AUTHOR=Huang Ruanming , Wang Xiaohui , Fei Fei , Li Haoen , Wu Enqi TITLE=Forecast Method of Distributed Photovoltaic Power Generation Based on EM-WS-CNN Neural Networks JOURNAL=Frontiers in Energy Research VOLUME=10 YEAR=2022 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2022.902722 DOI=10.3389/fenrg.2022.902722 ISSN=2296-598X ABSTRACT=
In order to cope with the challenges of dispatching of power grids brought by large-scale distributed photovoltaic power generation related to production and consumers, a maximum expected sample weighted convolutional neural network (EM-WS-CNN) is proposed to forecast the distributed photovoltaic output. First, the distance correlation coefficient and the principal component analysis method are used to extract the comprehensive meteorological factors from the original meteorological data, and then the 6 statistical indexes of the comprehensive meteorological factors and historical power data are used as the clustering characteristics. The historical data are divided into different weather types by using the maximum expectation clustering, and the training samples are weighted based on the membership matrix. Finally, the weighted training data are used to construct the EM-WS-CNN model. In the experimental analysis, the above-mentioned method is compared with the CNN model, and the results show that the proposed method has higher accuracy and robustness.