Over the next two years, scientists and engineers from NCAR will develop custom forecasting systems to allow Xcel Energy control centres in Minneapolis, Denver, Golden, Colorado, and Amarillo, Texas, to anticipate sudden changes in wind, shut down turbines ahead of potentially damaging icing events and predict the amount of energy generated by private solar panels.

The systems use highly detailed observations of atmospheric conditions, an ensemble of powerful computer models, and artificial intelligence techniques to issue high-resolution forecasts for wind farm sites. The forecasts are designed to help Xcel Energy provide power to its customers and reduce costs while moving to greater use of wind and solar. 

Xcel Energy is increasing its use of renewable energy in its territories served by public power companies Public Service Company of Colorado, Northern States Power Company of Minnesota, NSP-Wisconsin and Southwestern Public Service Company. The agreement with NCAR has already saved Xcel Energy's 3.4 million electricity customers millions of dollars, the company claimed.

"Xcel Energy has been the nation's largest utility provider of wind energy for the last nine years, and as our renewable energy portfolio continues to grow, accurate forecasts become increasingly important," said Ben Fowke, chairman, president and CEO of Xcel Energy.

"By creating more detailed and accurate forecasts of wind and sun, we can produce a major return on investment for utilities," said Thomas Bogdan, president of the University Corporation for Atmospheric Research, which manages NCAR on behalf of the National Science Foundation. "This type of cutting-edge research helps make renewable energy more cost competitive."

NCAR has also instigated a three-year US project to create 36 hour forecasts of incoming energy from the sun for solar energy power plants.