Staff View: A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction

A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction

Nowadays, with the growing interest in green energy, further improvements in photovoltaic (PV) power systems are needed. In this regard, the main aim is to find an optimal method to predict the output power of PV systems to maintain a sustainable operation. Hence, this work proposes a hybrid Machine...

Full description

Saved in:

Bibliographic Details
Main Authors:	Mubarak, Hamza, Hammoudeh, Ahmad, Ahmad, Shameem, Abdellatif, Abdallah, Mekhilef, Saad, Mokhlis, Hazlie, Dupont, Stephane
Format:	Article
Published:	Elsevier 2023
Subjects:	TK Electrical engineering. Electronics Nuclear engineering
Online Access:	http://eprints.um.edu.my/38874/
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my.um.eprints.38874
record_format	eprints
spelling	my.um.eprints.388742023-11-29T02:25:52Z http://eprints.um.edu.my/38874/ A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction Mubarak, Hamza Hammoudeh, Ahmad Ahmad, Shameem Abdellatif, Abdallah Mekhilef, Saad Mokhlis, Hazlie Dupont, Stephane TK Electrical engineering. Electronics Nuclear engineering Nowadays, with the growing interest in green energy, further improvements in photovoltaic (PV) power systems are needed. In this regard, the main aim is to find an optimal method to predict the output power of PV systems to maintain a sustainable operation. Hence, this work proposes a hybrid Machine Learning (ML) method LASSO-RFR for an hourly PV power output prediction. The model consists of Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest Regressor (RFR), where the former model makes a prediction and the latter fine tune it by the addition or subtraction of a relatively small value. The proposed model outperformed other models when tested on real data recorded from 2016 to 2019 for three Malaysian PV systems, namely Thin-Film (TF), Monocrystalline (MC), and Polycrystalline (PC). LASSO-RFR attained the lowest root mean square error (RMSE) of 23.7, 18.2, and 20.8 Wh/m2 for the TF, MC, and PC, respectively. This work also highlights the importance of explicit time encoding in improving PV power prediction. Although it is used to be ignored in the literature when developing ML models, the time feature is the second most influencing factor of PV power prediction after solar irradiance, as shown by the SHAP analysis (shapely additive explanation). For the study implications, the developed prediction model can assist the industry in predicting 1 h ahead of PV power output, demand-side management, and building operations and maintenance. Elsevier 2023-01 Article PeerReviewed Mubarak, Hamza and Hammoudeh, Ahmad and Ahmad, Shameem and Abdellatif, Abdallah and Mekhilef, Saad and Mokhlis, Hazlie and Dupont, Stephane (2023) A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction. Journal of Cleaner Production, 382. ISSN 0959-6526, DOI https://doi.org/10.1016/j.jclepro.2022.134979 <https://doi.org/10.1016/j.jclepro.2022.134979>. 10.1016/j.jclepro.2022.134979
institution	Universiti Malaya
building	UM Library
collection	Institutional Repository
continent	Asia
country	Malaysia
content_provider	Universiti Malaya
content_source	UM Research Repository
url_provider	http://eprints.um.edu.my/
topic	TK Electrical engineering. Electronics Nuclear engineering
spellingShingle	TK Electrical engineering. Electronics Nuclear engineering Mubarak, Hamza Hammoudeh, Ahmad Ahmad, Shameem Abdellatif, Abdallah Mekhilef, Saad Mokhlis, Hazlie Dupont, Stephane A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction
description	Nowadays, with the growing interest in green energy, further improvements in photovoltaic (PV) power systems are needed. In this regard, the main aim is to find an optimal method to predict the output power of PV systems to maintain a sustainable operation. Hence, this work proposes a hybrid Machine Learning (ML) method LASSO-RFR for an hourly PV power output prediction. The model consists of Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest Regressor (RFR), where the former model makes a prediction and the latter fine tune it by the addition or subtraction of a relatively small value. The proposed model outperformed other models when tested on real data recorded from 2016 to 2019 for three Malaysian PV systems, namely Thin-Film (TF), Monocrystalline (MC), and Polycrystalline (PC). LASSO-RFR attained the lowest root mean square error (RMSE) of 23.7, 18.2, and 20.8 Wh/m2 for the TF, MC, and PC, respectively. This work also highlights the importance of explicit time encoding in improving PV power prediction. Although it is used to be ignored in the literature when developing ML models, the time feature is the second most influencing factor of PV power prediction after solar irradiance, as shown by the SHAP analysis (shapely additive explanation). For the study implications, the developed prediction model can assist the industry in predicting 1 h ahead of PV power output, demand-side management, and building operations and maintenance.
format	Article
author	Mubarak, Hamza Hammoudeh, Ahmad Ahmad, Shameem Abdellatif, Abdallah Mekhilef, Saad Mokhlis, Hazlie Dupont, Stephane
author_facet	Mubarak, Hamza Hammoudeh, Ahmad Ahmad, Shameem Abdellatif, Abdallah Mekhilef, Saad Mokhlis, Hazlie Dupont, Stephane
author_sort	Mubarak, Hamza
title	A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction
title_short	A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction
title_full	A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction
title_fullStr	A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction
title_full_unstemmed	A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction
title_sort	hybrid machine learning method with explicit time encoding for improved malaysian photovoltaic power prediction
publisher	Elsevier
publishDate	2023
url	http://eprints.um.edu.my/38874/
_version_	1783876674493874176
score	13.211869

A hybrid machine learning method with explicit time encoding for improved Malaysian photovoltaic power prediction

Similar Items