Photovoltaic power prediction method and system based on deep mixed kernel extreme learning machine model

• Main Authors: SUN TIANLE, WU YAJUN, WU DONGCHENG, ZHU HAOJIE, FANG JIANI, WANG JIAXIN, HAN GA-YOUNG, ZHANG JINJIANG
• Format: Patent
• Language: Chinese; English
• Published: 21.06.2024
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention discloses a photovoltaic power prediction method and system based on a deep mixed kernel extreme learning machine model, and the method comprises the following steps: S1, carrying out the preprocessing of data, dividing a data set into a training set and a test set, and carrying out the screening of meteorological factors through the SCC; s2, performing similar daily clustering on the original data by using a K-means algorithm, dividing the data into three categories of sunny days, cloudy days and rainy days, selecting the last day as a test set, and taking the rest as training samples; s3, performing variational mode decomposition (VMD) decomposition on the photovoltaic power generation power in the first type of weather, and inputting decomposed data and meteorological factors into the DHKELM as data; s4, initializing IDBO parameters, and setting a population scale and a maximum number of iterations; s5, constructing a DHKELM model, respectively sending the training set and the test set into t