An Artificial Neural Network (ANN) approach is used to estimate power production yield by a 1 kWp experimental micro-morph silicon modules plant located at ENEA Portici Research Centre, in Italy South region. A large dataset consisting of data, measured every five minutes and acquired from 2006 to 2012, is used for the training/test of the ANN. First, AC power production evaluation is obtained from single-hidden layer Multi-Layer Perceptron (MPL) Neural Network with two inputs consisting in ambient temperature and solar global radiation. In order to improve the approximation of the AC power, the clear sky solar radiation is then added as input of the ANN. Experimental data are reported to demonstrate the feasibility and the potentiality of the adopted solutions. © 2014 IEEE.

Performance estimation of a thin-film photovoltaic plant based on an Artificial Neural Network model

Adinolfi, G.;Ferlito, S.;Graditi, G.
2014

Abstract

An Artificial Neural Network (ANN) approach is used to estimate power production yield by a 1 kWp experimental micro-morph silicon modules plant located at ENEA Portici Research Centre, in Italy South region. A large dataset consisting of data, measured every five minutes and acquired from 2006 to 2012, is used for the training/test of the ANN. First, AC power production evaluation is obtained from single-hidden layer Multi-Layer Perceptron (MPL) Neural Network with two inputs consisting in ambient temperature and solar global radiation. In order to improve the approximation of the AC power, the clear sky solar radiation is then added as input of the ANN. Experimental data are reported to demonstrate the feasibility and the potentiality of the adopted solutions. © 2014 IEEE.
9781479921966
photovoltaic production;Artificial Neural Network;MLP
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.12079/3782
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
social impact