Near-Field Channel Estimation for XL-MIMO: A Deep Generative Model Guided by Side Information

2025-05-11

IEEE Transactions on Cognitive Communications and Networking

AI Summary

To address the low channel estimation accuracy and high sampling overhead in extra-large-scale MIMO (XL-MIMO) systems under near-field propagation, this paper proposes a joint angle-distance (AD)-domain spherical-wavefront physical channel model that explicitly captures near-field sparsity, casting channel estimation as a sparse signal recovery problem. Innovatively, we introduce side-information-guided generative diffusion models (GDMs) and their non-Markovian variants (NM-GDMs), synergistically integrating compressive sensing with generative AI for efficient and robust channel reconstruction. The proposed method achieves approximately 10× improvement in sampling efficiency under near-field conditions and significantly outperforms existing baselines in estimation accuracy. Moreover, it exhibits strong generalization across both near-field and far-field regimes, offering a theoretically rigorous and practically viable paradigm for XL-MIMO deployment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Diffusion Models for Vision

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

This paper investigates the near-field (NF) channel estimation (CE) for extremely large-scale multiple-input multiple-output (XL-MIMO) systems. Considering the pronounced NF effects in XL-MIMO communications, we first establish a joint angle-distance (AD) domain-based spherical-wavefront physical channel model that captures the inherent sparsity of XL-MIMO channels. Leveraging the channel's sparsity in the joint AD domain, the CE is approached as a task of reconstructing sparse signals. Anchored in this framework, we first propose a compressed sensing algorithm to acquire a preliminary channel estimate. Harnessing the powerful implicit prior learning capability of generative artificial intelligence (GenAI), we further propose a GenAI-based approach to refine the estimated channel. Specifically, we introduce the preliminary estimated channel as side information, and derive the evidence lower bound (ELBO) of the log-marginal distribution of the target NF channel conditioned on the preliminary estimated channel, which serves as the optimization objective for the proposed generative diffusion model (GDM). Additionally, we introduce a more generalized version of the GDM, the non-Markovian GDM (NM-GDM), to accelerate the sampling process, achieving an approximately tenfold enhancement in sampling efficiency. Experimental results indicate that the proposed approach is capable of offering substantial performance gain in CE compared to existing benchmark schemes within NF XL-MIMO systems. Furthermore, our approach exhibits enhanced generalization capabilities in both the NF or far-field (FF) regions.

Problem

• Estimating near-field channels in XL-MIMO systems
• Leveraging sparsity for efficient channel reconstruction
• Enhancing accuracy with generative AI and side information

Innovation

• Deep generative model for channel estimation
• Non-Markovian GDM accelerates sampling
• Joint angle-distance domain sparsity utilization