Ensemble Deep Learning Model for Power System Outage Prediction for Resilience Enhancement

Extreme weather events can cause power outages anywhere, but quite extensively along the U.S. southeastern coastline. Accurate outage prediction before a hurricane landfall is essential for reducing the impacts from distribution outage management and restoration planning perspectives. An outage prediction model (OPM) is developed to predict outages associated with substations based on data collated from multiple sources using tree-based ensemble machine learning regression algorithm. For this study, publicly available data as well as actual outage data from a major utility in the U.S. are employed. Performance validation of outage prediction models is done using several extreme weather events data over the past decade. Results confirm enhancement in accuracy for power outage predictions over baseline approaches.