Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting
The ongoing upsurge of deep learning and artificial intelligence methodologies manifest incredible accomplishment in a broad scope of assessing issues in different industries, including the energy sector. In this article, we have presented a hybrid energy forecasting model based on machine learning...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-05-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/11/2681 |
| _version_ | 1827716161332051968 |
|---|---|
| author | Prince Waqas Khan Yung-Cheol Byun Sang-Joon Lee Namje Park |
| author_facet | Prince Waqas Khan Yung-Cheol Byun Sang-Joon Lee Namje Park |
| author_sort | Prince Waqas Khan |
| collection | DOAJ |
| description | The ongoing upsurge of deep learning and artificial intelligence methodologies manifest incredible accomplishment in a broad scope of assessing issues in different industries, including the energy sector. In this article, we have presented a hybrid energy forecasting model based on machine learning techniques. It is based on the three machine learning algorithms: extreme gradient boosting, categorical boosting, and random forest method. Usually, machine learning algorithms focus on fine-tuning the hyperparameters, but our proposed hybrid algorithm focuses on the preprocessing using feature engineering to improve forecasting. We also focus on the way to impute a significant data gap and its effect on predicting. The forecasting exactness of the proposed model is evaluated using the regression score, and it depicts that the proposed model, with an R-squared of 0.9212, is more accurate than existing models. For the testing purpose of the proposed energy consumption forecasting model, we have used the actual dataset of South Korea’s hourly energy consumption. The proposed model can be used for any other dataset as well. This research result will provide a scientific premise for the strategy modification of energy supply and demand. |
| first_indexed | 2024-03-10T19:34:41Z |
| format | Article |
| id | doaj.art-64dbb90097774235a3bd73c5950dd605 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T19:34:41Z |
| publishDate | 2020-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-64dbb90097774235a3bd73c5950dd6052023-11-20T01:46:46ZengMDPI AGEnergies1996-10732020-05-011311268110.3390/en13112681Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand ForecastingPrince Waqas Khan0Yung-Cheol Byun1Sang-Joon Lee2Namje Park3Department of Computer Engineering, Jeju National University, Jeju-si 63243, KoreaDepartment of Computer Engineering, Jeju National University, Jeju-si 63243, KoreaDepartment of Computer Engineering, Jeju National University, Jeju-si 63243, KoreaDepartment of Computer Education, Teachers College, Jeju National University, Jeju City 63243, KoreaThe ongoing upsurge of deep learning and artificial intelligence methodologies manifest incredible accomplishment in a broad scope of assessing issues in different industries, including the energy sector. In this article, we have presented a hybrid energy forecasting model based on machine learning techniques. It is based on the three machine learning algorithms: extreme gradient boosting, categorical boosting, and random forest method. Usually, machine learning algorithms focus on fine-tuning the hyperparameters, but our proposed hybrid algorithm focuses on the preprocessing using feature engineering to improve forecasting. We also focus on the way to impute a significant data gap and its effect on predicting. The forecasting exactness of the proposed model is evaluated using the regression score, and it depicts that the proposed model, with an R-squared of 0.9212, is more accurate than existing models. For the testing purpose of the proposed energy consumption forecasting model, we have used the actual dataset of South Korea’s hourly energy consumption. The proposed model can be used for any other dataset as well. This research result will provide a scientific premise for the strategy modification of energy supply and demand.https://www.mdpi.com/1996-1073/13/11/2681deep learningenergy forecastingmachine learningfeature engineeringtime seriesXGBoost |
| spellingShingle | Prince Waqas Khan Yung-Cheol Byun Sang-Joon Lee Namje Park Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting Energies deep learning energy forecasting machine learning feature engineering time series XGBoost |
| title | Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting |
| title_full | Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting |
| title_fullStr | Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting |
| title_full_unstemmed | Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting |
| title_short | Machine Learning Based Hybrid System for Imputation and Efficient Energy Demand Forecasting |
| title_sort | machine learning based hybrid system for imputation and efficient energy demand forecasting |
| topic | deep learning energy forecasting machine learning feature engineering time series XGBoost |
| url | https://www.mdpi.com/1996-1073/13/11/2681 |
| work_keys_str_mv | AT princewaqaskhan machinelearningbasedhybridsystemforimputationandefficientenergydemandforecasting AT yungcheolbyun machinelearningbasedhybridsystemforimputationandefficientenergydemandforecasting AT sangjoonlee machinelearningbasedhybridsystemforimputationandefficientenergydemandforecasting AT namjepark machinelearningbasedhybridsystemforimputationandefficientenergydemandforecasting |