A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System

<p>For the utility to plan the resources accurately and balance the electricity supply and demand, accurate and timely forecasting is required. The proliferation of smart meters in the grids has resulted in an explosion of energy datasets. Processing such data is challenging and usually takes...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ameema Zainab (16864263) (author)
مؤلفون آخرون: Dabeeruddin Syed (16864260) (author), Ali Ghrayeb (16864266) (author), Haitham Abu-Rub (16855500) (author), Shady S. Refaat (16864269) (author), Mahdi Houchati (16891560) (author), Othmane Bouhali (8252544) (author), Santiago Banales Lopez (16896411) (author)
منشور في: 2021
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513562715619328
author Ameema Zainab (16864263)
author2 Dabeeruddin Syed (16864260)
Ali Ghrayeb (16864266)
Haitham Abu-Rub (16855500)
Shady S. Refaat (16864269)
Mahdi Houchati (16891560)
Othmane Bouhali (8252544)
Santiago Banales Lopez (16896411)
author2_role author
author
author
author
author
author
author
author_facet Ameema Zainab (16864263)
Dabeeruddin Syed (16864260)
Ali Ghrayeb (16864266)
Haitham Abu-Rub (16855500)
Shady S. Refaat (16864269)
Mahdi Houchati (16891560)
Othmane Bouhali (8252544)
Santiago Banales Lopez (16896411)
author_role author
dc.creator.none.fl_str_mv Ameema Zainab (16864263)
Dabeeruddin Syed (16864260)
Ali Ghrayeb (16864266)
Haitham Abu-Rub (16855500)
Shady S. Refaat (16864269)
Mahdi Houchati (16891560)
Othmane Bouhali (8252544)
Santiago Banales Lopez (16896411)
dc.date.none.fl_str_mv 2021-02-16T00:00:00Z
dc.identifier.none.fl_str_mv 10.1109/access.2021.3059730
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/A_Multiprocessing-Based_Sensitivity_Analysis_of_Machine_Learning_Algorithms_for_Load_Forecasting_of_Electric_Power_Distribution_System/24049293
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
Load modeling
Load forecasting
Predictive models
Forecasting
Program processors
Computational modeling
Parallel processing
Big data applications
Machine learning algorithms
Load forecast
Smart grids
dc.title.none.fl_str_mv A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>For the utility to plan the resources accurately and balance the electricity supply and demand, accurate and timely forecasting is required. The proliferation of smart meters in the grids has resulted in an explosion of energy datasets. Processing such data is challenging and usually takes a longer time than the requirement of a short-term load forecast. The paper addresses this concern by utilizing parallel computing capabilities to minimize the execution time while maintaining highly accurate load forecasting models. In this paper, a thousand smart meter energy datasets are analyzed to perform day ahead, hourly short-term load forecast (STLF). The paper utilizes multi-processing to enhance the overall execution time of the forecasting models by submitting simultaneous jobs to all the processors available. The paper demonstrates the efficacy of the proposed approach through the choice of machine learning (ML) models, execution time, and scalability. The proposed approach is validated on real energy consumption data collected at distribution transformers' level in Spanish Electrical Grid. Decision trees have outperformed the other models accomplishing a tradeoff between model accuracy and execution time. The methodology takes only 4 minutes to train 1,000 transformers for an hourly day-ahead forecast of (~24 million records) utilizing 32 processors.</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.2021.3059730" target="_blank">https://dx.doi.org/10.1109/access.2021.3059730</a></p>
eu_rights_str_mv openAccess
id Manara2_715ca822021603e30bd7c810729d4184
identifier_str_mv 10.1109/access.2021.3059730
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/24049293
publishDate 2021
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution SystemAmeema Zainab (16864263)Dabeeruddin Syed (16864260)Ali Ghrayeb (16864266)Haitham Abu-Rub (16855500)Shady S. Refaat (16864269)Mahdi Houchati (16891560)Othmane Bouhali (8252544)Santiago Banales Lopez (16896411)EngineeringElectrical engineeringInformation and computing sciencesDistributed computing and systems softwareMachine learningLoad modelingLoad forecastingPredictive modelsForecastingProgram processorsComputational modelingParallel processingBig data applicationsMachine learning algorithmsLoad forecastSmart grids<p>For the utility to plan the resources accurately and balance the electricity supply and demand, accurate and timely forecasting is required. The proliferation of smart meters in the grids has resulted in an explosion of energy datasets. Processing such data is challenging and usually takes a longer time than the requirement of a short-term load forecast. The paper addresses this concern by utilizing parallel computing capabilities to minimize the execution time while maintaining highly accurate load forecasting models. In this paper, a thousand smart meter energy datasets are analyzed to perform day ahead, hourly short-term load forecast (STLF). The paper utilizes multi-processing to enhance the overall execution time of the forecasting models by submitting simultaneous jobs to all the processors available. The paper demonstrates the efficacy of the proposed approach through the choice of machine learning (ML) models, execution time, and scalability. The proposed approach is validated on real energy consumption data collected at distribution transformers' level in Spanish Electrical Grid. Decision trees have outperformed the other models accomplishing a tradeoff between model accuracy and execution time. The methodology takes only 4 minutes to train 1,000 transformers for an hourly day-ahead forecast of (~24 million records) utilizing 32 processors.</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.2021.3059730" target="_blank">https://dx.doi.org/10.1109/access.2021.3059730</a></p>2021-02-16T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1109/access.2021.3059730https://figshare.com/articles/journal_contribution/A_Multiprocessing-Based_Sensitivity_Analysis_of_Machine_Learning_Algorithms_for_Load_Forecasting_of_Electric_Power_Distribution_System/24049293CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/240492932021-02-16T00:00:00Z
spellingShingle A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
Ameema Zainab (16864263)
Engineering
Electrical engineering
Information and computing sciences
Distributed computing and systems software
Machine learning
Load modeling
Load forecasting
Predictive models
Forecasting
Program processors
Computational modeling
Parallel processing
Big data applications
Machine learning algorithms
Load forecast
Smart grids
status_str publishedVersion
title A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
title_full A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
title_fullStr A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
title_full_unstemmed A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
title_short A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
title_sort A Multiprocessing-Based Sensitivity Analysis of Machine Learning Algorithms for Load Forecasting of Electric Power Distribution System
topic Engineering
Electrical engineering
Information and computing sciences
Distributed computing and systems software
Machine learning
Load modeling
Load forecasting
Predictive models
Forecasting
Program processors
Computational modeling
Parallel processing
Big data applications
Machine learning algorithms
Load forecast
Smart grids