Wind power output typical scene generation method based on BIRCH clustering and Wasserstein distance

Abstract

The invention discloses a wind power output typical scene generation method based on BIRCH clustering and a Wasserstein distance, and the method comprises the steps: firstly obtaining an optimal quantile of a wind power probability through the minimization of the Wasserstein distance, and discretizing a continuous probability density function into a plurality of probability density points; performing iterative reduction, splicing and re-reduction on the initial scene set by applying BIRCH clustering to obtain a typical scene set. According to the method, the wind power output scene can be quickly and accurately reduced, and compared with other algorithms, the algorithm has great advantages in calculation time and storage scale.

Description

technical field [0001] The invention relates to a method for generating typical scenarios of wind power output based on BIRCH clustering and Wasserstein distance. Background technique [0002] In recent years, the scale of China's wind power generation has grown rapidly, becoming China's third largest source of electricity. Wind power generation has problems such as too large sampling scene set, which affects computing efficiency, etc. These problems can be solved by scene reduction. However, most of the existing scene reduction methods need to calculate and compare all possible distance combinations, and there are disadvantages such as large amount of calculation and low calculation efficiency when the number of scenes is large. Contents of the invention [0003] The purpose of the present invention is to provide an efficient method for generating typical scenarios of wind power output based on BIRCH clustering and Wasserstein distance. [0004] Technical solution of th...

AI Technical Summary

Problems solved by technology

Wind power generation has problems such as too large sampling scene set, which affects computing efficiency, etc. These problems can be solved by scene reduction

However, most of the existing scene reduction methods need to calculate and compare all possible distance combinations. When the number of scenes is large, there are disadvantages such as large amount of calculation and low calculation efficiency.

Images