Empowering Power Outage Prediction with Spatially Aware Hybrid Graph Neural Networks and Contrastive Learning

2026-04-06

AI Summary

This study addresses the limitation of existing power outage prediction models, which often neglect the spatial dependencies of extreme weather events, thereby constraining predictive accuracy. To overcome this, the authors propose a Spatially Aware Hybrid Graph Neural Network (SA-HGNN) that uniquely integrates contrastive learning with multi-source spatiotemporal features to jointly model static geographic structures and dynamic meteorological data. By pulling embedding representations of regions affected by similar events closer together while pushing apart those from dissimilar events, the model effectively mitigates class imbalance and enhances region-specific modeling capabilities. Empirical evaluations across four regions, including Connecticut, demonstrate that the proposed approach significantly outperforms current state-of-the-art systems, achieving leading performance in outage prediction.

Abstract

Extreme weather events, such as severe storms, hurricanes, snowstorms, and ice storms, which are exacerbated by climate change, frequently cause widespread power outages. These outages halt industrial operations, impact communities, damage critical infrastructure, profoundly disrupt economies, and have far-reaching effects across various sectors. To mitigate these effects, the University of Connecticut and Eversource Energy Center have developed an outage prediction modeling (OPM) system to provide pre-emptive forecasts for electric distribution networks before such weather events occur. However, existing predictive models in the system do not incorporate the spatial effect of extreme weather events. To this end, we develop Spatially Aware Hybrid Graph Neural Networks (SA-HGNN) with contrastive learning to enhance the OPM predictions for extreme weather-induced power outages. Specifically, we first encode spatial relationships of both static features (e.g., land cover, infrastructure) and event-specific dynamic features (e.g., wind speed, precipitation) via Spatially Aware Hybrid Graph Neural Networks (SA-HGNN). Next, we leverage contrastive learning to handle the imbalance problem associated with different types of extreme weather events and generate location-specific embeddings by minimizing intra-event distances between similar locations while maximizing inter-event distances across all locations. Thorough empirical studies in four utility service territories, i.e., Connecticut, Western Massachusetts, Eastern Massachusetts, and New Hampshire, demonstrate that SA-HGNN can achieve state-of-the-art performance for power outage prediction.

Problem

• power outage prediction
• extreme weather events
• spatial effect
• predictive modeling
• electric distribution networks

Innovation

• Spatially Aware Hybrid Graph Neural Networks
• Contrastive Learning
• Power Outage Prediction
• Extreme Weather Events
• Graph Representation Learning