Publications / Conference Poster

Improving wind power prediction intervals using vendor-supplied probabilistic forecast information

Nitsche, Sabrina; Silva-Monroy, Cesar A.; Staid, Andrea S.; Watson, Jean-Paul W.; Winner, Scott; Woodruff, David L.

We describe experiments concerning enhancing a simple, yet effective method to compute high-accuracy prediction intervals (PIs) for day-ahead wide area wind power forecasts. The resulting PIs are useful for operators and traders, to improve reliability, anticipate threats, and increase situational awareness. Sandia National Laboratories is a multi-program laboratory managed and operated by Sandia Corporation, a wholly owned subsidiary of Lockheed Martin Corporation, for the U.S. Department of Energy's National Nuclear Security Administration under Contract DE-AC04-94-AL85000. This work was funded by the Bonneville Power Administration (BPA).