Spatio-Temporal Conformal Prediction for Power Outage Data

TL;DR

This paper introduces a graph conformal prediction method to accurately forecast power outage numbers across states during extreme weather events, enhancing resilience and recovery planning.

Contribution

It presents a novel spatio-temporal conformal prediction approach tailored for power outage data, improving prediction accuracy over traditional methods.

Findings

Effective prediction regions for outage numbers across multiple states.

Demonstrated robustness during extreme weather events.

Enhanced power outage resilience planning.

Abstract

In recent years, increasingly unpredictable and severe global weather patterns have frequently caused long-lasting power outages. Building resilience, the ability to withstand, adapt to, and recover from major disruptions, has become crucial for the power industry. To enable rapid recovery, accurately predicting future outage numbers is essential. Rather than relying on simple point estimates, we analyze extensive quarter-hourly outage data and develop a graph conformal prediction method that delivers accurate prediction regions for outage numbers across the states for a time period. We demonstrate the effectiveness of this method through extensive numerical experiments in several states affected by extreme weather events that led to widespread outages.