A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption

With the share of electricity in total final energy consumption increasing quickly, the world is becoming increasingly dependent on electricity, which makes it more and more important to improve the forecasting accuracy of electricity consumption to ensure the normal operation of economic activities...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Xi Zhang, Rui Li
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	monthly electricity consumption STL time correlation modification ANN LSTM General Works A
Acceso en línea:	https://doaj.org/article/e2c71ff89046430585eb25b51024b63c
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:e2c71ff89046430585eb25b51024b63c
record_format	dspace
spelling	oai:doaj.org-article:e2c71ff89046430585eb25b51024b63c2021-12-01T21:43:52ZA Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption2296-598X10.3389/fenrg.2021.792358https://doaj.org/article/e2c71ff89046430585eb25b51024b63c2021-12-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fenrg.2021.792358/fullhttps://doaj.org/toc/2296-598XWith the share of electricity in total final energy consumption increasing quickly, the world is becoming increasingly dependent on electricity, which makes it more and more important to improve the forecasting accuracy of electricity consumption to ensure the normal operation of economic activities. In this paper, a novel decomposition and combination technique to forecast monthly electricity consumption is proposed. First, we use STL decomposition to obtain the trend, season, and residual components of the time series. Second, we use SARIMA, SVR, ANN, and LSTM to forecast trend, season, and residual component, respectively. Third, we use time correlation principle to improve the forecasting accuracy of season component. Fourth, we integrated the residual component predicted by SARIMA, SVR, ANN, and LSTM into a new sequence to improve the forecasting accuracy of residual component. In order to verify the performance of the proposed forecast model, monthly electricity consumption data in China is introduced as an example for empirical analysis. The results show that after STL decomposition, time correlation modification, and residual modification, the forecasting accuracy of each model has been gradually improved. We believe that the proposed forecast model in this paper can also be used to solve other mid- and long-term forecasting problems with obvious seasonal characteristics.Xi ZhangRui LiFrontiers Media S.A.articlemonthly electricity consumptionSTLtime correlation modificationANNLSTMGeneral WorksAENFrontiers in Energy Research, Vol 9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	monthly electricity consumption STL time correlation modification ANN LSTM General Works A
spellingShingle	monthly electricity consumption STL time correlation modification ANN LSTM General Works A Xi Zhang Rui Li A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption
description	With the share of electricity in total final energy consumption increasing quickly, the world is becoming increasingly dependent on electricity, which makes it more and more important to improve the forecasting accuracy of electricity consumption to ensure the normal operation of economic activities. In this paper, a novel decomposition and combination technique to forecast monthly electricity consumption is proposed. First, we use STL decomposition to obtain the trend, season, and residual components of the time series. Second, we use SARIMA, SVR, ANN, and LSTM to forecast trend, season, and residual component, respectively. Third, we use time correlation principle to improve the forecasting accuracy of season component. Fourth, we integrated the residual component predicted by SARIMA, SVR, ANN, and LSTM into a new sequence to improve the forecasting accuracy of residual component. In order to verify the performance of the proposed forecast model, monthly electricity consumption data in China is introduced as an example for empirical analysis. The results show that after STL decomposition, time correlation modification, and residual modification, the forecasting accuracy of each model has been gradually improved. We believe that the proposed forecast model in this paper can also be used to solve other mid- and long-term forecasting problems with obvious seasonal characteristics.
format	article
author	Xi Zhang Rui Li
author_facet	Xi Zhang Rui Li
author_sort	Xi Zhang
title	A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption
title_short	A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption
title_full	A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption
title_fullStr	A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption
title_full_unstemmed	A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption
title_sort	novel decomposition and combination technique for forecasting monthly electricity consumption
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/e2c71ff89046430585eb25b51024b63c
work_keys_str_mv	AT xizhang anoveldecompositionandcombinationtechniqueforforecastingmonthlyelectricityconsumption AT ruili anoveldecompositionandcombinationtechniqueforforecastingmonthlyelectricityconsumption AT xizhang noveldecompositionandcombinationtechniqueforforecastingmonthlyelectricityconsumption AT ruili noveldecompositionandcombinationtechniqueforforecastingmonthlyelectricityconsumption
_version_	1718404193962688512

A Novel Decomposition and Combination Technique for Forecasting Monthly Electricity Consumption

Ejemplares similares