%, markedly enhancing real-time deployability in large-scale networks. The core innovation lies in the first integration of structural sparsity into the multi-dimensional GNN architecture—achieving a balanced trade-off among performance, computational efficiency, and scalability.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization

Abstract

Cell-free massive multiple-input multiple-output (CF mMIMO) has emerged as a prominent candidate for future networks due to its ability to significantly enhance spectral efficiency by eliminating inter-cell interference. However, its practical deployment faces considerable challenges, such as high computational complexity and the optimization of its complex processing. To address these challenges, this correspondence proposes a framework based on a sparse multi-dimensional graph neural network (SP-MDGNN), which sparsifies the connections between access points (APs) and user equipments (UEs) to significantly reduce computational complexity while maintaining high performance. In addition, the weighted minimum mean square error (WMMSE) algorithm is introduced as a comparative method to further analyze the trade-off between performance and complexity. Simulation results demonstrate that the sparse method achieves an optimal balance between performance and complexity, significantly reducing the computational complexity of the original MDGNN method while incurring only a slight performance degradation, providing insights for the practical deployment of CF mMIMO systems in large-scale network.

Problem

• Reducing computational complexity in CF mMIMO systems
• Optimizing joint power control and precoding
• Balancing performance and complexity with SP-MDGNN

Innovation

• Sparse multi-dimensional graph neural network
• Reduces computational complexity significantly
• Maintains high performance with sparsification