Probabilistic forecasting of weather-driven faults in electricity networks: a flexible approach for extreme and non-extreme events

2026-03-02

AI Summary

This study addresses the critical need for reliable probabilistic forecasting of power network failures that accounts for both extreme and non-extreme weather events while quantifying uncertainty. The authors propose a unified probabilistic framework: non-extreme failures are modeled using multi-additive quantile regression with linear interpolation, while extreme events are captured via a discrete generalized Pareto distribution. By directly integrating ensemble numerical weather predictions, the method delivers up to four-day-ahead failure probability forecasts, further enhanced through probabilistic calibration to improve reliability. Evaluated on historical data from two UK distribution networks, the approach significantly outperforms existing methods. A real-world operational trial with Scottish Power Energy Networks from October 2024 to March 2025 demonstrates its practical utility in supporting maintenance decisions and reducing outage durations.

Technology Category

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

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Electricity networks are vulnerable to weather damage, with severe events often leading to faults and power outages. Timely forecasts of fault occurrences, ranging from nowcasts to several days ahead, can enhance preparedness, support faster response, and reduce outage durations. To be operationally useful, such forecasts must quantify uncertainty, enabling risk-informed resource allocation. We present a novel probabilistic framework for forecasting fault counts that captures typical and extreme events. Non-extreme faults are modeled linearly interpolating estimates from multiple additive quantile regressions, while extreme events are described through a discrete generalized Pareto distribution. To incorporate the impact of weather fluctuations, we use ensemble numerical weather predictions, which helps to quantify uncertainty in the forecasts. This approach is designed to provide reliable fault predictions up to four days ahead. We evaluate the model through numerical experiments and apply it to historical fault data from two electricity distribution networks in Great Britain. The resulting forecasts demonstrate substantial improvements over business-as-usual and alternative modeling approaches. A practitioner trial conducted with Scottish Power Energy Networks from October 2024 to March 2025 further demonstrates the operational value of the forecasts. Engineers found them sufficiently reliable to inform decision-making, offering benefits to both network operators and electricity consumers.

Problem

• probabilistic forecasting
• weather-driven faults
• electricity networks
• extreme events
• uncertainty quantification

Innovation

• probabilistic forecasting
• quantile regression
• generalized Pareto distribution
• ensemble weather prediction
• extreme event modeling