An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting

<p>This paper proposes an effective Photovoltaic (PV) Power Forecasting (PVPF) technique based on hierarchical learning combining Nonlinear Auto-Regressive Neural Networks with exogenous input (NARXNN) with Long Short-Term Memory (LSTM) model. First, the NARXNN model acquires the data to gener...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Mohamed Massaoudi (16888710) (author)
مؤلفون آخرون: Ines Chihi (16888713) (author), Lilia Sidhom (16896387) (author), Mohamed Trabelsi (16869891) (author), Shady S. Refaat (16864269) (author), Haitham Abu-Rub (16855500) (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_ 1864513562736590848
author Mohamed Massaoudi (16888710)
author2 Ines Chihi (16888713)
Lilia Sidhom (16896387)
Mohamed Trabelsi (16869891)
Shady S. Refaat (16864269)
Haitham Abu-Rub (16855500)
Fakhreddine S. Oueslati (16888716)
author2_role author
author
author
author
author
author
author_facet Mohamed Massaoudi (16888710)
Ines Chihi (16888713)
Lilia Sidhom (16896387)
Mohamed Trabelsi (16869891)
Shady S. Refaat (16864269)
Haitham Abu-Rub (16855500)
Fakhreddine S. Oueslati (16888716)
author_role author
dc.creator.none.fl_str_mv Mohamed Massaoudi (16888710)
Ines Chihi (16888713)
Lilia Sidhom (16896387)
Mohamed Trabelsi (16869891)
Shady S. Refaat (16864269)
Haitham Abu-Rub (16855500)
Fakhreddine S. Oueslati (16888716)
dc.date.none.fl_str_mv 2021-02-26T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3062776
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/An_Effective_Hybrid_NARX-LSTM_Model_for_Point_and_Interval_PV_Power_Forecasting/24049272
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
Data management and data science
Machine learning
Computational modeling
Data models
Long short-term memory (LSTM)
Forecasting
Meteorology
Nonlinear auto-regressive neural networks with exogenous input (NARXNN)
Predictive models
Tabu Search Algorithm (TSA)
Training
Uncertainty
Photovoltaic power forecasting
dc.title.none.fl_str_mv An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>This paper proposes an effective Photovoltaic (PV) Power Forecasting (PVPF) technique based on hierarchical learning combining Nonlinear Auto-Regressive Neural Networks with exogenous input (NARXNN) with Long Short-Term Memory (LSTM) model. First, the NARXNN model acquires the data to generate a residual error vector. Then, the stacked LSTM model, optimized by Tabu search algorithm, uses the residual error correction associated with the original data to produce a point and interval PVPF. The performance of the proposed PVPF technique was investigated using two real datasets with different scales and locations. The comparative analysis of the NARX-LSTM with twelve existing benchmarks confirms its superiority in terms of accuracy measures. In summary, the proposed NARX-LSTM technique has the following major achievements: 1) Improves the prediction performance of the original LSTM and NARXNN models; 2) Evaluates the uncertainties associated with point forecasts with high accuracy; 3) Provides a high generalization capability for PV systems with different scales. Numerical results of the comparison of the proposed NARX-LSTM method with two real-world PV systems in Australia and USA demonstrate its improved prediction accuracy, outperforming the benchmark approaches with an overall normalized Rooted Mean Squared Error (nRMSE) of 1.98% and 1.33% 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.2021.3062776" target="_blank">https://dx.doi.org/10.1109/access.2021.3062776</a></p>
eu_rights_str_mv openAccess
id Manara2_3cf0b780d0702cf9aa0dc1d427773651
identifier_str_mv 10.1109/access.2021.3062776
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24049272
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power ForecastingMohamed Massaoudi (16888710)Ines Chihi (16888713)Lilia Sidhom (16896387)Mohamed Trabelsi (16869891)Shady S. Refaat (16864269)Haitham Abu-Rub (16855500)Fakhreddine S. Oueslati (16888716)EngineeringElectrical engineeringInformation and computing sciencesData management and data scienceMachine learningComputational modelingData modelsLong short-term memory (LSTM)ForecastingMeteorologyNonlinear auto-regressive neural networks with exogenous input (NARXNN)Predictive modelsTabu Search Algorithm (TSA)TrainingUncertaintyPhotovoltaic power forecasting<p>This paper proposes an effective Photovoltaic (PV) Power Forecasting (PVPF) technique based on hierarchical learning combining Nonlinear Auto-Regressive Neural Networks with exogenous input (NARXNN) with Long Short-Term Memory (LSTM) model. First, the NARXNN model acquires the data to generate a residual error vector. Then, the stacked LSTM model, optimized by Tabu search algorithm, uses the residual error correction associated with the original data to produce a point and interval PVPF. The performance of the proposed PVPF technique was investigated using two real datasets with different scales and locations. The comparative analysis of the NARX-LSTM with twelve existing benchmarks confirms its superiority in terms of accuracy measures. In summary, the proposed NARX-LSTM technique has the following major achievements: 1) Improves the prediction performance of the original LSTM and NARXNN models; 2) Evaluates the uncertainties associated with point forecasts with high accuracy; 3) Provides a high generalization capability for PV systems with different scales. Numerical results of the comparison of the proposed NARX-LSTM method with two real-world PV systems in Australia and USA demonstrate its improved prediction accuracy, outperforming the benchmark approaches with an overall normalized Rooted Mean Squared Error (nRMSE) of 1.98% and 1.33% 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.2021.3062776" target="_blank">https://dx.doi.org/10.1109/access.2021.3062776</a></p>2021-02-26T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3062776https://figshare.com/articles/journal_contribution/An_Effective_Hybrid_NARX-LSTM_Model_for_Point_and_Interval_PV_Power_Forecasting/24049272CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240492722021-02-26T00:00:00Z
spellingShingle An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
Mohamed Massaoudi (16888710)
Engineering
Electrical engineering
Information and computing sciences
Data management and data science
Machine learning
Computational modeling
Data models
Long short-term memory (LSTM)
Forecasting
Meteorology
Nonlinear auto-regressive neural networks with exogenous input (NARXNN)
Predictive models
Tabu Search Algorithm (TSA)
Training
Uncertainty
Photovoltaic power forecasting
status_str publishedVersion
title An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
title_full An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
title_fullStr An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
title_full_unstemmed An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
title_short An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
title_sort An Effective Hybrid NARX-LSTM Model for Point and Interval PV Power Forecasting
topic Engineering
Electrical engineering
Information and computing sciences
Data management and data science
Machine learning
Computational modeling
Data models
Long short-term memory (LSTM)
Forecasting
Meteorology
Nonlinear auto-regressive neural networks with exogenous input (NARXNN)
Predictive models
Tabu Search Algorithm (TSA)
Training
Uncertainty
Photovoltaic power forecasting