Risk management of power outages caused by severe weather events, such as hurricanes, tornadoes, and thunderstorms, plays an important role in electric utility distribution operations. Damage prediction based on weather forecasts on an appropriate spatial scale can improve the efficiency of risk management by reducing the economic and societal costs associated with restoration efforts. We have developed a method of predicting the number of outages in a fashion that is suitable for use by electric utilities by using a Poisson regression model for spatial data in a Bayesian hierarchical framework. Particular attention is given to building models that incorporate uncertainty in the outage data from the perspective of multiple spatial resolutions and spatial correlation in the outage data. The outage-prediction model was developed using historical outage data from an electric utility company in the northeastern part of the United States. The model is being used by that company in the operations of its overhead electrical distribution system and emergency management operations. We discuss results to date and how the model is being applied. In addition to the damage forecasts, we have developed tools for risk visualization by displaying the uncertainty of the damage forecasts on geographic maps.
Note: The Institute of Electrical and Electronics Engineers, Incorporated is distributing this Article with permission of the International Business Machines Corporation (IBM) who is the exclusive owner. The recipient of this Article may not assign, sublicense, lease, rent or otherwise transfer, reproduce, prepare derivative works, publicly display or perform, or distribute the Article.
IBM Journal of Research and Development
Date of Publication:
- ISSN :
- Date of Current Version :
13 May 2010
- Issue Date :
- Sponsored by :