Photovoltaic power prediction method and device for improving precision based on combined prediction

• Main Authors: LI ZHUOHUAN, MA XIYUAN, LI PENG, ZHOU CHANGCHENG, CHEN YANSEN, CHENG KAI, ZHANG ZIHAO, ZHOU YUE, YAO SENJING, CHEN YUANFENG, BAO TAO
• Format: Patent
• Language: Chinese; English
• Published: 13.05.2022
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRICITY; GENERATION; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention relates to a photovoltaic power prediction method and device for improving precision based on combined prediction. The method comprises the following steps: acquiring historical photovoltaic power data within a preset duration; according to the historical photovoltaic power data, high-frequency power data and average power data within a preset duration are determined, and the high-frequency power data are data with the fluctuation frequency larger than a preset value within the set duration; acquiring meteorological data, inputting the meteorological data and the high-frequency power data into the neural network model, and determining a predicted value of the high-frequency power data; and determining a photovoltaic power prediction result according to the prediction value of the high-frequency power data and the average power data. Therefore, the high-frequency power can be stripped from the overall power for targeted prediction, and the precision of power prediction is improved. 本申请涉及一种基于组合预测的