Preparedness & Recovery

Prediction Model Powers Utilities to Reduce Outage Times

Power outages are lasting longer, and this tool is aimed at cutting restoration times.

by Staff Report / June 9, 2017
Shutterstock

The added strain on utilities by an aging infrastructure and increased population coupled with more intense storms has the length of the average power outage rising. To help mitigate this, The Weather Company introduced a tool that helps utility companies prepare for an anticipated event and reduce restoration time.

The Outage Prediction Model uses a machine-learning, predictive model to combine historical weather data and up-to-date, hyperlocal weather forecasts with historical outage data for the service area. This combination allows the utility to see what areas may be hit hardest and decide where to pre-stage restoration crews and equipment.

The prediction model allows utilities to:

  • ·         Review an automated storm prediction with 72-hour lead time as weather models update in real time.
  • ·         Perform historical storm searches, comparing current weather forecast conditions and predicted outages to past outcomes under similar weather conditions.
  • ·         Plan for best and worst-case scenarios looking at variable factors, such as wind speed, precipitation, temperature and humidity.

“With our new Outage Prediction solution, storm operations and emergency management teams are now able to make the best possible decision with all sources of information available to them, which will improve restoration times, boost customer and regulatory satisfaction and possibly save the utility millions of dollars per year,” said Mark Gildersleeve, president of business solutions, in a press release.

The prediction model accounts for parameters, including atmospheric pressure, soil moisture, and foliage. It includes other data such as types of vegetation, seasonality, or other information such as assets that could be incorporated based on location, weather regime and system design. The model allows for an individualized solution for each situation.