Spatio-temporal prediction for distributed PV generation system based on deep learning neural network model

To obtain higher accuracy of PV prediction to enhance power generation technology. This paper proposes a spatio-temporal method based on deep learning neural network model. Firstly, correlation analysis is performed for 17 sites. Secondly, we compare CNN-LSTM with single CNN or LSTM model trained the same dataset. From evaluation indexes such as loss map, regression RMSE, and MAE, that considers strong among sites has better performance. The results show our accuracy.