Regional multi-scale new energy power station output joint prediction method and system

The invention discloses a regional multi-scale new energy power station output joint prediction method and system, and the method comprises the steps of pre-processing the collected data in response to the obtained collection data, wherein the collected data comprises the predicted weather forecast data and the historical actual measurement data; and inputting the collected data into a joint output prediction model constructed based on a deep learning algorithm to output the predicted power of each station, wherein the joint output prediction model comprises an LSTM layer, a CNN layer and a full connection layer. By inputting the collected data into the constructed many-to-many mapping model based on the deep learning algorithm, the prediction power can be output, and the spatial-temporal correlation between the wind and light stations and the time sequence dependence at the prediction time are fully considered, so that the prediction precision of the model is higher, the prediction power is more accurate, th