Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques

In recent years, as photovoltaic (PV) power generation has rapidly increased on a global scale, there is a growing need for a highly accurate power generation forecasting model that is easy to implement for a wide range of electric utilities. Against this background, this study proposes a PV power f...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Takuji Matsumoto, Yuji Yamada
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	n/a Technology T
Acceso en línea:	https://doaj.org/article/8ba2d519aae34f3ab6e05f64fe8a2fce
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8ba2d519aae34f3ab6e05f64fe8a2fce
record_format	dspace
spelling	oai:doaj.org-article:8ba2d519aae34f3ab6e05f64fe8a2fce2021-11-11T15:56:00ZComprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques10.3390/en142171461996-1073https://doaj.org/article/8ba2d519aae34f3ab6e05f64fe8a2fce2021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7146https://doaj.org/toc/1996-1073In recent years, as photovoltaic (PV) power generation has rapidly increased on a global scale, there is a growing need for a highly accurate power generation forecasting model that is easy to implement for a wide range of electric utilities. Against this background, this study proposes a PV power forecasting model based on the generalized additive model (GAM) and compares its forecasting accuracy with four popular machine learning methods: k-nearest neighbor, artificial neural networks, support vector regression, and random forest. The empirical analysis provides an intuitive interpretation of the multidimensional smooth trends estimated by the GAM as tensor product splines and confirms the validity of the proposed modeling structure. The effectiveness of GAM is particularly evident in trend completion for missing data, where it is able to flexibly express the tangled trend structure inherent in time series data, and thus has an advantage not only in interpretability but also in improving forecast accuracy.Takuji MatsumotoYuji YamadaMDPI AGarticlen/aTechnologyTENEnergies, Vol 14, Iss 7146, p 7146 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	n/a Technology T
spellingShingle	n/a Technology T Takuji Matsumoto Yuji Yamada Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
description	In recent years, as photovoltaic (PV) power generation has rapidly increased on a global scale, there is a growing need for a highly accurate power generation forecasting model that is easy to implement for a wide range of electric utilities. Against this background, this study proposes a PV power forecasting model based on the generalized additive model (GAM) and compares its forecasting accuracy with four popular machine learning methods: k-nearest neighbor, artificial neural networks, support vector regression, and random forest. The empirical analysis provides an intuitive interpretation of the multidimensional smooth trends estimated by the GAM as tensor product splines and confirms the validity of the proposed modeling structure. The effectiveness of GAM is particularly evident in trend completion for missing data, where it is able to flexibly express the tangled trend structure inherent in time series data, and thus has an advantage not only in interpretability but also in improving forecast accuracy.
format	article
author	Takuji Matsumoto Yuji Yamada
author_facet	Takuji Matsumoto Yuji Yamada
author_sort	Takuji Matsumoto
title	Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
title_short	Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
title_full	Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
title_fullStr	Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
title_full_unstemmed	Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques
title_sort	comprehensive and comparative analysis of gam-based pv power forecasting models using multidimensional tensor product splines against machine learning techniques
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8ba2d519aae34f3ab6e05f64fe8a2fce
work_keys_str_mv	AT takujimatsumoto comprehensiveandcomparativeanalysisofgambasedpvpowerforecastingmodelsusingmultidimensionaltensorproductsplinesagainstmachinelearningtechniques AT yujiyamada comprehensiveandcomparativeanalysisofgambasedpvpowerforecastingmodelsusingmultidimensionaltensorproductsplinesagainstmachinelearningtechniques
_version_	1718432741766201344

Comprehensive and Comparative Analysis of GAM-Based PV Power Forecasting Models Using Multidimensional Tensor Product Splines against Machine Learning Techniques

Ejemplares similares