Wind power prediction method taking wind electricity uncertainty risk into account

Abstract

The invention provides a wind power prediction method taking wind electricity uncertainty risk into account. On the basis of a mixed distribution model, a self-adaption mixed uncertainty probabilisticmodeling method using a risk value VaR as a training target is provided, according to the method, firstly, historical wind electricity data is adopted for generating a training set, then the risk value VaR is used as the training target for updating a training sample, finally, through multiple rounds of studying, a high-precision day-ahead wind power prediction error mixed probabilistic model isgenerated, and the power generation economical efficiency can be effectively improved.

Description

Technical field [0001] The invention relates to the field of power generation, and in particular to a wind power prediction method considering the uncertainty risk of wind power. Background technique [0002] After long-term engineering practice and national "blowout" development, wind power generation has proven to be a reliable, clean energy that can be developed and utilized on a large scale. However, with the further increase of the power penetration rate of wind energy, the volatility and randomness of wind energy itself have brought challenges to the accurate formulation of the day-ahead power generation plan. In the context of the current wind power forecast error generally as high as 10%-20%, on the one hand, the high penetration of wind power sources forces the dispatching agency to purchase a large amount of power reserve during the previous generation plan stage to maintain the power balance of the grid operation in the day. On the one hand, due to the fact that the a...

AI Technical Summary

Problems solved by technology

However, in the uncertainty modeling process, the fact that the wind power forecast uncertainty tail distribution (high error interval) has a much greater impact on the economics of day-ahead power generation planning than the head distribution (error low value interval) is not considered. , there is no targeted modeling of the tail distribution of forecast uncertainty, which affects the further improvement of system economy

Images