Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network
Short-term load forecasting (STLF) plays an important role in the economic dispatch of power systems. Obtaining accurate short-term load can greatly improve the safety and economy of a power grid operation. In recent years, a large number of short-term load forecasting methods have been proposed. Ho...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-08-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/13/16/4121 |
| _version_ | 1797559292056829952 |
|---|---|
| author | Shaoqian Pei Hui Qin Liqiang Yao Yongqi Liu Chao Wang Jianzhong Zhou |
| author_facet | Shaoqian Pei Hui Qin Liqiang Yao Yongqi Liu Chao Wang Jianzhong Zhou |
| author_sort | Shaoqian Pei |
| collection | DOAJ |
| description | Short-term load forecasting (STLF) plays an important role in the economic dispatch of power systems. Obtaining accurate short-term load can greatly improve the safety and economy of a power grid operation. In recent years, a large number of short-term load forecasting methods have been proposed. However, how to select the optimal feature set and accurately predict multi-step ahead short-term load still faces huge challenges. In this paper, a hybrid feature selection method is proposed, an Improved Long Short-Term Memory network (ILSTM) is applied to predict multi-step ahead load. This method firstly takes the influence of temperature, humidity, dew point, and date type on the load into consideration. Furthermore, the maximum information coefficient is used for the preliminary screening of historical load, and Max-Relevance and Min-Redundancy (mRMR) is employed for further feature selection. Finally, the selected feature set is considered as input of the model to perform multi-step ahead short-term load prediction by the Improved Long Short-Term Memory network. In order to verify the performance of the proposed model, two categories of contrast methods are applied: (1) comparing the model with hybrid feature selection and the model which does not adopt hybrid feature selection; (2) comparing different models including Long Short-Term Memory network (LSTM), Gated Recurrent Unit (GRU), and Support Vector Regression (SVR) using hybrid feature selection. The result of the experiments, which were developed during four periods in the Hubei Province, China, show that hybrid feature selection can improve the prediction accuracy of the model, and the proposed model can accurately predict the multi-step ahead load. |
| first_indexed | 2024-03-10T17:43:16Z |
| format | Article |
| id | doaj.art-e8f572ebd4ce4965b1cfcd7fc39dcc24 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T17:43:16Z |
| publishDate | 2020-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-e8f572ebd4ce4965b1cfcd7fc39dcc242023-11-20T09:37:30ZengMDPI AGEnergies1996-10732020-08-011316412110.3390/en13164121Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory NetworkShaoqian Pei0Hui Qin1Liqiang Yao2Yongqi Liu3Chao Wang4Jianzhong Zhou5School of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaSchool of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaChangjiang River Scientific Research Institute of Changjiang Water Resources Commission, Wuhan 430074, ChinaSchool of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaDepartment of Water Resources, China Institute of Water Resources and Hydropower Research, Beijing 100044, ChinaSchool of Hydropower and Information Engineering, Huazhong University of Science and Technology, Wuhan 430074, ChinaShort-term load forecasting (STLF) plays an important role in the economic dispatch of power systems. Obtaining accurate short-term load can greatly improve the safety and economy of a power grid operation. In recent years, a large number of short-term load forecasting methods have been proposed. However, how to select the optimal feature set and accurately predict multi-step ahead short-term load still faces huge challenges. In this paper, a hybrid feature selection method is proposed, an Improved Long Short-Term Memory network (ILSTM) is applied to predict multi-step ahead load. This method firstly takes the influence of temperature, humidity, dew point, and date type on the load into consideration. Furthermore, the maximum information coefficient is used for the preliminary screening of historical load, and Max-Relevance and Min-Redundancy (mRMR) is employed for further feature selection. Finally, the selected feature set is considered as input of the model to perform multi-step ahead short-term load prediction by the Improved Long Short-Term Memory network. In order to verify the performance of the proposed model, two categories of contrast methods are applied: (1) comparing the model with hybrid feature selection and the model which does not adopt hybrid feature selection; (2) comparing different models including Long Short-Term Memory network (LSTM), Gated Recurrent Unit (GRU), and Support Vector Regression (SVR) using hybrid feature selection. The result of the experiments, which were developed during four periods in the Hubei Province, China, show that hybrid feature selection can improve the prediction accuracy of the model, and the proposed model can accurately predict the multi-step ahead load.https://www.mdpi.com/1996-1073/13/16/4121short-term load forecastingMax-Relevance and Min-RedundancyImproved Long Short-Term Memory networkmulti-step ahead loadhybrid feature selection |
| spellingShingle | Shaoqian Pei Hui Qin Liqiang Yao Yongqi Liu Chao Wang Jianzhong Zhou Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network Energies short-term load forecasting Max-Relevance and Min-Redundancy Improved Long Short-Term Memory network multi-step ahead load hybrid feature selection |
| title | Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network |
| title_full | Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network |
| title_fullStr | Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network |
| title_full_unstemmed | Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network |
| title_short | Multi-Step Ahead Short-Term Load Forecasting Using Hybrid Feature Selection and Improved Long Short-Term Memory Network |
| title_sort | multi step ahead short term load forecasting using hybrid feature selection and improved long short term memory network |
| topic | short-term load forecasting Max-Relevance and Min-Redundancy Improved Long Short-Term Memory network multi-step ahead load hybrid feature selection |
| url | https://www.mdpi.com/1996-1073/13/16/4121 |
| work_keys_str_mv | AT shaoqianpei multistepaheadshorttermloadforecastingusinghybridfeatureselectionandimprovedlongshorttermmemorynetwork AT huiqin multistepaheadshorttermloadforecastingusinghybridfeatureselectionandimprovedlongshorttermmemorynetwork AT liqiangyao multistepaheadshorttermloadforecastingusinghybridfeatureselectionandimprovedlongshorttermmemorynetwork AT yongqiliu multistepaheadshorttermloadforecastingusinghybridfeatureselectionandimprovedlongshorttermmemorynetwork AT chaowang multistepaheadshorttermloadforecastingusinghybridfeatureselectionandimprovedlongshorttermmemorynetwork AT jianzhongzhou multistepaheadshorttermloadforecastingusinghybridfeatureselectionandimprovedlongshorttermmemorynetwork |