Method, system and equipment for combined optimization prediction of photovoltaic power, and medium

• Main Authors: SUN HONGYAN, ZHENG MINGMING, QI YURONG, LIU JUN, WANG LILI, QI SIBO, LI YU, HU CHENGGANG, TIAN YING, WANG YINGFANG, ZHANG LANXI, ZHANG RUI, YANG MENG, WU SHUAI, TAKAYA, HU YI, ZHANG SHANRUI, ZHANG YANG, XIAO KUNJUN, SEO SEUNG-HWI
• Format: Patent
• Language: Chinese; English
• Published: 09.01.2024
• 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; ELECTRIC DIGITAL DATA PROCESSING; ELECTRICITY; GENERATION; PHYSICS; SYSTEMS FOR STORING ELECTRIC ENERGY

The invention relates to the technical field of photovoltaic power generation prediction, in particular to a method, a system, equipment and a medium for combined optimization prediction of photovoltaic power. The method comprises the steps of firstly preprocessing acquired photovoltaic data, and then converting the preprocessed photovoltaic data into a topological graph adjacency matrix to obtain a first predicted value; calling a long-short-term memory network to carry out linear transformation mapping on the photovoltaic data characteristics to obtain a second predicted value; and finally, jointly optimizing the first predicted value and the second predicted value according to a set joint optimization weight to obtain a final photovoltaic power predicted value. By fully mining the feature information in the photovoltaic data, the accuracy of photovoltaic power prediction is effectively improved. 本发明涉及光伏发电预测技术领域，具体地说，涉及一种联合优化预测光伏功率的方法、系统、设备及介质；该方法首先预处理获取的光伏数据，然后将预处理后的所述光伏数据转换为拓扑图邻接矩阵得到第一预测值；调用长短期记忆网络线性变换映射光