Please use this identifier to cite or link to this item:
Title: Review of techniques based on artificial neural networks for the electrical characterization of concentrator photovoltaic technology
Authors: Almonacid, Florencia 
Fernandez, Eduardo F. 
Mellit, Adel 
Kalogirou, Soteris A. 
Keywords: Artificial neural networks;Concentrator photovoltaics;Electrical characterization
Category: Mechanical Engineering
Field: Engineering and Technology
Issue Date: 1-Aug-2017
Publisher: Elsevier Ltd
Source: Renewable and Sustainable Energy Reviews, 2017, Volume 75, Pages 938-953
Abstract: Concentrator photovoltaics (CPV) is considered to be one of the most promising renewable energy components that could lead to a reduction on the dependence on fossil fuels. The aim of CPV technology is to lower the cost of the system by reducing the semiconductor material, and replacing it by cheap optical devices that concentrate the light received from the sun on a small-size solar cell. The electrical characterization of devices based on this technology however, is inherently different and more complex than that of the traditional PV devices. Due to the advantages offered by the Artificial Neuron Networks (ANNs) to solve complex and non-linear problems, and the great level of complexity of electrical modelling of CPV devices, in recent years, several authors have applied a variety of ANNs to solve issues related to CPV technology. In this paper, a review of the ANNs developed to address various topics related with both, low and high concentrator photovoltaics, is presented. Moreover, a review of the ANN-based models to predict the main environmental parameters that affect the performance of CPV systems operating outdoors is also provided. Published papers presented show the potential of the ANNs as a powerful tool for modelling the CPV technology.
ISSN: 13640321
Rights: © 2016 Elsevier Ltd
Type: Article
Appears in Collections:Άρθρα/Articles

Show full item record

Page view(s) 20

Last Week
Last month
checked on Feb 21, 2019

Google ScholarTM


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