Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids
Nowadays, electric load forecasting through a data analytic approach has become one of the most active and emerging research areas. It provides future consumption patterns of electric load. Since there are large fluctuations in both electricity production and use, it is a difficult task to achieve a...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/1/276 |
| _version_ | 1797625920191725568 |
|---|---|
| author | Sajawal ur Rehman Khan Israa Adil Hayder Muhammad Asif Habib Mudassar Ahmad Syed Muhammad Mohsin Farrukh Aslam Khan Kainat Mustafa |
| author_facet | Sajawal ur Rehman Khan Israa Adil Hayder Muhammad Asif Habib Mudassar Ahmad Syed Muhammad Mohsin Farrukh Aslam Khan Kainat Mustafa |
| author_sort | Sajawal ur Rehman Khan |
| collection | DOAJ |
| description | Nowadays, electric load forecasting through a data analytic approach has become one of the most active and emerging research areas. It provides future consumption patterns of electric load. Since there are large fluctuations in both electricity production and use, it is a difficult task to achieve a balance between electric load and demand. By analyzing past electric consumption records to estimate the upcoming electricity load, the issue of fluctuating behavior can be resolved. In this study, a framework for feature selection, extraction, and regression is put forward to carry out the electric load prediction. The feature selection phase uses a combination of extreme gradient boosting (<i>XGB</i>) and random forest (<i>RF</i>) to determine the significance of each feature. Redundant features in the feature extraction approach are removed by applying recursive feature elimination (RFE). We propose an enhanced support vector machine (ESVM) and an enhanced convolutional neural network (ECNN) for the regression component. Hyperparameters of both the proposed approaches are set using the random search (RS) technique. To illustrate the effectiveness of our proposed strategies, a comparison is also performed between the state-of-the-art approaches and our proposed techniques. In addition, we perform statistical analyses to prove the significance of our proposed approaches. Simulation findings illustrate that our proposed approaches ECNN and ESVM achieve higher accuracies of 98.83% and 98.7%, respectively. |
| first_indexed | 2024-03-11T10:03:18Z |
| format | Article |
| id | doaj.art-cc471f7033534dcbae337a2de9355991 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-11T10:03:18Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-cc471f7033534dcbae337a2de93559912023-11-16T15:16:58ZengMDPI AGEnergies1996-10732022-12-0116127610.3390/en16010276Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart GridsSajawal ur Rehman Khan0Israa Adil Hayder1Muhammad Asif Habib2Mudassar Ahmad3Syed Muhammad Mohsin4Farrukh Aslam Khan5Kainat Mustafa6Department of Computer Science, National Textile University, Faisalabad 37610, PakistanMinistry of Education, General Directorate of Vocational Education, Department of Scientific Affairs, Baghdad 10053, IraqDepartment of Computer Science, National Textile University, Faisalabad 37610, PakistanDepartment of Computer Science, National Textile University, Faisalabad 37610, PakistanDepartment of Computer Science, COMSATS University Islamabad, Islamabad 45550, PakistanCenter of Excellence in Information Assurance (CoEIA), King Saud University, Riyadh 11653, Saudi ArabiaDepartment of Computer Science, Virtual University of Pakistan, Lahore 55150, PakistanNowadays, electric load forecasting through a data analytic approach has become one of the most active and emerging research areas. It provides future consumption patterns of electric load. Since there are large fluctuations in both electricity production and use, it is a difficult task to achieve a balance between electric load and demand. By analyzing past electric consumption records to estimate the upcoming electricity load, the issue of fluctuating behavior can be resolved. In this study, a framework for feature selection, extraction, and regression is put forward to carry out the electric load prediction. The feature selection phase uses a combination of extreme gradient boosting (<i>XGB</i>) and random forest (<i>RF</i>) to determine the significance of each feature. Redundant features in the feature extraction approach are removed by applying recursive feature elimination (RFE). We propose an enhanced support vector machine (ESVM) and an enhanced convolutional neural network (ECNN) for the regression component. Hyperparameters of both the proposed approaches are set using the random search (RS) technique. To illustrate the effectiveness of our proposed strategies, a comparison is also performed between the state-of-the-art approaches and our proposed techniques. In addition, we perform statistical analyses to prove the significance of our proposed approaches. Simulation findings illustrate that our proposed approaches ECNN and ESVM achieve higher accuracies of 98.83% and 98.7%, respectively.https://www.mdpi.com/1996-1073/16/1/276smart gridfeature extractionfeature selectionload forecastingrandom forestrecursive feature eliminator |
| spellingShingle | Sajawal ur Rehman Khan Israa Adil Hayder Muhammad Asif Habib Mudassar Ahmad Syed Muhammad Mohsin Farrukh Aslam Khan Kainat Mustafa Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids Energies smart grid feature extraction feature selection load forecasting random forest recursive feature eliminator |
| title | Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids |
| title_full | Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids |
| title_fullStr | Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids |
| title_full_unstemmed | Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids |
| title_short | Enhanced Machine-Learning Techniques for Medium-Term and Short-Term Electric-Load Forecasting in Smart Grids |
| title_sort | enhanced machine learning techniques for medium term and short term electric load forecasting in smart grids |
| topic | smart grid feature extraction feature selection load forecasting random forest recursive feature eliminator |
| url | https://www.mdpi.com/1996-1073/16/1/276 |
| work_keys_str_mv | AT sajawalurrehmankhan enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids AT israaadilhayder enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids AT muhammadasifhabib enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids AT mudassarahmad enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids AT syedmuhammadmohsin enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids AT farrukhaslamkhan enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids AT kainatmustafa enhancedmachinelearningtechniquesformediumtermandshorttermelectricloadforecastinginsmartgrids |