POWER SYSTEM OPERATING RESERVE QUANTIFICATION METHOD BASED ON WIND POWER PROBABILITY PREDICTION

A power system operating reserve quantification method based on wind power probability prediction. In the method, a confidence level and a boundary quantile level of a prediction interval are not required to be preset, the lowest confidence level of the prediction interval with respect to a training sample is defined by means of an inequality constraint, and an extreme learning machine directly outputs a wind power prediction interval; system positive and negative operating reserve capacity requirements are determined on the basis of boundaries of the interval, reserve cost and reserve vacancy punishment are taken as a loss function, a power system operating reserve optimization model based on the wind power probability prediction is constructed, and the operating reserve optimization model based on the wind power probability prediction is constructed as a mixed integer linear programming problem. According to the method, the cost benefit brought by providing reserve can be balanced on the premise that a rese