Physics-informed VAE-EVT for Tail Aware Radio Map Prediction

2026-08-15

AI Summary

This study addresses the inaccurate outage prediction in URLLC radio maps caused by neglecting low-SNR tail distributions. We propose a Physics- and Tail-Aware VAE-EVT framework that uniquely integrates physical priors with Extreme Value Theory. By employing a dual-latent-space encoder to jointly model the SNR bulk and extreme fading distributions, alongside a modified variational objective for optimized training, this approach effectively captures tail characteristics. Experimental results demonstrate that the proposed method achieves an SNR RMSE of 4.83 dB at the 0.1% outage quantile, significantly outperforming state-of-the-art GAN models (21.90 dB). Notably, this performance advantage becomes more pronounced under stricter thresholds, thereby substantially enhancing communication reliability assurance in extreme scenarios.

Abstract

Ultra-reliable low-latency communication (URLLC) requires precise identification of spatial regions where the signal-to-noise ratio (SNR) falls below an outage threshold. In this context, an outage refers to instances in which SNR falls below a specified threshold, which, for URLLC, can be as stringent as the 0.1% quantile of the SNR distribution. Traditional generative radio map models tend to focus on reconstructing average signal levels, often overlooking the low SNR that is crucial for accurate outage prediction. To address this limitation, we introduce a physics- and tail-informed VAE-EVT (variational autoencoder-extreme value theory) framework that distinctly models both the bulk and tail distribution of SNR. Our approach begins with a physics-informed preprocessing stage that extracts deterministic features, including line-of-sight, shadowing, and distance, from the scene geometry. A dual-latent encoder then captures the bulk SNR using a Gaussian mixture and the tail using a generalized Pareto distribution (GPD). By employing a modified variational objective, the model is trained to jointly supervise both regimes, ensuring focused attention on extreme fading events. Evaluated on the RadioMapSeer dataset, our method achieves an SNR RMSE of 4.83 dB in the outage region defined by the low threshold of 0.1% SNR quantile. This significantly outperforms the state-of-the-art GAN-based model, which records an SNR RMSE of 21.90 dB, with the performance gap widening as the outage threshold becomes more stringent.

Problem

• Radio Map Prediction
• URLLC
• Tail Distribution
• Outage Prediction
• Signal-to-Noise Ratio

Innovation

• Physics-informed VAE-EVT
• Tail-aware modeling
• Extreme Value Theory
• Dual-latent encoder
• Radio map prediction