Wind power station output ultra-short time prediction method based on least square support vector machine

• Main Authors: HUA DANQIONG, ZHANG JIANBU, XING RUIMIN, SHEN RUNJIE
• Format: Patent
• Language: Chinese; English
• Published: 02.06.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a wind power station output ultra-short time prediction method based on a least square support vector machine. The method specifically comprises the following steps: S1, decomposing a wind speed time sequence into N modal components with different scales by utilizing variational modal decomposition; s2, respectively establishing an LSSVM prediction model of a least squaresupport vector machine for each modal component; s3, segmenting the data set of the wind speed historical sequence into a training set, a cross validation set and a test set, and normalizing the data;and S4, training the LSSVM prediction model in a rolling manner through the training set, optimizing the kernel width and penalty factor of the LSSVM prediction model on the cross validation set by using a particle swarm optimization algorithm, and then testing errors on the test set to obtain an optimal LSSVM prediction model smaller than an error threshold. Compared with the prior art, the method has the advantages of r