Wind power group power prediction method and device based on numerical weather forecast

• Main Authors: LIU XIAOLIN, HUA SHENBING, WANG ZHENG, ZHANG FEI, SONG ZONGPENG, WANG BO, WANG SHU, WANG ZHAO, FENG SHUANGLEI, DING YU, JIN SHUANGLONG, ZHAO YANQING, LIU CHUN, CHE JIANFENG
• Format: Patent
• Language: Chinese; English
• Published: 23.06.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The invention relates to the technical field of new energy power generation and dispatching operation, and particularly provides a wind power group power prediction method and device based on numerical weather forecast, and the method comprises the steps: inputting the grid numerical weather forecast data of a prediction day into a pre-constructed auto-encoder model, obtaining dimension reduction data output by the pre-constructed auto-encoder model, and determining a weather process to which the dimension reduction data belongs; and inputting the dimension-reduced data into a power prediction model corresponding to the weather process to which the dimension-reduced data belongs, and obtaining predicted daily power data output by the power prediction model. According to the technical scheme provided by the invention, the power prediction precision of a wind power group can be remarkably improved, the probability of occurrence of a maximum error is reduced, and wind power consumption is promoted. 本发明涉及新能源发电及调度