Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network

The next-day load forecasting is complex due to the load pattern variations driven by external factors, such as weather and time. This study proposes a hybrid model that incorporates the Classification and Regression Tree (CART) with pruning conditions and a Deep Belief Network (DBN) to improve fore...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pyae Pyae Phyo, Chawalit Jeenanunta
Formato: article
Lenguaje:EN
Publicado: IEEE 2021
Materias:
Acceso en línea:https://doaj.org/article/8b0ff91b3ffb46669facc8a72795cf27
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:8b0ff91b3ffb46669facc8a72795cf27
record_format dspace
spelling oai:doaj.org-article:8b0ff91b3ffb46669facc8a72795cf272021-11-20T00:01:34ZDaily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network2169-353610.1109/ACCESS.2021.3127211https://doaj.org/article/8b0ff91b3ffb46669facc8a72795cf272021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9611228/https://doaj.org/toc/2169-3536The next-day load forecasting is complex due to the load pattern variations driven by external factors, such as weather and time. This study proposes a hybrid model that incorporates the Classification and Regression Tree (CART) with pruning conditions and a Deep Belief Network (DBN) to improve forecasting accuracy. The CART can recognize the load patterns by classifying similar groups with low variance, thus reducing the complexity of the forecasting model. The actual 48-period load data from the Electricity Generating Authority of Thailand (EGAT) is used. The proposed model is compared with six widely used standalone forecasting benchmark models and provides better at the minimum 0.46% mean absolute percentage error. Moreover, the forecasting performance of DBN and the other four benchmark models are improved by using our hybrid approach.Pyae Pyae PhyoChawalit JeenanuntaIEEEarticleClassification and regression tree (CART)daily load forecastingdeep belief network (DBN)forecasting accuracypruned-CARTElectrical engineering. Electronics. Nuclear engineeringTK1-9971ENIEEE Access, Vol 9, Pp 152226-152242 (2021)
institution DOAJ
collection DOAJ
language EN
topic Classification and regression tree (CART)
daily load forecasting
deep belief network (DBN)
forecasting accuracy
pruned-CART
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
spellingShingle Classification and regression tree (CART)
daily load forecasting
deep belief network (DBN)
forecasting accuracy
pruned-CART
Electrical engineering. Electronics. Nuclear engineering
TK1-9971
Pyae Pyae Phyo
Chawalit Jeenanunta
Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network
description The next-day load forecasting is complex due to the load pattern variations driven by external factors, such as weather and time. This study proposes a hybrid model that incorporates the Classification and Regression Tree (CART) with pruning conditions and a Deep Belief Network (DBN) to improve forecasting accuracy. The CART can recognize the load patterns by classifying similar groups with low variance, thus reducing the complexity of the forecasting model. The actual 48-period load data from the Electricity Generating Authority of Thailand (EGAT) is used. The proposed model is compared with six widely used standalone forecasting benchmark models and provides better at the minimum 0.46% mean absolute percentage error. Moreover, the forecasting performance of DBN and the other four benchmark models are improved by using our hybrid approach.
format article
author Pyae Pyae Phyo
Chawalit Jeenanunta
author_facet Pyae Pyae Phyo
Chawalit Jeenanunta
author_sort Pyae Pyae Phyo
title Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network
title_short Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network
title_full Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network
title_fullStr Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network
title_full_unstemmed Daily Load Forecasting Based on a Combination of Classification and Regression Tree and Deep Belief Network
title_sort daily load forecasting based on a combination of classification and regression tree and deep belief network
publisher IEEE
publishDate 2021
url https://doaj.org/article/8b0ff91b3ffb46669facc8a72795cf27
work_keys_str_mv AT pyaepyaephyo dailyloadforecastingbasedonacombinationofclassificationandregressiontreeanddeepbeliefnetwork
AT chawalitjeenanunta dailyloadforecastingbasedonacombinationofclassificationandregressiontreeanddeepbeliefnetwork
_version_ 1718419847051739136