Cover Image

Improved machine learning model selection techniques for solar energy forecasting applications

Grid-Connected Photovoltaic System (GCPV) in Malaysia had become vital due to its usages and contribution to the community. One of the advanced technologies that has been implemented in the solar field is the forecasting of PV power output and comes with a great challenge to produce high accuracy. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Baharin, Kyairul Azmi, Gan, Chin Kim, Zulkifly, Zaim
Format: Article
Language:English
Published: Gazi University 2021
Online Access:http://eprints.utem.edu.my/id/eprint/25645/2/11772-38287-1-PB.PDF
http://eprints.utem.edu.my/id/eprint/25645/
https://www.ijrer.org/ijrer/index.php/ijrer/article/view/11772/pdf
https://doi.org/10.20508/ijrer.v11i1.11772.g8135
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utem.eprints.25645
record_format eprints
spelling my.utem.eprints.256452023-07-03T10:09:51Z http://eprints.utem.edu.my/id/eprint/25645/ Improved machine learning model selection techniques for solar energy forecasting applications Baharin, Kyairul Azmi Gan, Chin Kim Zulkifly, Zaim Grid-Connected Photovoltaic System (GCPV) in Malaysia had become vital due to its usages and contribution to the community. One of the advanced technologies that has been implemented in the solar field is the forecasting of PV power output and comes with a great challenge to produce high accuracy. This paper focuses on developing a ranking system to evaluate the performance of selected machine learning models. In this paper four models are considered, namely Support Vector Machine (SVM), Gaussian Process Regression (GPR), Linear Regression, and Decision Tree. Utilizing high-resolution ground-based measurement of meteorological and PV system power output, evaluation metrics such as Root Mean Squared Error (RMSE), coefficient of determination (R2), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE), and computation time has been recorded to evaluate the performance of machine learning forecasting methods. Results show that the computation time is the primary criterion that differentiates the performance of forecast models. Other statistical metrics show only marginal differences in terms of performance. The ranking system developed can serve as an indicator for solar power output forecasters to determine the best model for their application Gazi University 2021-03 Article PeerReviewed text en http://eprints.utem.edu.my/id/eprint/25645/2/11772-38287-1-PB.PDF Baharin, Kyairul Azmi and Gan, Chin Kim and Zulkifly, Zaim (2021) Improved machine learning model selection techniques for solar energy forecasting applications. International Journal of Renewable Energy Research, 11 (1). pp. 308-319. ISSN 1309-0127 https://www.ijrer.org/ijrer/index.php/ijrer/article/view/11772/pdf https://doi.org/10.20508/ijrer.v11i1.11772.g8135
institution Universiti Teknikal Malaysia Melaka
building UTEM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknikal Malaysia Melaka
content_source UTEM Institutional Repository
url_provider http://eprints.utem.edu.my/
language English
description Grid-Connected Photovoltaic System (GCPV) in Malaysia had become vital due to its usages and contribution to the community. One of the advanced technologies that has been implemented in the solar field is the forecasting of PV power output and comes with a great challenge to produce high accuracy. This paper focuses on developing a ranking system to evaluate the performance of selected machine learning models. In this paper four models are considered, namely Support Vector Machine (SVM), Gaussian Process Regression (GPR), Linear Regression, and Decision Tree. Utilizing high-resolution ground-based measurement of meteorological and PV system power output, evaluation metrics such as Root Mean Squared Error (RMSE), coefficient of determination (R2), Mean Absolute Deviation (MAD), Mean Absolute Error (MAE), and computation time has been recorded to evaluate the performance of machine learning forecasting methods. Results show that the computation time is the primary criterion that differentiates the performance of forecast models. Other statistical metrics show only marginal differences in terms of performance. The ranking system developed can serve as an indicator for solar power output forecasters to determine the best model for their application
format Article
author Baharin, Kyairul Azmi
Gan, Chin Kim
Zulkifly, Zaim
spellingShingle Baharin, Kyairul Azmi
Gan, Chin Kim
Zulkifly, Zaim
Improved machine learning model selection techniques for solar energy forecasting applications
author_facet Baharin, Kyairul Azmi
Gan, Chin Kim
Zulkifly, Zaim
author_sort Baharin, Kyairul Azmi
title Improved machine learning model selection techniques for solar energy forecasting applications
title_short Improved machine learning model selection techniques for solar energy forecasting applications
title_full Improved machine learning model selection techniques for solar energy forecasting applications
title_fullStr Improved machine learning model selection techniques for solar energy forecasting applications
title_full_unstemmed Improved machine learning model selection techniques for solar energy forecasting applications
title_sort improved machine learning model selection techniques for solar energy forecasting applications
publisher Gazi University
publishDate 2021
url http://eprints.utem.edu.my/id/eprint/25645/2/11772-38287-1-PB.PDF
http://eprints.utem.edu.my/id/eprint/25645/
https://www.ijrer.org/ijrer/index.php/ijrer/article/view/11772/pdf
https://doi.org/10.20508/ijrer.v11i1.11772.g8135
_version_ 1770555171822108672
score 13.211869

Similar Items