Please use this identifier to cite or link to this item: https://ktisis.cut.ac.cy/handle/10488/7501
DC FieldValueLanguage
dc.contributor.authorMellit, Adelen
dc.contributor.authorDrif, Mahmouden
dc.contributor.authorKalogirou, Soteris A.-
dc.contributor.authorMellit, Adel-
dc.contributor.authorDrif, Mahmoud-
dc.contributor.otherΚαλογήρου, Σωτήρης Α.-
dc.date.accessioned2013-03-04T10:53:59Zen
dc.date.accessioned2013-05-17T10:30:33Z-
dc.date.accessioned2015-12-09T09:40:48Z-
dc.date.available2013-03-04T10:53:59Zen
dc.date.available2013-05-17T10:30:33Z-
dc.date.available2015-12-09T09:40:48Z-
dc.date.issued2010en
dc.identifier.citationRenewable energy, 2010, Volume 35, Issue 12, Pages 2881–2893en
dc.identifier.issn09601481en
dc.identifier.urihttp://ktisis.cut.ac.cy/handle/10488/7501en
dc.description.abstractIn 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 promisingen
dc.formatpdfen
dc.language.isoenen
dc.publisherElsevieren
dc.rights© 2010 Elsevier Ltden
dc.subjectNeural networks (Computer science)en
dc.subjectGenetic algorithmsen
dc.subjectNumber theoryen
dc.titleApplication of neural networks and genetic algorithms for sizing of photovoltaic systemsen
dc.typeArticleen
dc.collaborationCentre de développement des énergies renouvelables-
dc.collaborationCyprus University of Technology-
dc.collaborationJijel University-
dc.subject.categoryEnvironmental Engineering-
dc.journalsSubscription Journal-
dc.reviewpeer reviewed-
dc.countryAlgeria-
dc.countryCyprus-
dc.subject.fieldEngineering and Technology-
dc.identifier.doihttp://dx.doi.org/10.1016/j.renene.2010.04.017en
dc.dept.handle123456789/141en
item.grantfulltextnone-
item.fulltextNo Fulltext-
item.languageiso639-1other-
crisitem.author.deptDepartment of Mechanical Engineering and Materials Science and Engineering-
crisitem.author.facultyFaculty of Engineering and Technology-
crisitem.author.orcid0000-0002-3654-1437-
crisitem.author.parentorgFaculty of Engineering and Technology-
Appears in Collections:Άρθρα/Articles
Show simple item record

SCOPUSTM   
Citations 50

35
checked on Feb 13, 2018

Page view(s) 5

131
Last Week
6
Last month
9
checked on Sep 22, 2019

Google ScholarTM

Check

Altmetric


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