Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia
Autor(a) principal: | |
---|---|
Data de Publicação: | 2022 |
Outros Autores: | , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da UNESP |
Texto Completo: | http://dx.doi.org/10.1016/j.egyr.2021.11.123 http://hdl.handle.net/11449/222986 |
Resumo: | Understanding patterns and energy-related data in photovoltaic systems is one of the key tasks in energy generation and distribution. In fact, the use of data-driven tools and predictive learning models can support the government, power regulatory agencies, and the energy industry in improving their decision-making and operational activities. Bering this in mind, this paper presents a case study of data-driven analysis and machine learning to forecast the energy charge in the distributed photovoltaic power grid of Queensland, in Australia. Our analysis relies on a freely, open energy tracking platform and the design of three Machine Learning approaches built on the basis of Random Forest, Support Vector Machines, and Gradient Boosting methods. Experimental results with real data showed that the trained models allow for very consistent predictions while reaching a high forecasting accuracy (around 95%–93% in Generated - Exported prediction, respectively). Moreover, it was found that the Gradient Boosting-based model ensures robust behavior and low prediction errors, as endorsed by quality validation metrics. Another technical aspect observed is that the variables artificially created to boost the models substantially improve the post-analysis and overall accuracy of the results. |
id |
UNSP_2a3608a3b3c536a0221afd10213e7587 |
---|---|
oai_identifier_str |
oai:repositorio.unesp.br:11449/222986 |
network_acronym_str |
UNSP |
network_name_str |
Repositório Institucional da UNESP |
repository_id_str |
2946 |
spelling |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, AustraliaData-driven modelsDistributed energyMachine learningPhotovoltaicsUnderstanding patterns and energy-related data in photovoltaic systems is one of the key tasks in energy generation and distribution. In fact, the use of data-driven tools and predictive learning models can support the government, power regulatory agencies, and the energy industry in improving their decision-making and operational activities. Bering this in mind, this paper presents a case study of data-driven analysis and machine learning to forecast the energy charge in the distributed photovoltaic power grid of Queensland, in Australia. Our analysis relies on a freely, open energy tracking platform and the design of three Machine Learning approaches built on the basis of Random Forest, Support Vector Machines, and Gradient Boosting methods. Experimental results with real data showed that the trained models allow for very consistent predictions while reaching a high forecasting accuracy (around 95%–93% in Generated - Exported prediction, respectively). Moreover, it was found that the Gradient Boosting-based model ensures robust behavior and low prediction errors, as endorsed by quality validation metrics. Another technical aspect observed is that the variables artificially created to boost the models substantially improve the post-analysis and overall accuracy of the results.Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)Department of Energy Engineering São Paulo State University (UNESP)Department of Energy Engineering São Paulo State University (UNESP)FAPESP: 2013/07375-0FAPESP: 2019/18857-1Universidade Estadual Paulista (UNESP)Ramos, Lucas [UNESP]Colnago, Marilaine [UNESP]Casaca, Wallace [UNESP]2022-04-28T19:47:53Z2022-04-28T19:47:53Z2022-04-01info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/article745-751http://dx.doi.org/10.1016/j.egyr.2021.11.123Energy Reports, v. 8, p. 745-751.2352-4847http://hdl.handle.net/11449/22298610.1016/j.egyr.2021.11.1232-s2.0-85120634018Scopusreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESPengEnergy Reportsinfo:eu-repo/semantics/openAccess2022-04-28T19:47:53Zoai:repositorio.unesp.br:11449/222986Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestopendoar:29462024-08-06T00:01:42.845544Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false |
dc.title.none.fl_str_mv |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
title |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
spellingShingle |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia Ramos, Lucas [UNESP] Data-driven models Distributed energy Machine learning Photovoltaics |
title_short |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
title_full |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
title_fullStr |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
title_full_unstemmed |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
title_sort |
Data-driven analysis and machine learning for energy prediction in distributed photovoltaic generation plants: A case study in Queensland, Australia |
author |
Ramos, Lucas [UNESP] |
author_facet |
Ramos, Lucas [UNESP] Colnago, Marilaine [UNESP] Casaca, Wallace [UNESP] |
author_role |
author |
author2 |
Colnago, Marilaine [UNESP] Casaca, Wallace [UNESP] |
author2_role |
author author |
dc.contributor.none.fl_str_mv |
Universidade Estadual Paulista (UNESP) |
dc.contributor.author.fl_str_mv |
Ramos, Lucas [UNESP] Colnago, Marilaine [UNESP] Casaca, Wallace [UNESP] |
dc.subject.por.fl_str_mv |
Data-driven models Distributed energy Machine learning Photovoltaics |
topic |
Data-driven models Distributed energy Machine learning Photovoltaics |
description |
Understanding patterns and energy-related data in photovoltaic systems is one of the key tasks in energy generation and distribution. In fact, the use of data-driven tools and predictive learning models can support the government, power regulatory agencies, and the energy industry in improving their decision-making and operational activities. Bering this in mind, this paper presents a case study of data-driven analysis and machine learning to forecast the energy charge in the distributed photovoltaic power grid of Queensland, in Australia. Our analysis relies on a freely, open energy tracking platform and the design of three Machine Learning approaches built on the basis of Random Forest, Support Vector Machines, and Gradient Boosting methods. Experimental results with real data showed that the trained models allow for very consistent predictions while reaching a high forecasting accuracy (around 95%–93% in Generated - Exported prediction, respectively). Moreover, it was found that the Gradient Boosting-based model ensures robust behavior and low prediction errors, as endorsed by quality validation metrics. Another technical aspect observed is that the variables artificially created to boost the models substantially improve the post-analysis and overall accuracy of the results. |
publishDate |
2022 |
dc.date.none.fl_str_mv |
2022-04-28T19:47:53Z 2022-04-28T19:47:53Z 2022-04-01 |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
http://dx.doi.org/10.1016/j.egyr.2021.11.123 Energy Reports, v. 8, p. 745-751. 2352-4847 http://hdl.handle.net/11449/222986 10.1016/j.egyr.2021.11.123 2-s2.0-85120634018 |
url |
http://dx.doi.org/10.1016/j.egyr.2021.11.123 http://hdl.handle.net/11449/222986 |
identifier_str_mv |
Energy Reports, v. 8, p. 745-751. 2352-4847 10.1016/j.egyr.2021.11.123 2-s2.0-85120634018 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.relation.none.fl_str_mv |
Energy Reports |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
745-751 |
dc.source.none.fl_str_mv |
Scopus reponame:Repositório Institucional da UNESP instname:Universidade Estadual Paulista (UNESP) instacron:UNESP |
instname_str |
Universidade Estadual Paulista (UNESP) |
instacron_str |
UNESP |
institution |
UNESP |
reponame_str |
Repositório Institucional da UNESP |
collection |
Repositório Institucional da UNESP |
repository.name.fl_str_mv |
Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP) |
repository.mail.fl_str_mv |
|
_version_ |
1808129573677694976 |