Aiming at the random change of photovoltaic power generation,this paper proposed a photovoltaic power interval prediction method based on principal component analysis and long short-term memory neural network,which effectively realized the interval prediction of photovoltaic power.Firstly,reduce the dimensions of the input data used for the training model by principal component analysis,which reduce the data dimensions while extracting data features.Then,input the reduced dimension data and the real photovoltaic power into the quantile based long short-term memory neural network prediction model for iterative training to obtain the trained prediction model.Finally,the effectiveness of the proposed method is verified in the comparative simulation.
long short-term memory neural networkquantile regressioninterval predictionprincipal component analysis
维普
万方数据
