Prediction of Short-Term Photovoltaic Power Based on SSA-BPNN Model

Meteorological factors affecting photovoltaic power generation are considered in order to improve the accuracy of photovoltaic power prediction, to promote the effective consumption of photovoltaic power generation and to improve the stability of the power system, the meteorological data were preprocessed using Spearman correlation analysis and normalization. Then the back-propagation neural network model is optimized using the sparrow search algorithm to obtain the best weights and thresholds, and the short-term PV power prediction model based on SSA-BPNN is established. The example simulation shows that the SSA-BPNN prediction model has a better fit between the predicted power curve and the actual power curve, MAE is 0.0392 and RMSE is 0.0737, lower prediction error than the original BPNN prediction model. The results show that the developed prediction model can improve the prediction accuracy of short-term PV power and make the power system stability improved.