Short-term prediction of PV power based on fusions of power series and ramp series

Abstract

Photovoltaic (PV) power generation is highly volatile and intermittent, which poses a major challenge to the prediction and intra-day scheduling of PV power. In order to effectively improve the prediction accuracy of PV power, this paper proposes a short-term prediction model through the fusion of power series and ramp series based on CNN-LSTM models. In the proposed hybrid model, both the power series prediction module and the ramp series prediction module are used to simultaneously predict the PV power, and then the results of both modules are combined by fully connected layers and corrected by a residual network to obtain the final prediction results. The prediction effects of the proposed model are illustrated by a multi-level evaluation system of prediction errors, including the evaluation of overall prediction errors, local prediction errors, and ramp point prediction errors. Case studies show that the ramp series of PV power can better characterize the fluctuation of PV power and that the proposed model has a better prediction effect than other models.