Wind power plant ultra-short-term output prediction method for dynamically dividing prediction period

• Main Authors: NIU HUAQING, ZHANG JIAZHONG, ZHANG MINGHUI, ZHANG YI, ZHAO WEI
• Format: Patent
• Language: Chinese; English
• Published: 30.04.2024
• Subjects: CALCULATING; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER; COMPUTING; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; 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 provides a wind power plant ultra-short-term output prediction method for dynamically dividing a prediction period, which combines the spatial distance between wind power plants and the output fluctuation correlation during prediction, and specifically comprises the following steps: firstly, calculating the time difference between similar output changes of the wind power plants based on the wind speed, the wind direction and the geographic position of each wind power plant; dynamically dividing the ultra-short-term prediction period of the target wind power plant into a time period with prior information and a time period without prior information; secondly, comprehensively considering the incidence relation among the historical output, the prior information and the predicted output by using a variational Bayesian model, and predicting the output of the target wind power plant in the time period with the prior information; and finally, predicting a time period without prior information to obtain