An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam

Abstract The advancement of Photovoltaic technology has undergone rapid acceleration in recent years. Nonetheless, the most significant drawback of Photovoltaic is its intermittence, making it an obvious source of power fluctuation. This study proposes a novel scheme for real‐time or intraday PV pow...

Full description

Saved in:
Bibliographic Details
Main Authors: Tuyen Nguyen‐Duc, Huu Vu‐Xuan‐Son, Hieu Do‐Dinh, Nam Nguyen‐Vu‐Nhat, Goro Fujita, Son Tran‐Thanh
Format: Article
Language:English
Published: Wiley 2024-10-01
Series:IET Renewable Power Generation
Subjects:
Online Access:https://doi.org/10.1049/rpg2.13108
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850112656418013184
author Tuyen Nguyen‐Duc
Huu Vu‐Xuan‐Son
Hieu Do‐Dinh
Nam Nguyen‐Vu‐Nhat
Goro Fujita
Son Tran‐Thanh
author_facet Tuyen Nguyen‐Duc
Huu Vu‐Xuan‐Son
Hieu Do‐Dinh
Nam Nguyen‐Vu‐Nhat
Goro Fujita
Son Tran‐Thanh
author_sort Tuyen Nguyen‐Duc
collection DOAJ
description Abstract The advancement of Photovoltaic technology has undergone rapid acceleration in recent years. Nonetheless, the most significant drawback of Photovoltaic is its intermittence, making it an obvious source of power fluctuation. This study proposes a novel scheme for real‐time or intraday PV power forecasting by adopting two predictive models, namely, White‐box and Combination. The White‐box model is implemented employing mathematical calculations and statistics called Exceedance Probability. Meanwhile, the Combination model is an aggregation of several predictive models' outputs including the White‐box model and benchmark ones by dynamically adjusting the weight coefficient of each model based on their forecasting accuracy. The experimental results, which are verified on two PV systems corresponding to two case studies located at Vietnam and Australia, indicate that the two proposed models outperform other referenced models as nMAPE improves approximately 40% and 38% in terms of the first and second case study, respectively. In particular, the White‐box model shows superiority by updating the forecast every 10 min, which can adapt to the fluctuation of weather conditions whereas the Combination one yields acceptable precision, indicating its flexible application.
format Article
id doaj-art-10f6ddcbe88a4d14be611346dd0cd721
institution OA Journals
issn 1752-1416
1752-1424
language English
publishDate 2024-10-01
publisher Wiley
record_format Article
series IET Renewable Power Generation
spelling doaj-art-10f6ddcbe88a4d14be611346dd0cd7212025-08-20T02:37:20ZengWileyIET Renewable Power Generation1752-14161752-14242024-10-0118142589260410.1049/rpg2.13108An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and VietnamTuyen Nguyen‐Duc0Huu Vu‐Xuan‐Son1Hieu Do‐Dinh2Nam Nguyen‐Vu‐Nhat3Goro Fujita4Son Tran‐Thanh5Department of Electrical Engineering Hanoi University of Science and Technology Hanoi VietnamRenewable Energy Management Department National Load Dispatch Centre Hanoi VietnamDepartment of Electrical Engineering Hanoi University of Science and Technology Hanoi VietnamRenewable Energy Management Department National Load Dispatch Centre Hanoi VietnamDepartment of Electrical Engineering Shibaura Institute of Technology Tokyo JapanDepartment of Electrical Engineering Hanoi University of Science and Technology Hanoi VietnamAbstract The advancement of Photovoltaic technology has undergone rapid acceleration in recent years. Nonetheless, the most significant drawback of Photovoltaic is its intermittence, making it an obvious source of power fluctuation. This study proposes a novel scheme for real‐time or intraday PV power forecasting by adopting two predictive models, namely, White‐box and Combination. The White‐box model is implemented employing mathematical calculations and statistics called Exceedance Probability. Meanwhile, the Combination model is an aggregation of several predictive models' outputs including the White‐box model and benchmark ones by dynamically adjusting the weight coefficient of each model based on their forecasting accuracy. The experimental results, which are verified on two PV systems corresponding to two case studies located at Vietnam and Australia, indicate that the two proposed models outperform other referenced models as nMAPE improves approximately 40% and 38% in terms of the first and second case study, respectively. In particular, the White‐box model shows superiority by updating the forecast every 10 min, which can adapt to the fluctuation of weather conditions whereas the Combination one yields acceptable precision, indicating its flexible application.https://doi.org/10.1049/rpg2.13108artificial intelligenceforecasting theorysolar photovoltaic systemsstatistical analysis
spellingShingle Tuyen Nguyen‐Duc
Huu Vu‐Xuan‐Son
Hieu Do‐Dinh
Nam Nguyen‐Vu‐Nhat
Goro Fujita
Son Tran‐Thanh
An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam
IET Renewable Power Generation
artificial intelligence
forecasting theory
solar photovoltaic systems
statistical analysis
title An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam
title_full An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam
title_fullStr An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam
title_full_unstemmed An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam
title_short An adaptive method for real‐time photovoltaic power forecasting utilizing mathematics and statistics: Case studies in Australia and Vietnam
title_sort adaptive method for real time photovoltaic power forecasting utilizing mathematics and statistics case studies in australia and vietnam
topic artificial intelligence
forecasting theory
solar photovoltaic systems
statistical analysis
url https://doi.org/10.1049/rpg2.13108
work_keys_str_mv AT tuyennguyenduc anadaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT huuvuxuanson anadaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT hieudodinh anadaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT namnguyenvunhat anadaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT gorofujita anadaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT sontranthanh anadaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT tuyennguyenduc adaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT huuvuxuanson adaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT hieudodinh adaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT namnguyenvunhat adaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT gorofujita adaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam
AT sontranthanh adaptivemethodforrealtimephotovoltaicpowerforecastingutilizingmathematicsandstatisticscasestudiesinaustraliaandvietnam