分布式光伏与数字孪生理念相结合,是应对大规模并网光伏群控挑战的有效方法,也是推进新型电力系统建设的重要内容。该文提出一种面向分布式光伏群调群控的数字孪生方法,拟从光伏一致性表征、孪生模型重建、功率推演预测3个方面支撑孪生系统构建。基于K-means算法提出光伏一致性表征方法,利用皮尔逊系数加权构造气象因子与光伏并网节点的电压灵敏度作为指标,对配电网电压影响相似的光伏进行聚类;以运动恢复结构(structure from motion
Fei Wang,Zhiming Xuan,Zhao Zhen,Kangping Li,Tieqiang Wang,Min Shi.A day-ahead PV power forecasting method based on LSTM-RNN model and time correlation modification under partial daily pattern prediction framework[J].Energy Conversion and Management,2020.
Kejun Wang,Xiaoxia Qi,Hongda Liu.A comparison of day-ahead photovoltaic power forecasting models based on deep learning neural network[J].Applied Energy,2019.
Yunjun Yu,Junfei Cao,Jianyong Zhu.An LSTM Short-Term Solar Irradiance Forecasting Under Complicated Weather Conditions.[J].IEEE Access,2019.
Han Pingping,Lin Zihao,Wang Lei,Fan Guijun,Zhang Xiaoan.A Survey on Equivalence Modeling for Large-Scale Photovoltaic Power Plants[J].Energies,2018.
JorgeJ.Moré.The Levenberg-Marquardt algorithm: Implementation and theory[J].Lecture Notes in Mathematics,1978(1).