EMForecaster: A Deep Learning Framework for Time Series Forecasting in Wireless Networks with Distribution-Free Uncertainty Quantification

2025-03-31

AI Summary

This paper addresses time-series forecasting and uncertainty quantification of electromagnetic field (EMF) exposure in wireless networks. We propose an end-to-end deep learning framework featuring a novel hybrid architecture that integrates multi-scale patch-wise modeling with invertible instance normalization, coupled with cross-temporal and cross-patch feature interaction mechanisms. To enable distribution-free, statistically rigorous uncertainty estimation, we incorporate conformal prediction for reliable confidence interval construction. We further introduce the Trade-off Score—a new metric balancing coverage probability and interval width—to holistically evaluate prediction reliability. Experiments demonstrate that our method improves point forecasting accuracy by 53.97% over Transformer baselines; its conformal prediction achieves an average 24.73% improvement in Trade-off Score over conventional baselines and a 49.17% gain over Transformer-based approaches. Extensive validation across diverse, real-world EMF datasets confirms strong generalizability and robustness.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Planning, Routing, and Scheduling: Scheduling under Uncertainty

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

With the recent advancements in wireless technologies, forecasting electromagnetic field (EMF) exposure has become critical to enable proactive network spectrum and power allocation, as well as network deployment planning. In this paper, we develop a deep learning (DL) time series forecasting framework referred to as extit{EMForecaster}. The proposed DL architecture employs patching to process temporal patterns at multiple scales, complemented by reversible instance normalization and mixing operations along both temporal and patch dimensions for efficient feature extraction. We augment {EMForecaster} with a conformal prediction mechanism, which is independent of the data distribution, to enhance the trustworthiness of model predictions via uncertainty quantification of forecasts. This conformal prediction mechanism ensures that the ground truth lies within a prediction interval with target error rate $alpha$, where $1-alpha$ is referred to as coverage. However, a trade-off exists, as increasing coverage often results in wider prediction intervals. To address this challenge, we propose a new metric called the extit{Trade-off Score}, that balances trustworthiness of the forecast (i.e., coverage) and the width of prediction interval. Our experiments demonstrate that EMForecaster achieves superior performance across diverse EMF datasets, spanning both short-term and long-term prediction horizons. In point forecasting tasks, EMForecaster substantially outperforms current state-of-the-art DL approaches, showing improvements of 53.97% over the Transformer architecture and 38.44% over the average of all baseline models. EMForecaster also exhibits an excellent balance between prediction interval width and coverage in conformal forecasting, measured by the tradeoff score, showing marked improvements of 24.73% over the average baseline and 49.17% over the Transformer architecture.

Problem

• Forecasting EMF exposure in wireless networks for proactive resource allocation
• Developing a deep learning framework with uncertainty quantification
• Balancing prediction trustworthiness and interval width via Trade-off Score

Innovation

• Deep learning with multi-scale patching for feature extraction
• Conformal prediction for distribution-free uncertainty quantification
• Trade-off Score balancing coverage and prediction interval width