Photovoltaic power generation power interval prediction method based on cloud cover characteristics of foundation cloud picture

The invention discloses a photovoltaic power generation power interval prediction method based on cloud cover characteristics of a foundation cloud picture, and the method comprises the steps: extracting the cloud cover characteristics of the foundation cloud picture of a photovoltaic power station according to a dense optical flow algorithm; obtaining input characteristics according to the cloud cover characteristics, the original photoelectric data of the photovoltaic power station and the corresponding meteorological data; adopting a bootstrap method to carry out resampling on the input features to obtain a plurality of data training samples; based on an attention mechanism, establishing a B-Informer network interval prediction model; and training the B-Informer network interval prediction model according to the plurality of data training samples to obtain a prediction result of the photovoltaic power generation power interval. According to the method, the precision of the training model and the accuracy o