Segmented day-ahead electric power limit prediction method and device based on whole network load rate

• Main Authors: SUN CAIXIN, YI WEIFENG, SHEN XUHUI, YAN YAO, GUAN HEGEGE, WANG HONGCE, SONG LITAO, WANG QIANG, PAN XIAOFENG
• Format: Patent
• Language: Chinese; English
• Published: 10.01.2023
• Subjects: CALCULATING; 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 provides a segmented day-ahead electric power limit prediction method and equipment based on a whole-network load rate, and the method comprises the steps: finding that the whole-network load rate and the day-ahead electric power price have high correlation through data analysis, and building a whole-network load rate algorithm model; the day-ahead electricity price is predicted through the whole-network load rate data characteristics, and only 7-30 days of historical data is needed, so that the demand on a historical data set is greatly reduced; according to the method, a sectional prediction algorithm based on the whole-network load rate characteristics is used, on the premise that the whole-network load rate characteristics with strong interpretability are adopted, the time-sharing difference of day-ahead electricity prices is considered, and the distribution rule of the whole-network load rates and the time-sharing electricity prices at different moments is described in a fine-grained mode.