Photovoltaic Power Generation Forecasting Based on Variational Modal Decomposition and Ensemble Learning
Targeting the problem of power generation prediction performance caused by the non-stationarity of photovoltaic power generation data,this paper proposes a photovoltaic power generation prediction method based on improved variational mode decomposition and ensemble learning.The photovoltaic power generation data is decomposed to obtain the power generation components by the improved variational mode decomposition,and the power generation component prediction model is established with the ensemble learning.Furthermore,the predicted values of the power generation components are combined to obtain the final power generation prediction results.The experimental results show that the mean square error,average absolute error,and determinant coefficient values of the proposed method for the photovoltaic power generation prediction on public datasets are 0.223 2,0.338 7,and 0.979 7,respectively,indicating that the method has higher prediction accuracy and smaller errors than other methods.
variational mode decompositionphotovoltaic power generation predictionStacking ensemble learninggreedy algorithm
万方数据
维普
