IDIES affiliate Dr. Seth Guikema of the Department of Geography and Environmental Engineering and collaborators have proposed a data-inferred model that predicts power outages for tropical cyclones with great accuracy.
New model proposed to predict power outages following severe storms
A new outage-forecasting model has been developed by IDIES affiliate Dr. Seth Guikema of the Department of Geography and Environmental Engineering and collaborators. The model estimates hurricane-induced outages prior to landfall with great predictive accuracy, based on only few input variables. The model is developed based on the method of random forest, using extensive data from a power distribution system serving two states in the Gulf Coast region of the United States. The intended users of these models are emergency response planners within power utilities and related government agencies. Estimates of system reliability based on wind speed alone are shown not to be sufficient for adequately capturing the reliability of system components while a multivariate approach can produce more accurate power outage predictions.