EMFusion: An Uncertainty-Aware Conditional Diffusion Framework for Frequency-Selective EMF Forecasting in Wireless Networks

TL;DR

EMFusion is a novel diffusion-based probabilistic framework that forecasts frequency-selective electromagnetic fields in wireless networks, incorporating external context and providing uncertainty estimates.

Contribution

It introduces EMFusion, a multivariate diffusion model with attention and imputation strategies for frequency-selective EMF forecasting with uncertainty quantification.

Findings

EMFusion outperforms baseline models by 23.85% in CRPS.

It achieves a 13.93% reduction in normalized RMSE.

EMFusion reduces prediction CRPS error by 22.47%.

Abstract

The rapid growth in wireless infrastructure has increased the need to accurately estimate and forecast electromagnetic field (EMF) levels to ensure ongoing compliance, assess potential health impacts, and support efficient network planning. While existing studies rely on univariate forecasting of wideband aggregate EMF data, frequency-selective multivariate forecasting is needed to capture the inter-operator and inter-frequency variations essential for proactive network planning. To this end, this paper introduces EMFusion, a conditional multivariate diffusion-based probabilistic forecasting framework that integrates diverse contextual factors, such as time of day, season, and holidays, while providing explicit uncertainty estimates. The proposed architecture features a residual U-Net backbone enhanced by a cross-attention mechanism that dynamically integrates external conditions to guide the generation process. Furthermore, EMFusion integrates an imputation-based sampling strategy that treats forecasting as a structural inpainting task, ensuring temporal coherence even with irregular measurements. Unlike standard point forecasters, EMFusion generates empirical probabilistic prediction intervals from the learned conditional distribution, providing uncertainty-aware probabilistic forecasting rather than simple point estimation. Numerical experiments conducted on frequency-selective EMF datasets demonstrate that EMFusion with the contextual information of working hours outperforms the baseline models with or without conditions. EMFusion outperforms the best baseline by 23.85% in continuous ranked probability score (CRPS), 13.93% in normalized root mean square error, and reduces prediction CRPS error by 22.47%.