A novel hybrid data-driven PV output prediction method based on error correction

Under the background of dual carbon, China's installed photovoltaic (PV) capacity has been consistently increasing, and prediction of PV output is of great significance to the safe operation of the power grid. In this paper, seven algorithms are selected to build data-driven sub-models and merged through multivariate linear regression to obtain a hybrid data-driven model. Then, a novel hybrid data-driven PV output prediction model is developed based on weather conditions and adjacent PV outputs. Finally, an error correction model based on mechanism modeling and similar day statistical modeling is built, and a new hybrid data-driven PV output prediction method based on error correction is obtained.