Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms

This work aims to model the combined cycle power plant (CCPP) using different algorithms. The algorithms used are Ridge, Linear regressor (LR), and upport vector regressor (SVR). The CCPP energy output data collected as a factor of thermal input variables, mainly exhaust vacuum, ambient temperature,...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Asif Afzal, Saad Alshahrani, Abdulrahman Alrobaian, Abdulrajak Buradi, Sher Afghan Khan
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	CCPP modeling ridge SVR linear regression R-squared Technology T
Acceso en línea:	https://doaj.org/article/8a495f4163774560aab862a28fd4c494
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:8a495f4163774560aab862a28fd4c494
record_format	dspace
spelling	oai:doaj.org-article:8a495f4163774560aab862a28fd4c4942021-11-11T16:00:45ZPower Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms10.3390/en142172541996-1073https://doaj.org/article/8a495f4163774560aab862a28fd4c4942021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7254https://doaj.org/toc/1996-1073This work aims to model the combined cycle power plant (CCPP) using different algorithms. The algorithms used are Ridge, Linear regressor (LR), and upport vector regressor (SVR). The CCPP energy output data collected as a factor of thermal input variables, mainly exhaust vacuum, ambient temperature, relative humidity, and ambient pressure. Initially, the Ridge algorithm-based modeling is performed in detail, and then SVR-based LR, named as SVR (LR), SVR-based radial basis function—SVR (RBF), and SVR-based polynomial regression—SVR (Poly.) algorithms, are applied. Mean absolute error (MAE), R-squared (R<sup>2</sup>), median absolute error (MeAE), mean absolute percentage error (MAPE), and mean Poisson deviance (MPD) are assessed after their training and testing of each algorithm. From the modeling of energy output data, it is seen that SVR (RBF) is the most suitable in providing very close predictions compared to other algorithms. SVR (RBF) training R<sup>2</sup> obtained is 0.98 while all others were 0.9–0.92. The testing predictions made by SVR (RBF), Ridge, and RidgeCV are nearly the same, i.e., R<sup>2</sup> is 0.92. It is concluded that these algorithms are suitable for predicting sensitive output energy data of a CCPP depending on thermal input variables.Asif AfzalSaad AlshahraniAbdulrahman AlrobaianAbdulrajak BuradiSher Afghan KhanMDPI AGarticleCCPPmodelingridgeSVRlinear regressionR-squaredTechnologyTENEnergies, Vol 14, Iss 7254, p 7254 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	CCPP modeling ridge SVR linear regression R-squared Technology T
spellingShingle	CCPP modeling ridge SVR linear regression R-squared Technology T Asif Afzal Saad Alshahrani Abdulrahman Alrobaian Abdulrajak Buradi Sher Afghan Khan Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms
description	This work aims to model the combined cycle power plant (CCPP) using different algorithms. The algorithms used are Ridge, Linear regressor (LR), and upport vector regressor (SVR). The CCPP energy output data collected as a factor of thermal input variables, mainly exhaust vacuum, ambient temperature, relative humidity, and ambient pressure. Initially, the Ridge algorithm-based modeling is performed in detail, and then SVR-based LR, named as SVR (LR), SVR-based radial basis function—SVR (RBF), and SVR-based polynomial regression—SVR (Poly.) algorithms, are applied. Mean absolute error (MAE), R-squared (R<sup>2</sup>), median absolute error (MeAE), mean absolute percentage error (MAPE), and mean Poisson deviance (MPD) are assessed after their training and testing of each algorithm. From the modeling of energy output data, it is seen that SVR (RBF) is the most suitable in providing very close predictions compared to other algorithms. SVR (RBF) training R<sup>2</sup> obtained is 0.98 while all others were 0.9–0.92. The testing predictions made by SVR (RBF), Ridge, and RidgeCV are nearly the same, i.e., R<sup>2</sup> is 0.92. It is concluded that these algorithms are suitable for predicting sensitive output energy data of a CCPP depending on thermal input variables.
format	article
author	Asif Afzal Saad Alshahrani Abdulrahman Alrobaian Abdulrajak Buradi Sher Afghan Khan
author_facet	Asif Afzal Saad Alshahrani Abdulrahman Alrobaian Abdulrajak Buradi Sher Afghan Khan
author_sort	Asif Afzal
title	Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms
title_short	Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms
title_full	Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms
title_fullStr	Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms
title_full_unstemmed	Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms
title_sort	power plant energy predictions based on thermal factors using ridge and support vector regressor algorithms
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/8a495f4163774560aab862a28fd4c494
work_keys_str_mv	AT asifafzal powerplantenergypredictionsbasedonthermalfactorsusingridgeandsupportvectorregressoralgorithms AT saadalshahrani powerplantenergypredictionsbasedonthermalfactorsusingridgeandsupportvectorregressoralgorithms AT abdulrahmanalrobaian powerplantenergypredictionsbasedonthermalfactorsusingridgeandsupportvectorregressoralgorithms AT abdulrajakburadi powerplantenergypredictionsbasedonthermalfactorsusingridgeandsupportvectorregressoralgorithms AT sherafghankhan powerplantenergypredictionsbasedonthermalfactorsusingridgeandsupportvectorregressoralgorithms
_version_	1718432426679599104

Power Plant Energy Predictions Based on Thermal Factors Using Ridge and Support Vector Regressor Algorithms

Ejemplares similares