Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models
This article involves forecasting daily electricity consumption in Thailand. Electricity consumption data are provided by the Electricity Generating Authority of Thailand, the leading power utility state enterprise under the Ministry of Energy. Five forecasting techniques, including multiple linear...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-04-01
|
Series: | Energies |
Subjects: | |
Online Access: | https://www.mdpi.com/1996-1073/15/9/3105 |
_version_ | 1797505046134390784 |
---|---|
author | Warut Pannakkong Thanyaporn Harncharnchai Jirachai Buddhakulsomsiri |
author_facet | Warut Pannakkong Thanyaporn Harncharnchai Jirachai Buddhakulsomsiri |
author_sort | Warut Pannakkong |
collection | DOAJ |
description | This article involves forecasting daily electricity consumption in Thailand. Electricity consumption data are provided by the Electricity Generating Authority of Thailand, the leading power utility state enterprise under the Ministry of Energy. Five forecasting techniques, including multiple linear regression, artificial neural network (ANN), support vector machine, hybrid models, and ensemble models, are implemented. The article proposes a hyperparameter tuning technique, called sequential grid search, which is based on the widely used grid search, for ANN and hybrid models. Auxiliary variables and indicator variables that can improve the models’ forecasting performance are included. From the computational experiment, the hybrid model of a multiple regression model to forecast the expected daily consumption and ANNs from the sequential grid search to forecast the error term, along with additional indicator variables for some national holidays, provides the best mean absolution percentage error of 1.5664% on the test data set. |
first_indexed | 2024-03-10T04:13:05Z |
format | Article |
id | doaj.art-6a526701ee144e5396d54fb4d7720078 |
institution | Directory Open Access Journal |
issn | 1996-1073 |
language | English |
last_indexed | 2024-03-10T04:13:05Z |
publishDate | 2022-04-01 |
publisher | MDPI AG |
record_format | Article |
series | Energies |
spelling | doaj.art-6a526701ee144e5396d54fb4d77200782023-11-23T08:06:36ZengMDPI AGEnergies1996-10732022-04-01159310510.3390/en15093105Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid ModelsWarut Pannakkong0Thanyaporn Harncharnchai1Jirachai Buddhakulsomsiri2School of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Thammasat University, Klong Luang 12121, Pathum Thani, ThailandSchool of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Thammasat University, Klong Luang 12121, Pathum Thani, ThailandSchool of Manufacturing Systems and Mechanical Engineering, Sirindhorn International Institute of Technology, Thammasat University, Klong Luang 12121, Pathum Thani, ThailandThis article involves forecasting daily electricity consumption in Thailand. Electricity consumption data are provided by the Electricity Generating Authority of Thailand, the leading power utility state enterprise under the Ministry of Energy. Five forecasting techniques, including multiple linear regression, artificial neural network (ANN), support vector machine, hybrid models, and ensemble models, are implemented. The article proposes a hyperparameter tuning technique, called sequential grid search, which is based on the widely used grid search, for ANN and hybrid models. Auxiliary variables and indicator variables that can improve the models’ forecasting performance are included. From the computational experiment, the hybrid model of a multiple regression model to forecast the expected daily consumption and ANNs from the sequential grid search to forecast the error term, along with additional indicator variables for some national holidays, provides the best mean absolution percentage error of 1.5664% on the test data set.https://www.mdpi.com/1996-1073/15/9/3105daily electricity consumptionforecastingartificial neural networksequential grid searchsupport vector machinemultiple linear regression |
spellingShingle | Warut Pannakkong Thanyaporn Harncharnchai Jirachai Buddhakulsomsiri Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models Energies daily electricity consumption forecasting artificial neural network sequential grid search support vector machine multiple linear regression |
title | Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models |
title_full | Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models |
title_fullStr | Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models |
title_full_unstemmed | Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models |
title_short | Forecasting Daily Electricity Consumption in Thailand Using Regression, Artificial Neural Network, Support Vector Machine, and Hybrid Models |
title_sort | forecasting daily electricity consumption in thailand using regression artificial neural network support vector machine and hybrid models |
topic | daily electricity consumption forecasting artificial neural network sequential grid search support vector machine multiple linear regression |
url | https://www.mdpi.com/1996-1073/15/9/3105 |
work_keys_str_mv | AT warutpannakkong forecastingdailyelectricityconsumptioninthailandusingregressionartificialneuralnetworksupportvectormachineandhybridmodels AT thanyapornharncharnchai forecastingdailyelectricityconsumptioninthailandusingregressionartificialneuralnetworksupportvectormachineandhybridmodels AT jirachaibuddhakulsomsiri forecastingdailyelectricityconsumptioninthailandusingregressionartificialneuralnetworksupportvectormachineandhybridmodels |