A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting

A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting

We evaluate and compare two common methods, artificial neural networks (ANN) and support vector regression (SVR), for predicting energy productions from a solar photovoltaic (PV) system in Florida 15 min, 1 h and 24 h ahead of time. A hierarchical approach is proposed based on the machine learning a...

Full description

Bibliographic Details
Main Authors: Zhaoxuan Li, SM Mahbobur Rahman, Rolando Vega, Bing Dong
Format: Article
Language:English
Published: MDPI AG 2016-01-01
Series:Energies
Subjects:
artificial neural network (ANN)
support vector regression (SVR)
photovoltaic (PV) forecasting
Online Access:http://www.mdpi.com/1996-1073/9/1/55
id doaj-9de3104f397949c78bb06389b2212d21
record_format Article
spelling doaj-9de3104f397949c78bb06389b2212d212020-11-24T21:07:12ZengMDPI AGEnergies1996-10732016-01-01915510.3390/en9010055en9010055A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production ForecastingZhaoxuan Li0SM Mahbobur Rahman1Rolando Vega2Bing Dong3Mechanical Engineering, University of Texas at San Antonio, San Antonio, TX 78249, USAMechanical Engineering, University of Texas at San Antonio, San Antonio, TX 78249, USATexas Sustainable Energy Research Institute, San Antonio, TX 78249, USAMechanical Engineering, University of Texas at San Antonio, San Antonio, TX 78249, USAWe evaluate and compare two common methods, artificial neural networks (ANN) and support vector regression (SVR), for predicting energy productions from a solar photovoltaic (PV) system in Florida 15 min, 1 h and 24 h ahead of time. A hierarchical approach is proposed based on the machine learning algorithms tested. The production data used in this work corresponds to 15 min averaged power measurements collected from 2014. The accuracy of the model is determined using computing error statistics such as mean bias error (MBE), mean absolute error (MAE), root mean square error (RMSE), relative MBE (rMBE), mean percentage error (MPE) and relative RMSE (rRMSE). This work provides findings on how forecasts from individual inverters will improve the total solar power generation forecast of the PV system.http://www.mdpi.com/1996-1073/9/1/55artificial neural network (ANN)support vector regression (SVR)photovoltaic (PV) forecasting
collection DOAJ
language English
format Article
sources DOAJ
author Zhaoxuan Li
SM Mahbobur Rahman
Rolando Vega
Bing Dong
spellingShingle Zhaoxuan Li
SM Mahbobur Rahman
Rolando Vega
Bing Dong
A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting
Energies
artificial neural network (ANN)
support vector regression (SVR)
photovoltaic (PV) forecasting
author_facet Zhaoxuan Li
SM Mahbobur Rahman
Rolando Vega
Bing Dong
author_sort Zhaoxuan Li
title A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting
title_short A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting
title_full A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting
title_fullStr A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting
title_full_unstemmed A Hierarchical Approach Using Machine Learning Methods in Solar Photovoltaic Energy Production Forecasting
title_sort hierarchical approach using machine learning methods in solar photovoltaic energy production forecasting
publisher MDPI AG
series Energies
issn 1996-1073
publishDate 2016-01-01
description We evaluate and compare two common methods, artificial neural networks (ANN) and support vector regression (SVR), for predicting energy productions from a solar photovoltaic (PV) system in Florida 15 min, 1 h and 24 h ahead of time. A hierarchical approach is proposed based on the machine learning algorithms tested. The production data used in this work corresponds to 15 min averaged power measurements collected from 2014. The accuracy of the model is determined using computing error statistics such as mean bias error (MBE), mean absolute error (MAE), root mean square error (RMSE), relative MBE (rMBE), mean percentage error (MPE) and relative RMSE (rRMSE). This work provides findings on how forecasts from individual inverters will improve the total solar power generation forecast of the PV system.
topic artificial neural network (ANN)
support vector regression (SVR)
photovoltaic (PV) forecasting
url http://www.mdpi.com/1996-1073/9/1/55
work_keys_str_mv AT zhaoxuanli ahierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT smmahboburrahman ahierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT rolandovega ahierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT bingdong ahierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT zhaoxuanli hierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT smmahboburrahman hierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT rolandovega hierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
AT bingdong hierarchicalapproachusingmachinelearningmethodsinsolarphotovoltaicenergyproductionforecasting
_version_ 1716763751094419456

Similar Items