A hybrid ensembled double-input-fuzzy-modules based precise prediction of PV power generation

As one of the most widespread renewable energy technologies, photovoltaic power generation system provides great environmental and economic benefits. Achieving precise prediction for PV will greatly improve quality electric enhance stability operation. Inspired by powerful ability fuzzy logic to deal with uncertainty superiority machine learning handle time series prediction, a hybrid ensembled model consisted Double-Input-Fuzzy-Modules (DIFM) Extreme Learning Machine is proposed in this paper. Firstly, data taken as input each DIFM order efficiently uncertainties. Then, outputs are used ELM. Moreover, least square estimation applied train parameters further predict precision. Finally, achieve real-world forecasting. The cases study comparisons results indicate that outperforms other methods, terms mean absolute error, root means error coefficient determination.