Short-term Forecasting of Photovoltaic Power Based on VMD-ISSA-LSTM

To solve the characteristics of photovoltaic (PV) power generation with uncertainty and instability, the article proposes a prediction model based on variational modal decomposition (VMD), improved sparrow search algorithm (ISSA), and long short-term time memory neural network ( LSTM) to enhance the accuracy of photovoltaic power prediction and optimize the power system scheduling scheme. The model first decomposes the power and inputs the decomposed subsequence into the prediction network, then optimizes the hyper-parameters of the LSTM model through ISSA, and finally outputs the prediction results. The experimental data verification shows that the algorithm proposed in the article has higher prediction accuracy and better performance in predicting Photovoltaic power.