A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting
Deep learning is increasingly used in short-term load forecasting. However, deep learning models are difficult to train, and adjusting training hyper-parameters takes time and effort. Automated machine learning (AutoML) can reduce human participation in machine learning process and improve the effic...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2022-01-01
|
| Series: | E3S Web of Conferences |
| Subjects: | |
| Online Access: | https://www.e3s-conferences.org/articles/e3sconf/pdf/2022/25/e3sconf_gesd2022_02045.pdf |
| _version_ | 1811179601925242880 |
|---|---|
| author | Meng Zhaorui Xie Xiaozhu Xie Yanqi Sun Jinhua |
| author_facet | Meng Zhaorui Xie Xiaozhu Xie Yanqi Sun Jinhua |
| author_sort | Meng Zhaorui |
| collection | DOAJ |
| description | Deep learning is increasingly used in short-term load forecasting. However, deep learning models are difficult to train, and adjusting training hyper-parameters takes time and effort. Automated machine learning (AutoML) can reduce human participation in machine learning process and improve the efficiency of modelling while ensuring the accuracy of prediction. In this paper, we compare the usage of three AutoML approaches in short-term load forecasting. The experiments on a real-world dataset show that the predictive performance of AutoGluon outperforms that of AutoPytorch and Auto-Keras, according to three performance metrics: MAE, RMSE and MAPE. AutoPytorch and Auto-Keras have similar performance and are not easy to compare. |
| first_indexed | 2024-04-11T06:37:03Z |
| format | Article |
| id | doaj.art-5eed990720c54e27ad57b9cb15c80e1a |
| institution | Directory Open Access Journal |
| issn | 2267-1242 |
| language | English |
| last_indexed | 2024-04-11T06:37:03Z |
| publishDate | 2022-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | E3S Web of Conferences |
| spelling | doaj.art-5eed990720c54e27ad57b9cb15c80e1a2022-12-22T04:39:39ZengEDP SciencesE3S Web of Conferences2267-12422022-01-013580204510.1051/e3sconf/202235802045e3sconf_gesd2022_02045A Comparative Study of AutoML Approaches for Short-Term Electric Load ForecastingMeng Zhaorui0Xie Xiaozhu1Xie Yanqi2Sun Jinhua3School of computer and information engineering, Xiamen University of TechnologySchool of computer and information engineering, Xiamen University of TechnologySchool of computer and information engineering, Xiamen University of TechnologySchool of computer and information engineering, Xiamen University of TechnologyDeep learning is increasingly used in short-term load forecasting. However, deep learning models are difficult to train, and adjusting training hyper-parameters takes time and effort. Automated machine learning (AutoML) can reduce human participation in machine learning process and improve the efficiency of modelling while ensuring the accuracy of prediction. In this paper, we compare the usage of three AutoML approaches in short-term load forecasting. The experiments on a real-world dataset show that the predictive performance of AutoGluon outperforms that of AutoPytorch and Auto-Keras, according to three performance metrics: MAE, RMSE and MAPE. AutoPytorch and Auto-Keras have similar performance and are not easy to compare.https://www.e3s-conferences.org/articles/e3sconf/pdf/2022/25/e3sconf_gesd2022_02045.pdfautomated machine learningload forecastingdeep learning |
| spellingShingle | Meng Zhaorui Xie Xiaozhu Xie Yanqi Sun Jinhua A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting E3S Web of Conferences automated machine learning load forecasting deep learning |
| title | A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting |
| title_full | A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting |
| title_fullStr | A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting |
| title_full_unstemmed | A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting |
| title_short | A Comparative Study of AutoML Approaches for Short-Term Electric Load Forecasting |
| title_sort | comparative study of automl approaches for short term electric load forecasting |
| topic | automated machine learning load forecasting deep learning |
| url | https://www.e3s-conferences.org/articles/e3sconf/pdf/2022/25/e3sconf_gesd2022_02045.pdf |
| work_keys_str_mv | AT mengzhaorui acomparativestudyofautomlapproachesforshorttermelectricloadforecasting AT xiexiaozhu acomparativestudyofautomlapproachesforshorttermelectricloadforecasting AT xieyanqi acomparativestudyofautomlapproachesforshorttermelectricloadforecasting AT sunjinhua acomparativestudyofautomlapproachesforshorttermelectricloadforecasting AT mengzhaorui comparativestudyofautomlapproachesforshorttermelectricloadforecasting AT xiexiaozhu comparativestudyofautomlapproachesforshorttermelectricloadforecasting AT xieyanqi comparativestudyofautomlapproachesforshorttermelectricloadforecasting AT sunjinhua comparativestudyofautomlapproachesforshorttermelectricloadforecasting |