Please use this identifier to cite or link to this item: http://ktisis.cut.ac.cy/handle/10488/7454
Title: Application of artificial neural networks for the prediction of a 20-kWp grid-connected photovoltaic plant power output
Authors: Kalogirou, Soteris A. 
Mellit, Adel 
Massi Pavan, Alessandro 
Kalogirou, Soteris A. 
Mellit, Adel 
Massi Pavan, Alessandro 
Keywords: Neural networks (Computer science)
Power-plants
Soft computing
Issue Date: 2011
Publisher: Springer
Source: Soft computing in green and renewable energy systems, 2011, Pages 261-283
Abstract: Due to various seasonal, hourly and daily changes in climate, it is relatively difficult to find a suitable analytic model for predicting the output power of Grid-Connected Photovoltaic (GCPV) plants. In this chapter, a simplified artificial neural network configuration is used for estimating the power produced by a 20kWp GCPV plant installed at Trieste, Italy. A database of experimentally measured climate (irradiance and air temperature) and electrical data (power delivered to the grid) for nine months is used. Four Multilayer-perceptron (MLP) models have been investigated in order to estimate the energy produced by the GCPV plant in question. The best MLP model has as inputs the solar irradiance and module temperature. The results show that good effectiveness is obtained between the measured and predicted power produced by the 20kWp GCPV plant. The developed model has been compared with different existing regression polynomial models in order to show its effectiveness. Three performance parameters that define the overall system performance with respect to the energy production, solar resource, and overall effect of system losses are the final PV system yield, reference yield and performance ratio
URI: http://ktisis.cut.ac.cy/handle/10488/7454
ISBN: 978-3-642-22175-0 (print)
978-3-642-22176-7 (online)
DOI: 10.1007/978-3-642-22176-7_10
Rights: © Springer-Verlag Berlin Heidelberg 2011
Appears in Collections:Κεφάλαια βιβλίων/Book chapters

Show full item record

SCOPUSTM   
Citations 20

5
checked on Jan 27, 2017

Page view(s) 10

17
checked on Mar 29, 2017

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.