Spatially Aware Ensemble-Based Learning to Predict Weather-Related Outages in Transmission

Abstract

This paper describes the implementation of prediction model for real-time assessment of weather related outages in the electric transmission system. The network data and historical outages are correlated with variety of weather sources in order to construct the knowledge extraction platform for accurate outage probability prediction. An extension of logistic regression prediction model that embeds the spatial configuration of the network was used for prediction. The results show that developed algorithm has very high accuracy and is able to differentiate the outage area from the rest of the network in 1 to 3 hours before the outage. The prediction algorithm is integrated inside weather testbed for real-time mapping of network outage probabilities using incoming weather forecast.