Predicting Electricity Outages Caused by Convective Storms

TL;DR

This paper explores machine learning methods, including random forests and neural networks, to predict power outages caused by convective storms, addressing data imbalance with SMOTE.

Contribution

It introduces a classification approach for storm damage prediction using storm features and applies techniques to handle imbalanced data in this context.

Findings

Effective storm damage classification achieved

SMOTE improves rare event prediction

Deep learning models outperform traditional methods

Abstract

We consider the problem of predicting power outages in an electrical power grid due to hazards produced by convective storms. These storms produce extreme weather phenomena such as intense wind, tornadoes and lightning over a small area. In this paper, we discuss the application of state-of-the-art machine learning techniques, such as random forest classifiers and deep neural networks, to predict the amount of damage caused by storms. We cast this application as a classification problem where the goal is to classify storm cells into a finite number of classes, each corresponding to a certain amount of expected damage. The classification method use as input features estimates for storm cell location and movement which has to be extracted from the raw data. A main challenge of this application is that the training data is heavily imbalanced as the occurrence of extreme weather events is rare. In order to address this issue, we applied SMOTE technique.