Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models
Electric load forecasting is crucial for the metallurgy industry because it enables effective resource allocation, production scheduling, and optimized energy management. To achieve an accurate load forecasting, it is essential to develop an efficient approach. In this study, we considered the time...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-07-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/14/5381 |
| _version_ | 1797589455706521600 |
|---|---|
| author | Fachrizal Aksan Vishnu Suresh Przemysław Janik Tomasz Sikorski |
| author_facet | Fachrizal Aksan Vishnu Suresh Przemysław Janik Tomasz Sikorski |
| author_sort | Fachrizal Aksan |
| collection | DOAJ |
| description | Electric load forecasting is crucial for the metallurgy industry because it enables effective resource allocation, production scheduling, and optimized energy management. To achieve an accurate load forecasting, it is essential to develop an efficient approach. In this study, we considered the time factor of univariate time-series data to implement various deep learning models for predicting the load one hour ahead under different conditions (seasonal and daily variations). The goal was to identify the most suitable model for each specific condition. In this study, two hybrid deep learning models were proposed. The first model combines variational mode decomposition (VMD) with a convolutional neural network (CNN) and gated recurrent unit (GRU). The second model incorporates VMD with a CNN and long short-term memory (LSTM). The proposed models outperformed the baseline models. The VMD–CNN–LSTM performed well for seasonal conditions, with an average RMSE of 12.215 kW, MAE of 9.543 kW, and MAPE of 0.095%. Meanwhile, the VMD–CNN–GRU performed well for daily variations, with an average RMSE value of 11.595 kW, MAE of 9.092 kW, and MAPE of 0.079%. The findings support the practical application of the proposed models for electrical load forecasting in diverse scenarios, especially concerning seasonal and daily variations. |
| first_indexed | 2024-03-11T01:06:56Z |
| format | Article |
| id | doaj.art-93612241b8be48a6a8b1b0a67ea32801 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T01:06:56Z |
| publishDate | 2023-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-93612241b8be48a6a8b1b0a67ea328012023-11-18T19:09:32ZengMDPI AGEnergies1996-10732023-07-011614538110.3390/en16145381Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning ModelsFachrizal Aksan0Vishnu Suresh1Przemysław Janik2Tomasz Sikorski3Faculty of Electrical Engineering, Wroclaw University of Science and Technology, 50-370 Wroclaw, PolandFaculty of Electrical Engineering, Wroclaw University of Science and Technology, 50-370 Wroclaw, PolandFaculty of Electrical Engineering, Wroclaw University of Science and Technology, 50-370 Wroclaw, PolandFaculty of Electrical Engineering, Wroclaw University of Science and Technology, 50-370 Wroclaw, PolandElectric load forecasting is crucial for the metallurgy industry because it enables effective resource allocation, production scheduling, and optimized energy management. To achieve an accurate load forecasting, it is essential to develop an efficient approach. In this study, we considered the time factor of univariate time-series data to implement various deep learning models for predicting the load one hour ahead under different conditions (seasonal and daily variations). The goal was to identify the most suitable model for each specific condition. In this study, two hybrid deep learning models were proposed. The first model combines variational mode decomposition (VMD) with a convolutional neural network (CNN) and gated recurrent unit (GRU). The second model incorporates VMD with a CNN and long short-term memory (LSTM). The proposed models outperformed the baseline models. The VMD–CNN–LSTM performed well for seasonal conditions, with an average RMSE of 12.215 kW, MAE of 9.543 kW, and MAPE of 0.095%. Meanwhile, the VMD–CNN–GRU performed well for daily variations, with an average RMSE value of 11.595 kW, MAE of 9.092 kW, and MAPE of 0.079%. The findings support the practical application of the proposed models for electrical load forecasting in diverse scenarios, especially concerning seasonal and daily variations.https://www.mdpi.com/1996-1073/16/14/5381deep learning modelsshort-term electric load forecastingtime factorvariational mode decomposition |
| spellingShingle | Fachrizal Aksan Vishnu Suresh Przemysław Janik Tomasz Sikorski Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models Energies deep learning models short-term electric load forecasting time factor variational mode decomposition |
| title | Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models |
| title_full | Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models |
| title_fullStr | Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models |
| title_full_unstemmed | Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models |
| title_short | Load Forecasting for the Laser Metal Processing Industry Using VMD and Hybrid Deep Learning Models |
| title_sort | load forecasting for the laser metal processing industry using vmd and hybrid deep learning models |
| topic | deep learning models short-term electric load forecasting time factor variational mode decomposition |
| url | https://www.mdpi.com/1996-1073/16/14/5381 |
| work_keys_str_mv | AT fachrizalaksan loadforecastingforthelasermetalprocessingindustryusingvmdandhybriddeeplearningmodels AT vishnusuresh loadforecastingforthelasermetalprocessingindustryusingvmdandhybriddeeplearningmodels AT przemysławjanik loadforecastingforthelasermetalprocessingindustryusingvmdandhybriddeeplearningmodels AT tomaszsikorski loadforecastingforthelasermetalprocessingindustryusingvmdandhybriddeeplearningmodels |