Blind Construction of Angular Power Maps in Massive MIMO Networks

2025-10-08

AI Summary

In large-scale MIMO networks, the absence of location labels impedes channel-state-information (CSI)-driven radio map construction. Method: This paper proposes an unsupervised Angle-Power Graph (APG) construction method leveraging long-term CSI sequences. It employs a Hidden Markov Model (HMM) to capture the latent correlation between user mobility trajectories and angular-domain channel evolution—enabling blind APG estimation without any position annotations. Contribution/Results: Theoretical analysis, grounded in the Cramér–Rao Lower Bound (CRLB), reveals that base station (BS) geometric distribution fundamentally governs localization performance: under uniform linear motion and Poisson-distributed BS deployment, the localization error lower bound approaches zero. Evaluated on real multi-cell massive MIMO network data, the method achieves a mean positioning accuracy of 18 meters using measurements dominated by a single serving cell—marking the first demonstration of high-accuracy, label-free APG construction and theoretically grounded localizability characterization.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Scheduling under Uncertainty
• Machine Learning: Graph-based Machine Learning

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Channel state information (CSI) acquisition is a challenging problem in massive multiple-input multiple-output (MIMO) networks. Radio maps provide a promising solution for radio resource management by reducing online CSI acquisition. However, conventional approaches for radio map construction require location-labeled CSI data, which is challenging in practice. This paper investigates unsupervised angular power map construction based on large timescale CSI data collected in a massive MIMO network without location labels. A hidden Markov model (HMM) is built to connect the hidden trajectory of a mobile with the CSI evolution of a massive MIMO channel. As a result, the mobile location can be estimated, enabling the construction of an angular power map. We show that under uniform rectilinear mobility with Poisson-distributed base stations (BSs), the Cramer-Rao Lower Bound (CRLB) for localization error can vanish at any signal-to-noise ratios (SNRs), whereas when BSs are confined to a limited region, the error remains nonzero even with infinite independent measurements. Based on reference signal received power (RSRP) data collected in a real multi-cell massive MIMO network, an average localization error of 18 meters can be achieved although measurements are mainly obtained from a single serving cell.

Problem

• Constructing angular power maps without location-labeled CSI data
• Estimating mobile locations using HMM from CSI evolution patterns
• Analyzing localization error bounds under different BS distributions

Innovation

• Unsupervised angular power map construction without location labels
• Hidden Markov model connects mobile trajectory to CSI evolution
• Achieves 18-meter localization using single-cell RSRP measurements