Short-Term Photovoltaic Power Prediction Modeling Based on AdaBoost Algorithm and Elman

In recent years, with the rapid expansion of the installed capacity of renewable energy systems, the availability, stability and quality of smart grids have become increasingly important^[1]. The application of renewable energy production forecasting has also been rapidly developed, especially in the field of solar photovoltaic (PV)^[2][3]. In the example of solar PV output prediction, machine learning and hybrid technologies have been implemented for many applications. In this paper, a high-precision PV system output power prediction model based on improved AdaBoost and Elman is proposed. Multiple model using integrated AdaBoost algorithm fusion with the bat algorithm for the parameters of optimized combination of weak Elman neural network predictor to become a higher prediction precision, the method of strong predictor of the model can according to the weather information, such as temperature, solar radiation and the history of the output of the PV system data, the probability of photovoltaic power generation for 12 hours and deterministic prediction. The prediction accuracy of the model is determined by Root Mean Squared Error (RMSE). Experimental results show that the prediction accuracy of this algorithm is better than that of other benchmark models, and the algorithm can effectively predict the volatility and irregularity of complex time series.