A Combined Optimization Structure of Adaptive Neuro-fuzzy Inference System for Probabilistic Photovoltaic Power Forecasting

The uncertainties of solar energy due to weather fluctuations will cause impact on photovoltaic (PV) integrated power system, limiting its further development. Hence, a novel probabilistic PV power forecasting approach based on lower upper bound estimation (LUBE) is proposed in this study, which consists of adaptive neuro-fuzzy inference system (ANFIS), modified grey wolf optimization (MGWO) algorithm and kernel density estimation (KDE). In the proposed method, two ANFIS models are combined as a group and optimized using MGWO. The output prediction intervals (PIs) from various groups are also merged together through KDE, which enhance the robustness and reliability of a sole optimized model. Owing to different quality indicators that measure diverse aspects of PIs, the proposed method achieves superior prediction results when compared with conventional forecasting methods.