Prediction of Expressway Slope Photovoltaic Power Generation Based on Green Transportation
As an environmentally friendly,sustainable,and clean energy technology,slope photovoltaic power generation helps develop green transportation.In this paper,the field-collected data of slope photovoltaic power generation was preprocessed to analyze the data variation rules.The proportion of outliers was preliminary estimated by the box plot,and outliers were accurately identified by the isolated forest model,then predicted and filled by the LightGBM model.Besides,based on the concept of time series prediction,the GRU model was established to predict the photovoltaic power generation for various time intervals(1 hour,2 hours,3 hours,1 day,2 days,and 3 days),and the model was evaluated by the assessment indexes.The results showed that the established GRU model can accurately predict the photovoltaic power generation under different prediction intervals,providing a foundation for predicting slope photovoltaic power generation in the future.
photovoltaic power generationdata predictionisolated forest modelLightGBM modelGRU model
万方数据
维普
