A General Framework for Scalable UE-AP Association in User-Centric Cell-Free Massive MIMO based on Recurrent Neural Networks

2025-03-06

AI Summary

To address the challenges of dynamic user equipment (UE)/access point (AP) association, poor scalability, and severe pilot contamination in cell-free massive MIMO systems, this paper proposes an end-to-end deep learning framework tailored for the user-centric architecture. Methodologically, it introduces a novel bidirectional LSTM integrated with a hybrid probabilistic weight update mechanism, enabling arbitrary variations in both UE and AP counts without retraining; it further incorporates an adaptive pilot contamination suppression strategy to enhance channel estimation robustness. Key contributions include: (i) the first dynamic and scalable joint association modeling framework; (ii) a robust association variant explicitly designed to mitigate pilot contamination; and (iii) end-to-end joint training of association and physical-layer tasks. Experiments demonstrate over 35% performance gain in association accuracy over classical heuristic algorithms across diverse network scales, with strong generalization—requiring only a single training instance to adapt seamlessly to varying UE/AP configurations.

Technology Category

• Multiagent Systems: Multiagent Learning
• Search and Optimization: Learning to Search
• Machine Learning: Life-Long and Continual Learning

Application Category

• 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
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

This study addresses the challenge of access point (AP) and user equipment (UE) association in cell-free massive MIMO networks. It introduces a deep learning algorithm leveraging Bidirectional Long Short-Term Memory cells and a hybrid probabilistic methodology for weight updating. This approach enhances scalability by adapting to variations in the number of UEs without requiring retraining. Additionally, the study presents a training methodology that improves scalability not only with respect to the number of UEs but also to the number of APs. Furthermore, a variant of the proposed AP-UE algorithm ensures robustness against pilot contamination effects, a critical issue arising from pilot reuse in channel estimation. Extensive numerical results validate the effectiveness and adaptability of the proposed methods, demonstrating their superiority over widely used heuristic alternatives.

Problem

• Scalable UE-AP association in cell-free massive MIMO networks.
• Deep learning algorithm using RNNs for dynamic UE-AP association.
• Robustness against pilot contamination in channel estimation.

Innovation

• Bidirectional LSTM for scalable UE-AP association
• Hybrid probabilistic method for weight updating
• Robust algorithm against pilot contamination effects