Risk due to load forecast uncertainty in short term power system planning

This paper presents a methodology to analyze the risk of short term power system operational planning in the presence of electrical load forecast uncertainty. As the authors' methodology requires an estimate of the load forecast variance, a Bayesian load forecaster is used in the practical implementation. They express their results as a function of forecast lead time from one to five days into the future, in terms of $/MWH. The risk due to load forecast uncertainty is based on the forecast variance, and found by determining the expected cost of perfect information. They illustrate their risk evaluation method in a case study with utility-derived power system data and temperature forecast data from the US National Weather Service.