Application of genetic algorithm and neural network for sizing of hybrid photovoltaic wind power generation (HPVWPG) systems
by Adel Mellit
International Journal of Renewable Energy Technology (IJRET), Vol. 1, No. 2, 2009

Abstract: In this paper, a methodology for sizing of hybrid photovoltaic-wind power generation (HPVWPG) system is described. The purpose of this methodology is to predict the PV-generator area, the capacity of the battery and the capacity of the wind generator in isolated (remote) areas, where the meteorological data (solar irradiation, air temperature, wind speed, etc) are not always available. For this purpose, a database of meteorological data (solar irradiation, ambient temperature and wind speed) for 40 sites located in Algeria has been studied. Firstly, based on the objective function minimisation using genetic algorithms (GA), the different optimal components (PV-generator area, battery capacity and wind generator capacity) for 40 sites were estimated. Subsequently, based on the optimal estimated components, an artificial neural network (ANN) is used for predicting the optimal components of the hybrid system in isolated areas from only the geographical coordinates of the sites. The results showed clearly the potential of the proposed methodology for predicting the optimal sizing components of HPVWPG systems in isolated area.

Online publication date: Wed, 26-Aug-2009

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Renewable Energy Technology (IJRET):
Login with your Inderscience username and password:

Username:        Password:          Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com