Statistical Channel Fingerprint Construction for Massive MIMO: A Unified Tensor Learning Framework

arXiv cs.LG / 5/1/2026

📰 NewsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper introduces a new “statistical channel fingerprint” (sCF) concept for massive MIMO that captures statistical CSI at each potential location.
It clarifies how the channel spatial covariance matrix (CSCM) relates to the channel power angular spectrum (CPAS), and uses this relationship to form a unified tensor representation of sCF.
The authors reduce tensor dimensionality via eigenvalue decomposition of the CSCM and its correlation with the PAS, making the approach more practical.
To handle measurement cost, privacy, and security constraints, they model three representative sCF acquisition scenarios as tensor restoration problems.
They propose LPWTNet, a unified tensor-learning architecture that uses Laplacian pyramid decomposition/reconstruction, shared mask learning for high-frequency refinement, and a wavelet-based small-kernel convolution to improve efficiency and accuracy, validated by extensive experiments against strong baselines.

Abstract

Channel fingerprint (CF) is considered a key enabler for facilitating the acquisition of channel state information (CSI) in massive multiple-input multiple-output (MIMO) communication systems. In this work, we investigate a novel type of CF that stores statistical CSI (sCSI) at each potential location, referred to as statistical CF (sCF). Specifically, we reveal the relationship between sCSI, namely the channel spatial covariance matrix (CSCM), and the channel power angular spectrum (CPAS). Building on this foundation, we construct a unified tensor representation of the sCF and further reduce its dimension by exploiting the eigenvalue decomposition of the CSCM and its correlation with the PAS. Considering the practical constraints imposed by measurement cost, privacy, and security, we focus on three representative scenarios and uniformly formulate them as tensor restoration tasks. To this end, we propose a unified tensor-based learning architecture, termed LPWTNet. The architecture incorporates a closed-form Laplacian pyramid (LP) decomposition and reconstruction framework that replaces the traditional encoder-decoder structure, enabling efficient inference while capturing multi-scale frequency subband characteristics of the sCF. Additionally, a shared mask learning strategy is introduced to adaptively refine high-frequency sCF components through level-wise adjustments. To achieve a larger receptive field without over-parameterization, we further propose a small-kernel convolution mechanism based on the wavelet transform (WT), which decouples convolution across different frequency components of the sCF and enhances feature extraction efficiency. Extensive experiments show that the proposed approach delivers competitive reconstruction accuracy and computational efficiency across various sCF construction scenarios when compared with state-of-the-art baselines.