Ultra-short-term photovoltaic power generation power prediction method and device and storage medium

The invention discloses an ultra-short-term photovoltaic power generation power prediction method and device and a storage medium, and the method comprises the steps: obtaining data related to a centralized photovoltaic power station, including basic data, historical operation data, historical meteorological data and meteorological forecast data of the centralized photovoltaic power station, and generating a plurality of original data sequences; determining a preset wavelet decomposition layer number, and performing wavelet decomposition processing on the original data sequence to generate a sample data set; training and optimizing a preset original prediction model according to the sample data set to obtain a target prediction model; wherein the target prediction model is of a CNN-LSTM network structure, and the target prediction model is used for predicting the photovoltaic power generation power of the centralized photovoltaic power station in a future preset duration. By adopting the method, the accuracy