The operation of the distribution system of an electric utility, particularly with an overhead infrastructure, can be highly sensitive to local weather conditions. Hence, the ability to predict specific events or combination of weather conditions that can disrupt that distribution network with sufficient spatial and temporal precision, and lead time has the potential to enable proactive allocation and deployment of resources (people and equipment) to minimize time for restoration.

To determine the viability of this idea, we build upon earlier efforts at the IBM Thomas J. Watson Research Center to implement and apply an operational mesoscale prediction system to business problems, dubbed “Deep Thunder”. In particular, we have extended our capabilities in the New York City metropolitan area in several key ways, working with the emergency management group at a major utility company in the northeastern United States. The first was implementing a number of customized visualizations available via a web browser, which are automatically updated for each forecast cycle. They reflect the relevant weather conditions and predicted threats, and incorporate information concerning the utility's infrastructure and resource response thresholds. This was part of an overall effort to tailor the underlying software and hardware system to meet the geographic, throughput and dissemination requirements of the utility operations. Data from a local, relatively dense mesonet were utilized to validate and improve the forecasts, which include both model tuning and assimilation for initialization. Historical observations from the mesonet were analyzed along with data from the utility concerning the characteristics of outage-related infrastructure damage from weather events, as well as the information about the distribution network and local environmental conditions. This enabled the development of a statistical representation of outage-related infrastructure damage for predictive purposes. This infrastructure damage estimation model can then be used with weather forecast information derived from the Deep Thunder modeling capability as well as in real-time from observations available from the aforementioned mesonet. Finally, the initial focus of the numerical weather prediction component was to provide 24-hour forecasts at resolutions as high as one km. This was then extended to include complementary model results at a somewhat broader geographic scale for up to three days to enable longer-term planning.

We will discuss the on-going work, which began in 2007, the overall approach to the problem, some specifics of the solution, and lessons that were learned through the development and deployment. We will present how the content is being used and its quality with respect to specific weather events that affected utility operations. We will also discuss some results concerning the overall effectiveness of such modelling capabilities and this particular approach for these applications and recommendations for future work.