A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM

An efficient energy operation strategy for the smart grid requires accurate day-ahead electricity load forecasts with high time resolutions, such as 15 or 30 min. Most high-time resolution electricity load prediction techniques deal with a single output prediction, so their ability to cope with sudd...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Jinwoong Park, Eenjun Hwang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	n/a Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/b03a3751ad664accbbf6df2df0e63098
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:b03a3751ad664accbbf6df2df0e63098
record_format	dspace
spelling	oai:doaj.org-article:b03a3751ad664accbbf6df2df0e630982021-11-25T18:58:43ZA Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM10.3390/s212276971424-8220https://doaj.org/article/b03a3751ad664accbbf6df2df0e630982021-11-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/22/7697https://doaj.org/toc/1424-8220An efficient energy operation strategy for the smart grid requires accurate day-ahead electricity load forecasts with high time resolutions, such as 15 or 30 min. Most high-time resolution electricity load prediction techniques deal with a single output prediction, so their ability to cope with sudden load changes is limited. Multistep-ahead forecasting addresses this problem, but conventional multistep-ahead prediction models suffer from deterioration in prediction performance as the prediction range is expanded. In this paper, we propose a novel two-stage multistep-ahead forecasting model that combines a single-output forecasting model and a multistep-ahead forecasting model to solve the aforementioned problem. In the first stage, we perform a single-output prediction based on recent electricity load data using a light gradient boosting machine with time-series cross-validation, and feed it to the second stage. In the second stage, we construct a multistep-ahead forecasting model that applies an attention mechanism to sequence-to-sequence bidirectional long short-term memory (S2S ATT-BiLSTM). Compared to the single S2S ATT-BiLSTM model, our proposed model achieved improvements of 3.23% and 4.92% in mean absolute percentage error and normalized root mean square error, respectively.Jinwoong ParkEenjun HwangMDPI AGarticlen/aChemical technologyTP1-1185ENSensors, Vol 21, Iss 7697, p 7697 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	n/a Chemical technology TP1-1185
spellingShingle	n/a Chemical technology TP1-1185 Jinwoong Park Eenjun Hwang A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM
description	An efficient energy operation strategy for the smart grid requires accurate day-ahead electricity load forecasts with high time resolutions, such as 15 or 30 min. Most high-time resolution electricity load prediction techniques deal with a single output prediction, so their ability to cope with sudden load changes is limited. Multistep-ahead forecasting addresses this problem, but conventional multistep-ahead prediction models suffer from deterioration in prediction performance as the prediction range is expanded. In this paper, we propose a novel two-stage multistep-ahead forecasting model that combines a single-output forecasting model and a multistep-ahead forecasting model to solve the aforementioned problem. In the first stage, we perform a single-output prediction based on recent electricity load data using a light gradient boosting machine with time-series cross-validation, and feed it to the second stage. In the second stage, we construct a multistep-ahead forecasting model that applies an attention mechanism to sequence-to-sequence bidirectional long short-term memory (S2S ATT-BiLSTM). Compared to the single S2S ATT-BiLSTM model, our proposed model achieved improvements of 3.23% and 4.92% in mean absolute percentage error and normalized root mean square error, respectively.
format	article
author	Jinwoong Park Eenjun Hwang
author_facet	Jinwoong Park Eenjun Hwang
author_sort	Jinwoong Park
title	A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM
title_short	A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM
title_full	A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM
title_fullStr	A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM
title_full_unstemmed	A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM
title_sort	two-stage multistep-ahead electricity load forecasting scheme based on lightgbm and attention-bilstm
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/b03a3751ad664accbbf6df2df0e63098
work_keys_str_mv	AT jinwoongpark atwostagemultistepaheadelectricityloadforecastingschemebasedonlightgbmandattentionbilstm AT eenjunhwang atwostagemultistepaheadelectricityloadforecastingschemebasedonlightgbmandattentionbilstm AT jinwoongpark twostagemultistepaheadelectricityloadforecastingschemebasedonlightgbmandattentionbilstm AT eenjunhwang twostagemultistepaheadelectricityloadforecastingschemebasedonlightgbmandattentionbilstm
_version_	1718410482953486336

A Two-Stage Multistep-Ahead Electricity Load Forecasting Scheme Based on LightGBM and Attention-BiLSTM

Ejemplares similares