Please use this identifier to cite or link to this item:
Title: Application of neural networks and genetic algorithms for sizing of photovoltaic systems
Authors: Mellit, Adel 
Drif, Mahmoud 
Kalogirou, Soteris A. 
Mellit, Adel 
Drif, Mahmoud 
Keywords: Neural networks (Computer science);Genetic algorithms;Number theory
Category: Environmental Engineering
Field: Engineering and Technology
Issue Date: 2010
Publisher: Elsevier
Source: Renewable energy, 2010, Volume 35, Issue 12, Pages 2881–2893
Abstract: In this paper, an artificial neural network-based genetic algorithm (ANN-GA) model was developed for generating the sizing curve of stand-alone photovoltaic (SAPV) systems. Firstly, a numerical method is used for generating the sizing curves for different loss of load probability (LLP) corresponding to 40 sites located in Algeria. The inputs of ANN-GA are the geographical coordinates (Lat, Lon and Alt) and the LLP while the output is the sizing curve represented by CA=f(CS). Subsequently, the proposed ANN-GA model has been trained by using a set of 36 sites, whereas data for 4 sites which are not included in the training dataset have been used for testing the ANN-GA model. The results obtained are compared and tested with those of the numerical method. In addition, two new regression models have been developed and compared with the conventional regression models. The results show that, the proposed exponential regression model with three coefficients presents more accurate results than the conventional regression models. A new ANN has been used for predicting the sizing coefficients for the best regression model. These coefficients can be used for developing the sizing curve in different locations in Algeria. The results obtained showed that the coefficient of multiple determination (R2) is 0.9998, which can be considered as very promising
ISSN: 09601481
Rights: © 2010 Elsevier Ltd
Type: Article
Appears in Collections:Άρθρα/Articles

Show full item record

Citations 50

checked on Feb 13, 2018

Page view(s) 5

Last Week
Last month
checked on Aug 18, 2019

Google ScholarTM



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