Graph Attention Network for Predicting Duration of Large-Scale Power Outages Induced by Natural Disasters
This work addresses power grid resilience by improving outage prediction for utilities and emergency responders, though it is incremental as it builds on existing GAT methods.
The paper tackled predicting power outage durations from natural disasters using a Graph Attention Network (GAT) approach, achieving over 93% accuracy and outperforming existing methods by 2-15% on data from four hurricanes affecting 501 counties.
Natural disasters such as hurricanes, wildfires, and winter storms have induced large-scale power outages in the U.S., resulting in tremendous economic and societal impacts. Accurately predicting power outage recovery and impact is key to resilience of power grid. Recent advances in machine learning offer viable frameworks for estimating power outage duration from geospatial and weather data. However, three major challenges are inherent to the task in a real world setting: spatial dependency of the data, spatial heterogeneity of the impact, and moderate event data. We propose a novel approach to estimate the duration of severe weather-induced power outages through Graph Attention Networks (GAT). Our network uses a simple structure from unsupervised pre-training, followed by semi-supervised learning. We use field data from four major hurricanes affecting $501$ counties in eight Southeastern U.S. states. The model exhibits an excellent performance ($>93\%$ accuracy) and outperforms the existing methods XGBoost, Random Forest, GCN and simple GAT by $2\% - 15\%$ in both the overall performance and class-wise accuracy.