Radio Map Updating from Streaming Spectrum Measurements via Memory-Based Online Gaussian Processes

2026-07-20

AI Summary

This work addresses the high computational overhead of traditional batch methods in updating radio channel maps under continuous spectral data streams, which stems from repeatedly reprocessing historical data. To overcome this limitation, the authors propose a Memory-based Online Sparse Variational Gaussian Process (M-OSVGP) that incorporates a memory replay mechanism to mitigate catastrophic forgetting. Furthermore, they introduce a Grid-assisted Online Inducing Point Selection (GOIPS) strategy to enhance the quality of posterior approximation. The proposed approach effectively balances computational efficiency and modeling accuracy, consistently outperforming existing batch and online baselines across diverse scenarios. It demonstrates superior performance in reconstruction fidelity, inference speed, and uncertainty quantification.

Abstract

Radio maps, which estimate spatial radio-frequency characteristics from spectrum measurements, are essential for applications such as spectrum management and network planning. With the continuous arrival of spectrum measurements, conventional batch processing methods for radio map reconstruction become computationally prohibitive, as they require reprocessing all accumulated measurements for each radio map update. To address this, we propose a memory-based online sparse variational Gaussian process (M-OSVGP) method that efficiently updates radio maps from streaming spectrum measurements. Our method employs sparse variational inference and updates the posterior online by minimizing a hybrid objective that integrates newly received measurements and a memory subset of previous ones to mitigate catastrophic forgetting. To further improve posterior approximation as measurements accumulate over spatially diverse regions, we extend M-OSVGP with a grid-assisted online inducing point selection (GOIPS) algorithm. GOIPS dynamically adapts the number and locations of inducing points based on measurement density and spatial correlation, providing a more informative inducing set while maintaining computational efficiency. Extensive simulations demonstrate the effectiveness of our proposed methods in reconstruction accuracy, computational efficiency, and uncertainty quantification, compared to existing batch and online baselines across various scenarios.

Problem

• radio map updating
• streaming spectrum measurements
• online learning
• computational efficiency
• catastrophic forgetting

Innovation

• online Gaussian processes
• radio map updating
• sparse variational inference
• catastrophic forgetting mitigation
• inducing point selection