Channel Estimation for XL-MIMO Systems with Decentralized Baseband Processing: Integrating Local Reconstruction with Global Refinement

TL;DR

The work addresses XL-MIMO channel estimation in a hybrid, DBP-based star topology by proposing a two-stage scheme that first performs local sparse reconstruction using a SBL-GNNs estimator and then fuses and refines the global channel at a central unit. The local stage leverages a graph-neural-network-enhanced sparse Bayesian learning approach to capture long-range dependencies among channel coefficients, while the global stage uses angular-domain fusion and a Bayesian denoising step with a Markov chain-based hierarchical prior through variational message passing. The combination yields substantial reductions in computational burden compared to centralized schemes while achieving estimation accuracy close to centralized performance, validated by simulations that show improved NMSE and shorter runtimes. This approach offers a scalable, high-performance solution for XL-MIMO systems with decentralized baseband processing and hybrid architectures, enabling efficient deployment in future wireless networks.

Abstract

In this paper, we investigate the channel estimation problem for extremely large-scale multiple-input multiple-output (XL-MIMO) systems with a hybrid analog-digital architecture, implemented within a decentralized baseband processing (DBP) framework with a star topology. Existing centralized and fully decentralized channel estimation methods face limitations due to excessive computational complexity or degraded performance. To overcome these challenges, we propose a novel two-stage channel estimation scheme that integrates local sparse reconstruction with global fusion and refinement. Specifically, in the first stage, by exploiting the sparsity of channels in the angular-delay domain, the local reconstruction task is formulated as a sparse signal recovery problem. To solve it, we develop a graph neural networks-enhanced sparse Bayesian learning (SBL-GNNs) algorithm, which effectively captures dependencies among channel coefficients, significantly improving estimation accuracy. In the second stage, the local estimates from the local processing units (LPUs) are aligned into a global angular domain for fusion at the central processing unit (CPU). Based on the aggregated observations, the channel refinement is modeled as a Bayesian denoising problem. To efficiently solve it, we devise a variational message passing algorithm that incorporates a Markov chain-based hierarchical sparse prior, effectively leveraging both the sparsity and the correlations of the channels in the global angular-delay domain. Simulation results validate the effectiveness and superiority of the proposed SBL-GNNs algorithm over existing methods, demonstrating improved estimation performance and reduced computational complexity.

Figures (9)

• Figure 1: XL-MIMO systems with star-topology DBP architecture.
• Figure 2: Proposed two-stage channel estimation scheme.
• Figure 3: The structure of the proposed SBL-GNNs network
• Figure 4: The factor graph representation of (\ref{['MAP3']}).
• Figure 5: NMSE of SBL-GNNs versus subarray number.

Theorems & Definitions (7)

• Remark 1
• Remark 2
• Lemma 1
• proof
• Remark 3
• Remark 4
• Remark 5