RADIANCE: Radio-Frequency Adversarial Deep-learning Inference for Automated Network Coverage Estimation

TL;DR

RADIANCE is a GAN-based method that automates indoor RF map generation using semantic maps and a novel gradient-based loss, reducing the need for labor-intensive site surveys and improving accuracy.

Contribution

It introduces a new gradient-based loss function and leverages semantic maps for RF map synthesis, advancing automated indoor coverage estimation.

Findings

Achieves low MAE of 0.09 in RF map prediction

Outperforms traditional ray-tracing in accuracy

Effectively captures indoor signal propagation patterns

Abstract

Radio-frequency coverage maps (RF maps) are extensively utilized in wireless networks for capacity planning, placement of access points and base stations, localization, and coverage estimation. Conducting site surveys to obtain RF maps is labor-intensive and sometimes not feasible. In this paper, we propose radio-frequency adversarial deep-learning inference for automated network coverage estimation (RADIANCE), a generative adversarial network (GAN) based approach for synthesizing RF maps in indoor scenarios. RADIANCE utilizes a semantic map, a high-level representation of the indoor environment to encode spatial relationships and attributes of objects within the environment and guide the RF map generation process. We introduce a new gradient-based loss function that computes the magnitude and direction of change in received signal strength (RSS) values from a point within the environment. RADIANCE incorporates this loss function along with the antenna pattern to capture signal propagation within a given indoor configuration and generate new patterns under new configuration, antenna (beam) pattern, and center frequency. Extensive simulations are conducted to compare RADIANCE with ray-tracing simulations of RF maps. Our results show that RADIANCE achieves a mean average error (MAE) of 0.09, root-mean-squared error (RMSE) of 0.29, peak signal-to-noise ratio (PSNR) of 10.78, and multi-scale structural similarity index (MS-SSIM) of 0.80.