Photovoltaic output typical scene generation method and system, and storage medium

• Main Authors: WU HUAHUA, WU XIAOGANG, WU XINHUA, ZENG KAILE, YE JIEYANG, SUN KE, ZHANG SI, WU YIFENG, ZHOU MIAOFEI, HU XINWEI, XU LIZHONG, YE JICHAO, TAO YUFENG, YANG LI, JI QINGFENG, JIANG XINYUE, WANG QIANYING, ZHOU YIZHI
• Format: Patent
• Language: Chinese; English
• Published: 29.12.2023
• 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 discloses a photovoltaic output typical scene generation method and system, and a storage medium. The method comprises the steps of obtaining a photovoltaic output sample group, forming a tree diagram, determining an optimal cluster number, obtaining a photovoltaic output typical scene, and determining the probability of the typical scene. A large number of sample groups containing similar photovoltaic output scenes are clustered based on an agglomerated hierarchical clustering algorithm, the number of finally formed photovoltaic output clustering clusters is indirectly controlled through the sum of squares of errors, the photovoltaic output samples are divided more finely, corresponding cluster points of a tree diagram are cut off through the optimal clustering cluster number, and the clustering efficiency of the tree diagram is improved. The influence caused by the uncertainty of the photovoltaic output data set is effectively overcome, and the photovoltaic output typical scene probability is