Bayesian Learning for Pilot Decontamination in Cell-Free Massive MIMO

2025-08-15

AI Summary

To address pilot contamination arising from non-orthogonal pilot reuse in uplink cell-free massive MIMO systems, this paper proposes a distributed joint channel estimation and data detection algorithm based on an enhanced bilinear expectation propagation (EP) framework integrated with Bayesian learning. We introduce a user-level pilot contamination metric, revealing for the first time its monotonic relationship with estimation and detection performance; further, we theoretically prove that non-orthogonal pilots can outperform conventional orthogonal ones under specific channel conditions. The proposed algorithm is scalable and amenable to fully distributed implementation. Extensive evaluations demonstrate that it consistently surpasses existing Bayesian methods across diverse pilot configurations, achieving superior robustness against pilot contamination and significantly higher data detection accuracy.

Technology Category

• Machine Learning: Bayesian Learning
• Search and Optimization: Distributed Search
• Intelligent Robots: State Estimation

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Pilot contamination (PC) arises when the pilot sequences assigned to user equipments (UEs) are not mutually orthogonal, eventually due to their reuse. In this work, we propose a novel expectation propagation (EP)-based joint channel estimation and data detection (JCD) algorithm specifically designed to mitigate the effects of PC in the uplink of cell-free massive multiple-input multiple-output (CF-MaMIMO) systems. This modified bilinear-EP algorithm is distributed, scalable, demonstrates strong robustness to PC, and outperforms state-of-the-art Bayesian learning algorithms. Through a comprehensive performance evaluation, we assess the performance of Bayesian learning algorithms for different pilot sequences and observe that the use of non-orthogonal pilots can lead to better performance compared to shared orthogonal sequences. Motivated by this analysis, we introduce a new metric to quantify PC at the UE level. We show that the performance of the considered algorithms degrades monotonically with respect to this metric, providing a valuable theoretical and practical tool for understanding and managing PC via iterative JCD algorithms.

Problem

• Mitigating pilot contamination in cell-free massive MIMO uplink systems
• Developing distributed Bayesian learning for joint channel estimation
• Quantifying pilot contamination effects using new UE-level metric

Innovation

• Distributed scalable EP algorithm
• Robust Bayesian learning decontamination
• UE-level PC metric quantification