Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements
Short-term Photovoltaic (PV) Power Forecasting (STPF) is considered a topic of utmost importance in smart grids. The deployment of STPF techniques provides fast dispatching in the case of sudden variations due to stochastic weather conditions. This paper presents an efficient data-driven method base...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/14/13/3992 |
id |
doaj-fab6482aba014a01acbb4b25c6f520da |
---|---|
record_format |
Article |
spelling |
doaj-fab6482aba014a01acbb4b25c6f520da2021-07-15T15:33:41ZengMDPI AGEnergies1996-10732021-07-01143992399210.3390/en14133992Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather MeasurementsMohamed Massaoudi0Ines Chihi1Lilia Sidhom2Mohamed Trabelsi3Shady S. Refaat4Fakhreddine S. Oueslati5Department of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha 3263, QatarDépartement Ingénierie, Faculté des Sciences, des Technologies et de Médecine, Campus Kirchberg, Université du Luxembourg, 1359 Luxembourg, LuxembourgLaboratory of Energy Applications and Renewable Energy Efficiency (LAPER), El Manar University, Tunis 1068, TunisiaDepartment of Electronic and Communications Engineering, Kuwait College of Science and Technology, Doha District, Block 4, Doha P.O. Box 27235, KuwaitDepartment of Electrical and Computer Engineering, Texas A&M University at Qatar, Doha 3263, QatarLaboratoire Matériaux Molécules et Applications (LMMA) à l’IPEST, Carthage University, Tunis 1054, TunisiaShort-term Photovoltaic (PV) Power Forecasting (STPF) is considered a topic of utmost importance in smart grids. The deployment of STPF techniques provides fast dispatching in the case of sudden variations due to stochastic weather conditions. This paper presents an efficient data-driven method based on enhanced Random Forest (RF) model. The proposed method employs an ensemble of attribute selection techniques to manage bias/variance optimization for STPF application and enhance the forecasting quality results. The overall architecture strategy gathers the relevant information to constitute a voted feature-weighting vector of weather inputs. The main emphasis in this paper is laid on the knowledge expertise obtained from weather measurements. The feature selection techniques are based on local Interpretable Model-Agnostic Explanations, Extreme Boosting Model, and Elastic Net. A comparative performance investigation using an actual database, collected from the weather sensors, demonstrates the superiority of the proposed technique versus several data-driven machine learning models when applied to a typical distributed PV system.https://www.mdpi.com/1996-1073/14/13/3992smart gridPhotovoltaic (PV) Power Forecastingweather sensorsrandom decision forestfeature importanceenergy management |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Mohamed Massaoudi Ines Chihi Lilia Sidhom Mohamed Trabelsi Shady S. Refaat Fakhreddine S. Oueslati |
spellingShingle |
Mohamed Massaoudi Ines Chihi Lilia Sidhom Mohamed Trabelsi Shady S. Refaat Fakhreddine S. Oueslati Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements Energies smart grid Photovoltaic (PV) Power Forecasting weather sensors random decision forest feature importance energy management |
author_facet |
Mohamed Massaoudi Ines Chihi Lilia Sidhom Mohamed Trabelsi Shady S. Refaat Fakhreddine S. Oueslati |
author_sort |
Mohamed Massaoudi |
title |
Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements |
title_short |
Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements |
title_full |
Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements |
title_fullStr |
Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements |
title_full_unstemmed |
Enhanced Random Forest Model for Robust Short-Term Photovoltaic Power Forecasting Using Weather Measurements |
title_sort |
enhanced random forest model for robust short-term photovoltaic power forecasting using weather measurements |
publisher |
MDPI AG |
series |
Energies |
issn |
1996-1073 |
publishDate |
2021-07-01 |
description |
Short-term Photovoltaic (PV) Power Forecasting (STPF) is considered a topic of utmost importance in smart grids. The deployment of STPF techniques provides fast dispatching in the case of sudden variations due to stochastic weather conditions. This paper presents an efficient data-driven method based on enhanced Random Forest (RF) model. The proposed method employs an ensemble of attribute selection techniques to manage bias/variance optimization for STPF application and enhance the forecasting quality results. The overall architecture strategy gathers the relevant information to constitute a voted feature-weighting vector of weather inputs. The main emphasis in this paper is laid on the knowledge expertise obtained from weather measurements. The feature selection techniques are based on local Interpretable Model-Agnostic Explanations, Extreme Boosting Model, and Elastic Net. A comparative performance investigation using an actual database, collected from the weather sensors, demonstrates the superiority of the proposed technique versus several data-driven machine learning models when applied to a typical distributed PV system. |
topic |
smart grid Photovoltaic (PV) Power Forecasting weather sensors random decision forest feature importance energy management |
url |
https://www.mdpi.com/1996-1073/14/13/3992 |
work_keys_str_mv |
AT mohamedmassaoudi enhancedrandomforestmodelforrobustshorttermphotovoltaicpowerforecastingusingweathermeasurements AT ineschihi enhancedrandomforestmodelforrobustshorttermphotovoltaicpowerforecastingusingweathermeasurements AT liliasidhom enhancedrandomforestmodelforrobustshorttermphotovoltaicpowerforecastingusingweathermeasurements AT mohamedtrabelsi enhancedrandomforestmodelforrobustshorttermphotovoltaicpowerforecastingusingweathermeasurements AT shadysrefaat enhancedrandomforestmodelforrobustshorttermphotovoltaicpowerforecastingusingweathermeasurements AT fakhreddinesoueslati enhancedrandomforestmodelforrobustshorttermphotovoltaicpowerforecastingusingweathermeasurements |
_version_ |
1721299738514423808 |