An on-line prediction algorithm able to estimate, over a determined time horizon, the solar irradiation of a specific site is considered. The learning algorithm is based on Radial Basis Function (RBF) networks and combines the growing criterion and the pruning strategy of the minimal resource allocating network technique. An adaptive extended Kalman filter is used to update all the parameters of the Neural Network (NN). The on-line learning mechanism avoids the initial training of the NN with a large data set. The proposed solution has been experimentally tested on a 14 kWp PhotoVoltaic (PV) plant and results are compared to a classical RBF neural network. © Springer-Verlag Berlin Heidelberg 2013.
Solar irradiation forecasting for PV systems by fully tuned minimal RBF neural networks / Ciabattoni, Lucio; Ippoliti, Gianluca; Longhi, Sauro; Pirro, Matteo; Cavalletti, Matteo. - 19:(2013), pp. 289-300. [10.1007/978-3-642-35467-0_29]
Solar irradiation forecasting for PV systems by fully tuned minimal RBF neural networks
CIABATTONI, LUCIO;IPPOLITI, Gianluca;LONGHI, SAURO;PIRRO, MATTEO;CAVALLETTI, MATTEO
2013-01-01
Abstract
An on-line prediction algorithm able to estimate, over a determined time horizon, the solar irradiation of a specific site is considered. The learning algorithm is based on Radial Basis Function (RBF) networks and combines the growing criterion and the pruning strategy of the minimal resource allocating network technique. An adaptive extended Kalman filter is used to update all the parameters of the Neural Network (NN). The on-line learning mechanism avoids the initial training of the NN with a large data set. The proposed solution has been experimentally tested on a 14 kWp PhotoVoltaic (PV) plant and results are compared to a classical RBF neural network. © Springer-Verlag Berlin Heidelberg 2013.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
