An approach for day-ahead interval forecasting of photovoltaic power: A novel DCGAN and LSTM based quantile regression modeling method

Abstract

In order to effectively quantify the uncertainty of PV power and improve the forecasting accuracy, a day-ahead interval forecasting method of PV power based on multi-correlation parameter scenarios generation is proposed. The historical PV power data is divided into a limited set of scenarios representing different output and fluctuation characteristics through the K-means clustering algorithm; Combined with the strong correlation feature parameters determined by the correlation coefficient, the characteristic curves of PV power and multi-correlation parameter in different scenarios are generated through the deep convolutional generative adversarial networks (DCGAN) model; The average value of each characteristic curve and other explanatory variables are input together into a quantile regression long short-term memory (QRLSTM) model to achieve day-ahead PV power forecasting, and obtain the forecasting interval under different confidence levels. The results of the experiment of a PV power station in Yangzhou, Jiangsu Province, China show that the forecasting performance of the proposed method under different evaluation indicators is 17.9755% and 18.1571% higher than that of the Gaussian process regression (GPR) model and the single QRLSTM model, respectively, which has obvious advantages.