Interval model of a wind turbine power curve
The wind turbine power curve model is critical to a wind turbine’s power prediction and performance analysis. However, abnormal data in the training set decrease the prediction accuracy of trained models. This paper proposes a sample average approach-based method to construct an interval model of a...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-11-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1305612/full |
| _version_ | 1827643447339646976 |
|---|---|
| author | Kai Zhou Hao Han Junfen Li Yongjie Wang Wei Tang Fei Han Yulei Li Ruyu Bi Haitao Zhao Lingxiao Jiao |
| author_facet | Kai Zhou Hao Han Junfen Li Yongjie Wang Wei Tang Fei Han Yulei Li Ruyu Bi Haitao Zhao Lingxiao Jiao |
| author_sort | Kai Zhou |
| collection | DOAJ |
| description | The wind turbine power curve model is critical to a wind turbine’s power prediction and performance analysis. However, abnormal data in the training set decrease the prediction accuracy of trained models. This paper proposes a sample average approach-based method to construct an interval model of a wind turbine, which increases robustness against abnormal data and further improves the model accuracy. We compare our proposed methods with the traditional neural network-based and Bayesian neural network-based models in experimental data-based validations. Our model shows better performance in both accuracy and computational time. |
| first_indexed | 2024-03-09T17:54:26Z |
| format | Article |
| id | doaj.art-ac9c00ed485a4ffb8dae6987bd25eaf2 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-03-09T17:54:26Z |
| publishDate | 2023-11-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-ac9c00ed485a4ffb8dae6987bd25eaf22023-11-24T10:30:43ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-11-011110.3389/fenrg.2023.13056121305612Interval model of a wind turbine power curveKai ZhouHao HanJunfen LiYongjie WangWei TangFei HanYulei LiRuyu BiHaitao ZhaoLingxiao JiaoThe wind turbine power curve model is critical to a wind turbine’s power prediction and performance analysis. However, abnormal data in the training set decrease the prediction accuracy of trained models. This paper proposes a sample average approach-based method to construct an interval model of a wind turbine, which increases robustness against abnormal data and further improves the model accuracy. We compare our proposed methods with the traditional neural network-based and Bayesian neural network-based models in experimental data-based validations. Our model shows better performance in both accuracy and computational time.https://www.frontiersin.org/articles/10.3389/fenrg.2023.1305612/fullabnormal detectiondata cleaningwind power predictionprediction accuracystochastic optimization |
| spellingShingle | Kai Zhou Hao Han Junfen Li Yongjie Wang Wei Tang Fei Han Yulei Li Ruyu Bi Haitao Zhao Lingxiao Jiao Interval model of a wind turbine power curve Frontiers in Energy Research abnormal detection data cleaning wind power prediction prediction accuracy stochastic optimization |
| title | Interval model of a wind turbine power curve |
| title_full | Interval model of a wind turbine power curve |
| title_fullStr | Interval model of a wind turbine power curve |
| title_full_unstemmed | Interval model of a wind turbine power curve |
| title_short | Interval model of a wind turbine power curve |
| title_sort | interval model of a wind turbine power curve |
| topic | abnormal detection data cleaning wind power prediction prediction accuracy stochastic optimization |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1305612/full |
| work_keys_str_mv | AT kaizhou intervalmodelofawindturbinepowercurve AT haohan intervalmodelofawindturbinepowercurve AT junfenli intervalmodelofawindturbinepowercurve AT yongjiewang intervalmodelofawindturbinepowercurve AT weitang intervalmodelofawindturbinepowercurve AT feihan intervalmodelofawindturbinepowercurve AT yuleili intervalmodelofawindturbinepowercurve AT ruyubi intervalmodelofawindturbinepowercurve AT haitaozhao intervalmodelofawindturbinepowercurve AT lingxiaojiao intervalmodelofawindturbinepowercurve |