ReVeal: A Physics-Informed Neural Network for High-Fidelity Radio Environment Mapping

TL;DR

ReVeal is a physics-informed neural network that accurately maps radio environments using sparse measurements, outperforming existing models in accuracy and computational efficiency by integrating a PDE residual into its loss function.

Contribution

The paper introduces ReVeal, a novel PINN that incorporates a PDE for RSSI to improve radio environment mapping with sparse data, demonstrating superior accuracy and efficiency.

Findings

ReVeal achieves an RMSE of 1.95 dB, outperforming existing models.

ReVeal requires only 30 samples over 514 km² for high accuracy.

ReVeal combines physics-based modeling with neural networks for efficient radio mapping.

Abstract

Accurately mapping the radio environment (e.g., identifying wireless signal strength at specific frequency bands and geographic locations) is crucial for efficient spectrum sharing, enabling secondary users (SUs) to access underutilized spectrum bands while protecting primary users (PUs). However, current models are either not generalizable due to shadowing, interference, and fading or are computationally too expensive, limiting real-world applicability. To address the shortcomings of existing models, we derive a second-order partial differential equation (PDE) for the Received Signal Strength Indicator (RSSI) based on a statistical model used in the literature. We then propose ReVeal (Re-constructor and Visualizer of Spectrum Landscape), a novel Physics-Informed Neural Network (PINN) that integrates the PDE residual into a neural network loss function to accurately model the radio environment based on sparse RF sensor measurements. ReVeal is validated using real-world measurement data from the rural and suburban areas of the ARA testbed and benchmarked against existing methods.ReVeal outperforms the existing methods in predicting the radio environment; for instance, with a root mean square error (RMSE) of only 1.95 dB, ReVeal achieves an accuracy that is an order of magnitude higher than existing methods such as the 3GPP and ITU-R channel models, ray-tracing, and neural networks. ReVeal achieves both high accuracy and low computational complexity while only requiring sparse RF sampling, for instance, only requiring 30 training sample points across an area of 514 square kilometers.