One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models

This paper proposes two hybrid grey-based short-term wind power prediction techniques: GM(1,1)-ARMA and GM(1,1)-NARnet. These techniques are combined with ARMA models and nonlinear autoregressive neural network (NARnet) models, respectively. The efficiency of these algorithms is examined using a rec...

Full description

Saved in:
Bibliographic Details
Main Author: Osman, Ahmed (author)
Other Authors: Hassan, Mohamed (author), Marzbani, Fatemeh (author), Landolsi, Taha (author)
Format: article
Published: 2016
Subjects:
Online Access:http://hdl.handle.net/11073/16312
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513432330436608
author Osman, Ahmed
author2 Hassan, Mohamed
Marzbani, Fatemeh
Landolsi, Taha
author2_role author
author
author
author_facet Osman, Ahmed
Hassan, Mohamed
Marzbani, Fatemeh
Landolsi, Taha
author_role author
dc.creator.none.fl_str_mv Osman, Ahmed
Hassan, Mohamed
Marzbani, Fatemeh
Landolsi, Taha
dc.date.none.fl_str_mv 2016
2018-11-05T08:17:12Z
2018-11-05T08:17:12Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv Osman, Ahmed, Mohamed S. Hassan, Fatemeh Marzabani, and Taha Landolsi. "One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models." International Journal of Operational Research 27, no. 1-2 (2016): 212-231.
1745-7653
http://hdl.handle.net/11073/16312
10.1504/IJOR.2016.078472
dc.language.none.fl_str_mv en_US
dc.publisher.none.fl_str_mv Inderscience
dc.relation.none.fl_str_mv International Journal of Operational Research
https://doi.org/10.1504/IJOR.2016.078472
dc.subject.none.fl_str_mv Wind power forecasting
Wind energy prediction
Time series analysis
ARMA models
Grey theory
GM(1,1)
GM(1,1)-ARMA
GM(1,1)-NARnet
neural networks
dc.title.none.fl_str_mv One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
description This paper proposes two hybrid grey-based short-term wind power prediction techniques: GM(1,1)-ARMA and GM(1,1)-NARnet. These techniques are combined with ARMA models and nonlinear autoregressive neural network (NARnet) models, respectively. The efficiency of these algorithms is examined using a recorded wind power dataset. The performance of these predictors is compared with classical ARMA models as well as the traditional grey model GM(1,1). Unlike the classical predictors, the proposed hybrid algorithms are not affected by the inherent uncertainty in the wind power. Therefore, the results obtained using the proposed hybrid algorithms outperform those obtained using classical predictors. In contrast to the GM(1,1)-ARMA model, the GM(1,1)-NARnet model utilises the nonlinear components of wind power in the forecasting procedure. Consequently, the obtained results from the GM(1,1)-NARnet outperform those obtained by the GM(1,1)-ARMA.
format article
id aus_2aae82b19cf465047d662462b3bfcf1a
identifier_str_mv Osman, Ahmed, Mohamed S. Hassan, Fatemeh Marzabani, and Taha Landolsi. "One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models." International Journal of Operational Research 27, no. 1-2 (2016): 212-231.
1745-7653
10.1504/IJOR.2016.078472
language_invalid_str_mv en_US
network_acronym_str aus
network_name_str aus
oai_identifier_str oai:repository.aus.edu:11073/16312
publishDate 2016
publisher.none.fl_str_mv Inderscience
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
spelling One-Hour-Ahead Wind Power Forecast Using Hybrid Grey ModelsOsman, AhmedHassan, MohamedMarzbani, FatemehLandolsi, TahaWind power forecastingWind energy predictionTime series analysisARMA modelsGrey theoryGM(1,1)GM(1,1)-ARMAGM(1,1)-NARnetneural networksThis paper proposes two hybrid grey-based short-term wind power prediction techniques: GM(1,1)-ARMA and GM(1,1)-NARnet. These techniques are combined with ARMA models and nonlinear autoregressive neural network (NARnet) models, respectively. The efficiency of these algorithms is examined using a recorded wind power dataset. The performance of these predictors is compared with classical ARMA models as well as the traditional grey model GM(1,1). Unlike the classical predictors, the proposed hybrid algorithms are not affected by the inherent uncertainty in the wind power. Therefore, the results obtained using the proposed hybrid algorithms outperform those obtained using classical predictors. In contrast to the GM(1,1)-ARMA model, the GM(1,1)-NARnet model utilises the nonlinear components of wind power in the forecasting procedure. Consequently, the obtained results from the GM(1,1)-NARnet outperform those obtained by the GM(1,1)-ARMA.Inderscience2018-11-05T08:17:12Z2018-11-05T08:17:12Z2016info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfOsman, Ahmed, Mohamed S. Hassan, Fatemeh Marzabani, and Taha Landolsi. "One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models." International Journal of Operational Research 27, no. 1-2 (2016): 212-231.1745-7653http://hdl.handle.net/11073/1631210.1504/IJOR.2016.078472en_USInternational Journal of Operational Researchhttps://doi.org/10.1504/IJOR.2016.078472oai:repository.aus.edu:11073/163122024-08-22T12:16:37Z
spellingShingle One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
Osman, Ahmed
Wind power forecasting
Wind energy prediction
Time series analysis
ARMA models
Grey theory
GM(1,1)
GM(1,1)-ARMA
GM(1,1)-NARnet
neural networks
status_str publishedVersion
title One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
title_full One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
title_fullStr One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
title_full_unstemmed One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
title_short One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
title_sort One-Hour-Ahead Wind Power Forecast Using Hybrid Grey Models
topic Wind power forecasting
Wind energy prediction
Time series analysis
ARMA models
Grey theory
GM(1,1)
GM(1,1)-ARMA
GM(1,1)-NARnet
neural networks
url http://hdl.handle.net/11073/16312