Pilot Contamination-Aware Graph Attention Network for Power Control in CFmMIMO

2025-06-01

AI Summary

To address three key bottlenecks in downlink power control for cell-free massive MIMO—pilot contamination, dynamic user equipment (UE) population, and high overhead of supervised training—this paper proposes a self-supervised graph attention network (SS-GAT). First, it explicitly models channel cross-talk induced by non-orthogonal pilots within a graph neural network (GNN) framework. Second, it constructs a variable-size channel graph to accommodate real-time activation and deactivation of UEs. Third, it introduces a self-supervised loss based on power constraint consistency, eliminating reliance on costly optimal power allocation labels. Experiments demonstrate that SS-GAT achieves performance comparable to the state-of-the-art accelerated projected gradient method, while accelerating inference by two orders of magnitude. Moreover, it exhibits significantly stronger generalization than existing supervised GNN-based approaches across diverse network topologies and load conditions.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Search and Optimization: Learning to Search
• Computer Vision: Generative Adversarial Networks (GANs) for Vision

Application Category

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

Abstract

Optimization-based power control algorithms are predominantly iterative with high computational complexity, making them impractical for real-time applications in cell-free massive multiple-input multiple-output (CFmMIMO) systems. Learning-based methods have emerged as a promising alternative, and among them, graph neural networks (GNNs) have demonstrated their excellent performance in solving power control problems. However, all existing GNN-based approaches assume ideal orthogonality among pilot sequences for user equipments (UEs), which is unrealistic given that the number of UEs exceeds the available orthogonal pilot sequences in CFmMIMO schemes. Moreover, most learning-based methods assume a fixed number of UEs, whereas the number of active UEs varies over time in practice. Additionally, supervised training necessitates costly computational resources for computing the target power control solutions for a large volume of training samples. To address these issues, we propose a graph attention network for downlink power control in CFmMIMO systems that operates in a self-supervised manner while effectively handling pilot contamination and adapting to a dynamic number of UEs. Experimental results show its effectiveness, even in comparison to the optimal accelerated projected gradient method as a baseline.

Problem

• High computational complexity in iterative power control algorithms
• Assumption of ideal pilot orthogonality in existing GNN methods
• Inability to handle dynamic number of active UEs

Innovation

• Self-supervised graph attention network for power control
• Handles pilot contamination in CFmMIMO systems
• Adapts to dynamic number of user equipments