Characterization for photovoltaic generation systems via Higher Order Wavelet Neural Networks

This paper focusses on applications of neural networks for forecasting in photovoltaic arrays. A Higher Order Wavelet Neural Network trained with an extended Kalman Filter training algorithm is implemented for data modeling in smart grids. The length of the regression vector is determined using the Cao methodology. The applicability of this architecture is illustrated via simulation using real data values from Photovoltaic modules.