Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules

This paper presents a study on neural network-based modeling techniques and sensor data to estimate the power output of photovoltaic systems under soiling conditions. Predicting maximum power output under soiling conditions is considered an important and difficult problem and a variety of models usi...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Shapsough, Salsabeel Yousef (author)
مؤلفون آخرون: Dhaouadi, Rached (author), Zualkernan, Imran (author)
التنسيق: article
منشور في: 2019
الموضوعات:
الوصول للمادة أونلاين:http://hdl.handle.net/11073/16621
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513439255232512
author Shapsough, Salsabeel Yousef
author2 Dhaouadi, Rached
Zualkernan, Imran
author2_role author
author
author_facet Shapsough, Salsabeel Yousef
Dhaouadi, Rached
Zualkernan, Imran
author_role author
dc.creator.none.fl_str_mv Shapsough, Salsabeel Yousef
Dhaouadi, Rached
Zualkernan, Imran
dc.date.none.fl_str_mv 2019
2020-02-23T08:42:31Z
2020-02-23T08:42:31Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Salsabeel Shapsough, Rached Dhaouadi, Imran Zualkernan, Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules, Procedia Computer Science, Volume 155, 2019, Pages 463-470, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2019.08.065.
1877-0509
http://hdl.handle.net/11073/16621
10.1016/j.procs.2019.08.065
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Elsevier
dc.relation.none.fl_str_mv https://doi.org/10.1016/j.procs.2019.08.065
dc.subject.none.fl_str_mv PV
Neural Networks
Soiling
dc.title.none.fl_str_mv Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
dc.type.none.fl_str_mv Peer-Reviewed
Published version
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This paper presents a study on neural network-based modeling techniques and sensor data to estimate the power output of photovoltaic systems under soiling conditions. Predicting maximum power output under soiling conditions is considered an important and difficult problem and a variety of models using a host of factors including temperature and weather profiles have been proposed. This study used linear regression models and artificial neural networks and used only solar irradiation and ambient temperature, as well and the maximum power point (MPP) characteristic variables of photovoltaic (PV) modules obtained from online current-voltage (IV) tracers in the site of a PV installation. The two models were trained and validated using actual monitoring data of two 100-Watt PV modules installed in the UAE. One reference panel was cleaned on a weekly basis and the second panel was left to accumulate dust over the entire period between July 1, 2018 and 17 September, 2018. The results show that it is possible to predict maximum power output of soiled PV modules at about 97% accuracy. The proposed models perform at an accuracy comparable to more complex models in literature.
format article
id aus_5c4d0b1dd2acc80f8dd39095e07b23cc
identifier_str_mv Salsabeel Shapsough, Rached Dhaouadi, Imran Zualkernan, Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules, Procedia Computer Science, Volume 155, 2019, Pages 463-470, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2019.08.065.
1877-0509
10.1016/j.procs.2019.08.065
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/16621
publishDate 2019
publisher.none.fl_str_mv Elsevier
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV ModulesShapsough, Salsabeel YousefDhaouadi, RachedZualkernan, ImranPVNeural NetworksSoilingThis paper presents a study on neural network-based modeling techniques and sensor data to estimate the power output of photovoltaic systems under soiling conditions. Predicting maximum power output under soiling conditions is considered an important and difficult problem and a variety of models using a host of factors including temperature and weather profiles have been proposed. This study used linear regression models and artificial neural networks and used only solar irradiation and ambient temperature, as well and the maximum power point (MPP) characteristic variables of photovoltaic (PV) modules obtained from online current-voltage (IV) tracers in the site of a PV installation. The two models were trained and validated using actual monitoring data of two 100-Watt PV modules installed in the UAE. One reference panel was cleaned on a weekly basis and the second panel was left to accumulate dust over the entire period between July 1, 2018 and 17 September, 2018. The results show that it is possible to predict maximum power output of soiled PV modules at about 97% accuracy. The proposed models perform at an accuracy comparable to more complex models in literature.Elsevier2020-02-23T08:42:31Z2020-02-23T08:42:31Z2019Peer-ReviewedPublished versioninfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfSalsabeel Shapsough, Rached Dhaouadi, Imran Zualkernan, Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules, Procedia Computer Science, Volume 155, 2019, Pages 463-470, ISSN 1877-0509, https://doi.org/10.1016/j.procs.2019.08.065.1877-0509http://hdl.handle.net/11073/1662110.1016/j.procs.2019.08.065en_UShttps://doi.org/10.1016/j.procs.2019.08.065oai:repository.aus.edu:11073/166212024-08-22T12:15:12Z
spellingShingle Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
Shapsough, Salsabeel Yousef
PV
Neural Networks
Soiling
status_str publishedVersion
title Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
title_full Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
title_fullStr Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
title_full_unstemmed Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
title_short Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
title_sort Using Linear Regression and Back Propagation Neural Networks to Predict Performance of Soiled PV Modules
topic PV
Neural Networks
Soiling
url http://hdl.handle.net/11073/16621