Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models
Achieving relatively high-accuracy short-term wind speed forecasting estimates is a precondition for the construction and grid-connected operation of wind power forecasting systems for wind farms. Currently, most research is focused on the structure of forecasting models and does not consider the se...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2017-10-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/10/10/1522 |
| _version_ | 1798039876574117888 |
|---|---|
| author | Hui Wang Jingxuan Sun Jianbo Sun Jilong Wang |
| author_facet | Hui Wang Jingxuan Sun Jianbo Sun Jilong Wang |
| author_sort | Hui Wang |
| collection | DOAJ |
| description | Achieving relatively high-accuracy short-term wind speed forecasting estimates is a precondition for the construction and grid-connected operation of wind power forecasting systems for wind farms. Currently, most research is focused on the structure of forecasting models and does not consider the selection of input variables, which can have significant impacts on forecasting performance. This paper presents an input variable selection method for wind speed forecasting models. The candidate input variables for various leading periods are selected and random forests (RF) is employed to evaluate the importance of all variable as features. The feature subset with the best evaluation performance is selected as the optimal feature set. Then, kernel-based extreme learning machine is constructed to evaluate the performance of input variables selection based on RF. The results of the case study show that by removing the uncorrelated and redundant features, RF effectively extracts the most strongly correlated set of features from the candidate input variables. By finding the optimal feature combination to represent the original information, RF simplifies the structure of the wind speed forecasting model, shortens the training time required, and substantially improves the model’s accuracy and generalization ability, demonstrating that the input variables selected by RF are effective. |
| first_indexed | 2024-04-11T21:59:43Z |
| format | Article |
| id | doaj.art-9ee3a77932504ee79c5e92015773ed89 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-04-11T21:59:43Z |
| publishDate | 2017-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-9ee3a77932504ee79c5e92015773ed892022-12-22T04:01:00ZengMDPI AGEnergies1996-10732017-10-011010152210.3390/en10101522en10101522Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting ModelsHui Wang0Jingxuan Sun1Jianbo Sun2Jilong Wang3School of Economics and Management, North China Electric Power University, Changping District, Beijing 102206, ChinaThe Second High School Attached to Beijing Normal University, Xi Cheng District, Beijing 100088, ChinaSchool of Economics and Management, North China Electric Power University, Changping District, Beijing 102206, ChinaSchool of Economics and Management, North China Electric Power University, Changping District, Beijing 102206, ChinaAchieving relatively high-accuracy short-term wind speed forecasting estimates is a precondition for the construction and grid-connected operation of wind power forecasting systems for wind farms. Currently, most research is focused on the structure of forecasting models and does not consider the selection of input variables, which can have significant impacts on forecasting performance. This paper presents an input variable selection method for wind speed forecasting models. The candidate input variables for various leading periods are selected and random forests (RF) is employed to evaluate the importance of all variable as features. The feature subset with the best evaluation performance is selected as the optimal feature set. Then, kernel-based extreme learning machine is constructed to evaluate the performance of input variables selection based on RF. The results of the case study show that by removing the uncorrelated and redundant features, RF effectively extracts the most strongly correlated set of features from the candidate input variables. By finding the optimal feature combination to represent the original information, RF simplifies the structure of the wind speed forecasting model, shortens the training time required, and substantially improves the model’s accuracy and generalization ability, demonstrating that the input variables selected by RF are effective.https://www.mdpi.com/1996-1073/10/10/1522random forests (RF)feature selectioninput variables selectionkernel-based extreme learning machineshort-term wind speed forecasting |
| spellingShingle | Hui Wang Jingxuan Sun Jianbo Sun Jilong Wang Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models Energies random forests (RF) feature selection input variables selection kernel-based extreme learning machine short-term wind speed forecasting |
| title | Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models |
| title_full | Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models |
| title_fullStr | Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models |
| title_full_unstemmed | Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models |
| title_short | Using Random Forests to Select Optimal Input Variables for Short-Term Wind Speed Forecasting Models |
| title_sort | using random forests to select optimal input variables for short term wind speed forecasting models |
| topic | random forests (RF) feature selection input variables selection kernel-based extreme learning machine short-term wind speed forecasting |
| url | https://www.mdpi.com/1996-1073/10/10/1522 |
| work_keys_str_mv | AT huiwang usingrandomforeststoselectoptimalinputvariablesforshorttermwindspeedforecastingmodels AT jingxuansun usingrandomforeststoselectoptimalinputvariablesforshorttermwindspeedforecastingmodels AT jianbosun usingrandomforeststoselectoptimalinputvariablesforshorttermwindspeedforecastingmodels AT jilongwang usingrandomforeststoselectoptimalinputvariablesforshorttermwindspeedforecastingmodels |