A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection
A hybrid feature selection (HFS) algorithm to obtain the optimal feature set to attain optimal forecast accuracy for short-term load forecasting (STLF) problems is proposed in this paper. The HFS employs an elitist genetic algorithm (EGA) and random forest method, which is embedded in the load forec...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-01-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/16/2/867 |
| _version_ | 1797443143856029696 |
|---|---|
| author | Ankit Kumar Srivastava Ajay Shekhar Pandey Mohamad Abou Houran Varun Kumar Dinesh Kumar Saurabh Mani Tripathi Sivasankar Gangatharan Rajvikram Madurai Elavarasan |
| author_facet | Ankit Kumar Srivastava Ajay Shekhar Pandey Mohamad Abou Houran Varun Kumar Dinesh Kumar Saurabh Mani Tripathi Sivasankar Gangatharan Rajvikram Madurai Elavarasan |
| author_sort | Ankit Kumar Srivastava |
| collection | DOAJ |
| description | A hybrid feature selection (HFS) algorithm to obtain the optimal feature set to attain optimal forecast accuracy for short-term load forecasting (STLF) problems is proposed in this paper. The HFS employs an elitist genetic algorithm (EGA) and random forest method, which is embedded in the load forecasting algorithm for online feature selection (FS). Using selected features, the performance of the forecaster was tested to signify the utility of the proposed methodology. For this, a day-ahead STLF using the M5P forecaster (a comprehensive forecasting approach using the regression tree concept) was implemented with FS and without FS (WoFS). The performance of the proposed forecaster (with FS and WoFS) was compared with the forecasters based on J48 and Bagging. The simulation was carried out in MATLAB and WEKA software. Through analyzing short-term load forecasts for the Australian electricity markets, evaluation of the proposed approach indicates that the input feature selected by the HFS approach consistently outperforms forecasters with larger feature sets. |
| first_indexed | 2024-03-09T12:51:48Z |
| format | Article |
| id | doaj.art-46511612d1ac4ae380df3e9ba0fe4517 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-09T12:51:48Z |
| publishDate | 2023-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-46511612d1ac4ae380df3e9ba0fe45172023-11-30T22:05:14ZengMDPI AGEnergies1996-10732023-01-0116286710.3390/en16020867A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature SelectionAnkit Kumar Srivastava0Ajay Shekhar Pandey1Mohamad Abou Houran2Varun Kumar3Dinesh Kumar4Saurabh Mani Tripathi5Sivasankar Gangatharan6Rajvikram Madurai Elavarasan7Electrical Engineering Department, Dr. Rammanohar Lohia Avadh University, Ayodhya 224001, IndiaDepartment of Electrical Engineering, Kamla Nehru Institute of Technology, Sultanpur 228118, IndiaSchool of Electrical Engineering, Xi’an Jiaotong University, Xi’an 710049, ChinaDepartment of Electrical Engineering, Kamla Nehru Institute of Technology, Sultanpur 228118, IndiaElectrical Engineering Department, Dr. Rammanohar Lohia Avadh University, Ayodhya 224001, IndiaDepartment of Electrical Engineering, Kamla Nehru Institute of Technology, Sultanpur 228118, IndiaElectrical & Electronics Engineering Department, Thiagarajar College of Engineering, Madurai 625015, IndiaSchool of Information Technology and Electrical Engineering, The University of Queensland, St. Lucia, QLD 4072, AustraliaA hybrid feature selection (HFS) algorithm to obtain the optimal feature set to attain optimal forecast accuracy for short-term load forecasting (STLF) problems is proposed in this paper. The HFS employs an elitist genetic algorithm (EGA) and random forest method, which is embedded in the load forecasting algorithm for online feature selection (FS). Using selected features, the performance of the forecaster was tested to signify the utility of the proposed methodology. For this, a day-ahead STLF using the M5P forecaster (a comprehensive forecasting approach using the regression tree concept) was implemented with FS and without FS (WoFS). The performance of the proposed forecaster (with FS and WoFS) was compared with the forecasters based on J48 and Bagging. The simulation was carried out in MATLAB and WEKA software. Through analyzing short-term load forecasts for the Australian electricity markets, evaluation of the proposed approach indicates that the input feature selected by the HFS approach consistently outperforms forecasters with larger feature sets.https://www.mdpi.com/1996-1073/16/2/867confidence intervalelitist genetic algorithmfeature selectionshort-term load forecastingM5P forecastermachine learning |
| spellingShingle | Ankit Kumar Srivastava Ajay Shekhar Pandey Mohamad Abou Houran Varun Kumar Dinesh Kumar Saurabh Mani Tripathi Sivasankar Gangatharan Rajvikram Madurai Elavarasan A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection Energies confidence interval elitist genetic algorithm feature selection short-term load forecasting M5P forecaster machine learning |
| title | A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection |
| title_full | A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection |
| title_fullStr | A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection |
| title_full_unstemmed | A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection |
| title_short | A Day-Ahead Short-Term Load Forecasting Using M5P Machine Learning Algorithm along with Elitist Genetic Algorithm (EGA) and Random Forest-Based Hybrid Feature Selection |
| title_sort | day ahead short term load forecasting using m5p machine learning algorithm along with elitist genetic algorithm ega and random forest based hybrid feature selection |
| topic | confidence interval elitist genetic algorithm feature selection short-term load forecasting M5P forecaster machine learning |
| url | https://www.mdpi.com/1996-1073/16/2/867 |
| work_keys_str_mv | AT ankitkumarsrivastava adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT ajayshekharpandey adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT mohamadabouhouran adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT varunkumar adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT dineshkumar adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT saurabhmanitripathi adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT sivasankargangatharan adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT rajvikrammaduraielavarasan adayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT ankitkumarsrivastava dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT ajayshekharpandey dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT mohamadabouhouran dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT varunkumar dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT dineshkumar dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT saurabhmanitripathi dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT sivasankargangatharan dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection AT rajvikrammaduraielavarasan dayaheadshorttermloadforecastingusingm5pmachinelearningalgorithmalongwithelitistgeneticalgorithmegaandrandomforestbasedhybridfeatureselection |