Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting

Short-Term Load Forecasting is critical for reliable power system operation, and the search for enhanced methodologies has been a constant field of investigation, particularly in an increasingly competitive environment where the market operator and its participants need to better inform their decisi...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pedro M. R. Bento, Jose A. N. Pombo, Maria R. A. Calado, Silvio J. P. S. Mariano
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	ARIMA models correlation analysis deep learning deep neural networks ensemble methods ISO New England Technology T
Acceso en línea:	https://doaj.org/article/dd27aaef327f4061b5d5426f0f4a3a92
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:dd27aaef327f4061b5d5426f0f4a3a92
record_format	dspace
spelling	oai:doaj.org-article:dd27aaef327f4061b5d5426f0f4a3a922021-11-11T16:05:23ZStacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting10.3390/en142173781996-1073https://doaj.org/article/dd27aaef327f4061b5d5426f0f4a3a922021-11-01T00:00:00Zhttps://www.mdpi.com/1996-1073/14/21/7378https://doaj.org/toc/1996-1073Short-Term Load Forecasting is critical for reliable power system operation, and the search for enhanced methodologies has been a constant field of investigation, particularly in an increasingly competitive environment where the market operator and its participants need to better inform their decisions. Hence, it is important to continue advancing in terms of forecasting accuracy and consistency. This paper presents a new deep learning-based ensemble methodology for 24 h ahead load forecasting, where an automatic framework is proposed to select the best Box-Jenkins models (ARIMA Forecasters), from a wide-range of combinations. The method is distinct in its parameters but more importantly in considering different batches of historical (training) data, thus benefiting from prediction models focused on recent and longer load trends. Afterwards, these accurate predictions, mainly the linear components of the load time-series, are fed to the ensemble Deep Forward Neural Network. This flexible type of network architecture not only functions as a combiner but also receives additional historical and auxiliary data to further its generalization capabilities. Numerical testing using New England market data validated the proposed ensemble approach with diverse base forecasters, achieving promising results in comparison with other state-of-the-art methods.Pedro M. R. BentoJose A. N. PomboMaria R. A. CaladoSilvio J. P. S. MarianoMDPI AGarticleARIMA modelscorrelation analysisdeep learningdeep neural networksensemble methodsISO New EnglandTechnologyTENEnergies, Vol 14, Iss 7378, p 7378 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	ARIMA models correlation analysis deep learning deep neural networks ensemble methods ISO New England Technology T
spellingShingle	ARIMA models correlation analysis deep learning deep neural networks ensemble methods ISO New England Technology T Pedro M. R. Bento Jose A. N. Pombo Maria R. A. Calado Silvio J. P. S. Mariano Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting
description	Short-Term Load Forecasting is critical for reliable power system operation, and the search for enhanced methodologies has been a constant field of investigation, particularly in an increasingly competitive environment where the market operator and its participants need to better inform their decisions. Hence, it is important to continue advancing in terms of forecasting accuracy and consistency. This paper presents a new deep learning-based ensemble methodology for 24 h ahead load forecasting, where an automatic framework is proposed to select the best Box-Jenkins models (ARIMA Forecasters), from a wide-range of combinations. The method is distinct in its parameters but more importantly in considering different batches of historical (training) data, thus benefiting from prediction models focused on recent and longer load trends. Afterwards, these accurate predictions, mainly the linear components of the load time-series, are fed to the ensemble Deep Forward Neural Network. This flexible type of network architecture not only functions as a combiner but also receives additional historical and auxiliary data to further its generalization capabilities. Numerical testing using New England market data validated the proposed ensemble approach with diverse base forecasters, achieving promising results in comparison with other state-of-the-art methods.
format	article
author	Pedro M. R. Bento Jose A. N. Pombo Maria R. A. Calado Silvio J. P. S. Mariano
author_facet	Pedro M. R. Bento Jose A. N. Pombo Maria R. A. Calado Silvio J. P. S. Mariano
author_sort	Pedro M. R. Bento
title	Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting
title_short	Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting
title_full	Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting
title_fullStr	Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting
title_full_unstemmed	Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting
title_sort	stacking ensemble methodology using deep learning and arima models for short-term load forecasting
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/dd27aaef327f4061b5d5426f0f4a3a92
work_keys_str_mv	AT pedromrbento stackingensemblemethodologyusingdeeplearningandarimamodelsforshorttermloadforecasting AT joseanpombo stackingensemblemethodologyusingdeeplearningandarimamodelsforshorttermloadforecasting AT mariaracalado stackingensemblemethodologyusingdeeplearningandarimamodelsforshorttermloadforecasting AT silviojpsmariano stackingensemblemethodologyusingdeeplearningandarimamodelsforshorttermloadforecasting
_version_	1718432444098543616

Stacking Ensemble Methodology Using Deep Learning and ARIMA Models for Short-Term Load Forecasting

Ejemplares similares