Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method

<p>The random fluctuation and non-uniformity of Photovoltaic (PV) power generation greatly affect the power grids’ stability and operation. This paper addresses the high volatility of PV power by proposing a precise and reliable ensemble learning model for short-term PV power generation foreca...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Mohamed Massaoudi (16888710) (author)
مؤلفون آخرون: Haitham Abu-Rub (16855500) (author), Shady S. Refaat (16864269) (author), Mohamed Trabelsi (16869891) (author), Ines Chihi (16888713) (author), Fakhreddine S. Oueslati (16888716) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513562697793536
author Mohamed Massaoudi (16888710)
author2 Haitham Abu-Rub (16855500)
Shady S. Refaat (16864269)
Mohamed Trabelsi (16869891)
Ines Chihi (16888713)
Fakhreddine S. Oueslati (16888716)
author2_role author
author
author
author
author
author_facet Mohamed Massaoudi (16888710)
Haitham Abu-Rub (16855500)
Shady S. Refaat (16864269)
Mohamed Trabelsi (16869891)
Ines Chihi (16888713)
Fakhreddine S. Oueslati (16888716)
author_role author
dc.creator.none.fl_str_mv Mohamed Massaoudi (16888710)
Haitham Abu-Rub (16855500)
Shady S. Refaat (16864269)
Mohamed Trabelsi (16869891)
Ines Chihi (16888713)
Fakhreddine S. Oueslati (16888716)
dc.date.none.fl_str_mv 2021-11-08T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3125895
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Enhanced_Deep_Belief_Network_Based_on_Ensemble_Learning_and_Tree-Structured_of_Parzen_Estimators_An_Optimal_Photovoltaic_Power_Forecasting_Method/24056460
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Engineering
Electrical engineering
Information and computing sciences
Distributed computing and systems software
Machine learning
Forecasting
Support vector machines
Temperature distribution
Predictive models
Photovoltaic systems
Feature extraction
Wind forecasting
Deep belief network
PV power forecasting
Stacking ensemble
Smart grid
Power generation planning
dc.title.none.fl_str_mv Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>The random fluctuation and non-uniformity of Photovoltaic (PV) power generation greatly affect the power grids’ stability and operation. This paper addresses the high volatility of PV power by proposing a precise and reliable ensemble learning model for short-term PV power generation forecasting. The proposed forecasting tool incorporates a base model and meta-model layers. The first-layer base learner combines extreme learning machines, extremely randomized trees, k-nearest neighbor, and mondrian forest models. The meta-model layer exploits deep belief network to generate the final outputs. The hyper-parameters of the proposed stacking ensemble are carefully tuned using the tree-structured of parzen estimators algorithm to achieve top-notch predictive performance. The proposed model is thoroughly assessed through an empirical study using a real data set from Australia. The simulation results confirm the performance superiority of the proposed model over the existing forecasting models with the lowest average root mean square error and mean absolute percentage error of 3.88kW and 2.30%, respectively.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3125895" target="_blank">https://dx.doi.org/10.1109/access.2021.3125895</a></p>
eu_rights_str_mv openAccess
id Manara2_b64fbbeb9c8f6290013ec597f5d645d7
identifier_str_mv 10.1109/access.2021.3125895
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24056460
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting MethodMohamed Massaoudi (16888710)Haitham Abu-Rub (16855500)Shady S. Refaat (16864269)Mohamed Trabelsi (16869891)Ines Chihi (16888713)Fakhreddine S. Oueslati (16888716)EngineeringElectrical engineeringInformation and computing sciencesDistributed computing and systems softwareMachine learningForecastingSupport vector machinesTemperature distributionPredictive modelsPhotovoltaic systemsFeature extractionWind forecastingDeep belief networkPV power forecastingStacking ensembleSmart gridPower generation planning<p>The random fluctuation and non-uniformity of Photovoltaic (PV) power generation greatly affect the power grids’ stability and operation. This paper addresses the high volatility of PV power by proposing a precise and reliable ensemble learning model for short-term PV power generation forecasting. The proposed forecasting tool incorporates a base model and meta-model layers. The first-layer base learner combines extreme learning machines, extremely randomized trees, k-nearest neighbor, and mondrian forest models. The meta-model layer exploits deep belief network to generate the final outputs. The hyper-parameters of the proposed stacking ensemble are carefully tuned using the tree-structured of parzen estimators algorithm to achieve top-notch predictive performance. The proposed model is thoroughly assessed through an empirical study using a real data set from Australia. The simulation results confirm the performance superiority of the proposed model over the existing forecasting models with the lowest average root mean square error and mean absolute percentage error of 3.88kW and 2.30%, respectively.</p><h2>Other Information</h2><p>Published in: IEEE Access<br>License: <a href="https://creativecommons.org/licenses/by/4.0/legalcode" target="_blank">https://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1109/access.2021.3125895" target="_blank">https://dx.doi.org/10.1109/access.2021.3125895</a></p>2021-11-08T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3125895https://figshare.com/articles/journal_contribution/Enhanced_Deep_Belief_Network_Based_on_Ensemble_Learning_and_Tree-Structured_of_Parzen_Estimators_An_Optimal_Photovoltaic_Power_Forecasting_Method/24056460CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240564602021-11-08T00:00:00Z
spellingShingle Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
Mohamed Massaoudi (16888710)
Engineering
Electrical engineering
Information and computing sciences
Distributed computing and systems software
Machine learning
Forecasting
Support vector machines
Temperature distribution
Predictive models
Photovoltaic systems
Feature extraction
Wind forecasting
Deep belief network
PV power forecasting
Stacking ensemble
Smart grid
Power generation planning
status_str publishedVersion
title Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
title_full Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
title_fullStr Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
title_full_unstemmed Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
title_short Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
title_sort Enhanced Deep Belief Network Based on Ensemble Learning and Tree-Structured of Parzen Estimators: An Optimal Photovoltaic Power Forecasting Method
topic Engineering
Electrical engineering
Information and computing sciences
Distributed computing and systems software
Machine learning
Forecasting
Support vector machines
Temperature distribution
Predictive models
Photovoltaic systems
Feature extraction
Wind forecasting
Deep belief network
PV power forecasting
Stacking ensemble
Smart grid
Power generation planning