New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE
Feature selection helps improve the accuracy and computational time of solar forecasting. However, FS is often passed by or conducted with methods that do not suit the solar forecasting issue, such as filter or linear methods. In this study, we propose a wrapper method termed Sequential Forward Sele...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-09-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/16/19/6842 |
_version_ | 1797575963940225024 |
---|---|
author | Jérémy Macaire Sara Zermani Laurent Linguet |
author_facet | Jérémy Macaire Sara Zermani Laurent Linguet |
author_sort | Jérémy Macaire |
collection | DOAJ |
description | Feature selection helps improve the accuracy and computational time of solar forecasting. However, FS is often passed by or conducted with methods that do not suit the solar forecasting issue, such as filter or linear methods. In this study, we propose a wrapper method termed Sequential Forward Selection (SFS), with a Kernel Conditional Density Estimator (KCDE) named SFS-KCDE, as FS to forecast day-ahead regional PV power production in French Guiana. This method was compared to three other FS methods used in earlier studies: the Pearson correlation method, the RReliefF (RRF) method, and SFS using a linear regression. It has been shown that SFS-KCDE outperforms other FS methods, particularly for overcast sky conditions. Moreover, Wrapper methods show better forecasting performance than filter methods and should be used. |
first_indexed | 2024-03-10T21:45:50Z |
format | Article |
id | doaj.art-8ab4c3daa8194d8f8f6f008adb16213b |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T21:45:50Z |
publishDate | 2023-09-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-8ab4c3daa8194d8f8f6f008adb16213b2023-11-19T14:19:36ZengMDPI AGEnergies1996-10732023-09-011619684210.3390/en16196842New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDEJérémy Macaire0Sara Zermani1Laurent Linguet2Espace pour le Développement (Espace-Dev), Université de Guyane, 97300 Cayenne, FranceEspace pour le Développement (Espace-Dev), Université de Guyane, 97300 Cayenne, FranceEspace pour le Développement (Espace-Dev), Université de Guyane, 97300 Cayenne, FranceFeature selection helps improve the accuracy and computational time of solar forecasting. However, FS is often passed by or conducted with methods that do not suit the solar forecasting issue, such as filter or linear methods. In this study, we propose a wrapper method termed Sequential Forward Selection (SFS), with a Kernel Conditional Density Estimator (KCDE) named SFS-KCDE, as FS to forecast day-ahead regional PV power production in French Guiana. This method was compared to three other FS methods used in earlier studies: the Pearson correlation method, the RReliefF (RRF) method, and SFS using a linear regression. It has been shown that SFS-KCDE outperforms other FS methods, particularly for overcast sky conditions. Moreover, Wrapper methods show better forecasting performance than filter methods and should be used.https://www.mdpi.com/1996-1073/16/19/6842photovoltaic power forecastingfeature selectionmachine learningKernel conditional density estimator |
spellingShingle | Jérémy Macaire Sara Zermani Laurent Linguet New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE Energies photovoltaic power forecasting feature selection machine learning Kernel conditional density estimator |
title | New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE |
title_full | New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE |
title_fullStr | New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE |
title_full_unstemmed | New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE |
title_short | New Feature Selection Approach for Photovoltaïc Power Forecasting Using KCDE |
title_sort | new feature selection approach for photovoltaic power forecasting using kcde |
topic | photovoltaic power forecasting feature selection machine learning Kernel conditional density estimator |
url | https://www.mdpi.com/1996-1073/16/19/6842 |
work_keys_str_mv | AT jeremymacaire newfeatureselectionapproachforphotovoltaicpowerforecastingusingkcde AT sarazermani newfeatureselectionapproachforphotovoltaicpowerforecastingusingkcde AT laurentlinguet newfeatureselectionapproachforphotovoltaicpowerforecastingusingkcde |