Deep Learning Based Joint Channel Estimation and Positioning for Sparse XL-MIMO OFDM Systems

2025-07-26

AI Summary

This work addresses the joint channel estimation and device localization challenge in near-field sparse ultra-massive MIMO-OFDM systems. We propose a two-stage deep learning framework featuring CP-Mamba—a novel U-shaped architecture that synergistically integrates Mamba’s long-range sequential modeling capability with convolutional operators’ local spatial feature extraction, explicitly capturing the coupling between channel responses and user positions. The framework employs coordinate prediction to guide and refine channel estimation, enabling end-to-end joint optimization. Experimental results demonstrate that CP-Mamba achieves substantial improvements over state-of-the-art methods in both channel estimation normalized mean square error (NMSE) and localization accuracy. Furthermore, the incorporation of a sparse antenna array enhances both estimation/positioning performance and hardware efficiency.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

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 paper investigates joint channel estimation and positioning in near-field sparse extra-large multiple-input multiple-output (XL-MIMO) orthogonal frequency division multiplexing (OFDM) systems. To achieve cooperative gains between channel estimation and positioning, we propose a deep learning-based two-stage framework comprising positioning and channel estimation. In the positioning stage, the user's coordinates are predicted and utilized in the channel estimation stage, thereby enhancing the accuracy of channel estimation. Within this framework, we propose a U-shaped Mamba architecture for channel estimation and positioning, termed as CP-Mamba. This network integrates the strengths of the Mamba model with the structural advantages of U-shaped convolutional networks, enabling effective capture of local spatial features and long-range temporal dependencies of the channel. Numerical simulation results demonstrate that the proposed two-stage approach with CP-Mamba architecture outperforms existing baseline methods. Moreover, sparse arrays (SA) exhibit significantly superior performance in both channel estimation and positioning accuracy compared to conventional compact arrays.

Problem

• Joint channel estimation and positioning in near-field sparse XL-MIMO OFDM systems
• Enhancing accuracy via deep learning-based two-stage framework
• Improving performance with U-shaped Mamba architecture (CP-Mamba)

Innovation

• Deep learning two-stage framework for XL-MIMO
• U-shaped Mamba architecture for channel estimation
• Sparse arrays enhance estimation and positioning accuracy