A novel two-stage data-driven model for ultra-short-term wind speed prediction
Accurate prediction of wind speed and its output power is playing an essential role in the planning and scheduling of wind power grid. This study presents a novel two-stage data-driven model for ultra-short-term wind speed prediction based on the smoothing spline preprocessing (SSP) method and error...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-11-01
|
| Series: | Energy Reports |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2352484722013130 |
| _version_ | 1828011072061177856 |
|---|---|
| author | Weicheng Hu Qingshan Yang Pei Zhang Ziting Yuan Hua-Peng Chen Hongtao Shen Tong Zhou Kunpeng Guo Tian Li |
| author_facet | Weicheng Hu Qingshan Yang Pei Zhang Ziting Yuan Hua-Peng Chen Hongtao Shen Tong Zhou Kunpeng Guo Tian Li |
| author_sort | Weicheng Hu |
| collection | DOAJ |
| description | Accurate prediction of wind speed and its output power is playing an essential role in the planning and scheduling of wind power grid. This study presents a novel two-stage data-driven model for ultra-short-term wind speed prediction based on the smoothing spline preprocessing (SSP) method and error optimization theory (EOT). Firstly, high-resolution wind data observed from 39 wind turbines are collected and transformed according to the proposed SSP method to eliminate the non-Gaussian and non-stationary features. Then, several individual models are introduced to perform multi-step ahead wind speed prediction for the transformed wind data, and the prediction of transformed data should be recovered to wind speed. Finally, these single models are combined based on the proposed EOT theory for multi-step ahead wind speed prediction, and their accuracy and uncertainty are analyzed and compared with other existing models in depth. The results show that the proposed SSP method can reasonably identify non-Gaussian and non-stationary features of the original wind series, and the transformed data are more favorable for prediction. Furthermore, the suggested two-stage data-driven model can reduce prediction errors by 3%–20% compared with other models mentioned in this study, indicating that it is more effective and stable in terms of providing reasonable ultra-short-term wind speed prediction results. |
| first_indexed | 2024-04-10T09:09:41Z |
| format | Article |
| id | doaj.art-350e144638fd4a4bb47bbc0243fe49bd |
| institution | Directory Open Access Journal |
| issn | 2352-4847 |
| language | English |
| last_indexed | 2024-04-10T09:09:41Z |
| publishDate | 2022-11-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Energy Reports |
| spelling | doaj.art-350e144638fd4a4bb47bbc0243fe49bd2023-02-21T05:12:27ZengElsevierEnergy Reports2352-48472022-11-01894679480A novel two-stage data-driven model for ultra-short-term wind speed predictionWeicheng Hu0Qingshan Yang1Pei Zhang2Ziting Yuan3Hua-Peng Chen4Hongtao Shen5Tong Zhou6Kunpeng Guo7Tian Li8Chongqing Key Laboratory of Wind Engineering and Wind Energy Utilization, School of Civil Engineering, Chongqing University, Chongqing, 400044, China; Institute for Smart Transportation Infrastructure, School of Transportation Engineering, East China Jiaotong University, Nanchang, 330013, China; Zhejiang Jiangnan Project Management Co., Ltd., Hangzhou, 310007, China; Corresponding author at: Chongqing Key Laboratory of Wind Engineering and Wind Energy Utilization, School of Civil Engineering, Chongqing University, Chongqing, 400044, China.Chongqing Key Laboratory of Wind Engineering and Wind Energy Utilization, School of Civil Engineering, Chongqing University, Chongqing, 400044, ChinaSchool of Electrical and Automation Engineering, East China Jiaotong University, Nanchang, 330013, ChinaSchool of Civil Engineering and Architecture, Nanchang Jiaotong Institute, Nanchang, 330100, China; Corresponding author.Institute for Smart Transportation Infrastructure, School of Transportation Engineering, East China Jiaotong University, Nanchang, 330013, ChinaPowerChina Sichuan Electric Power Engineering Co., Ltd., Chengdu, 610016, ChinaDepartment of Civil Engineering, School of Engineering, The University of Tokyo, Tokyo, 113-8656, JapanChongqing Key Laboratory of Wind Engineering and Wind Energy Utilization, School of Civil Engineering, Chongqing University, Chongqing, 400044, ChinaChongqing Key Laboratory of Wind Engineering and Wind Energy Utilization, School of Civil Engineering, Chongqing University, Chongqing, 400044, ChinaAccurate prediction of wind speed and its output power is playing an essential role in the planning and scheduling of wind power grid. This study presents a novel two-stage data-driven model for ultra-short-term wind speed prediction based on the smoothing spline preprocessing (SSP) method and error optimization theory (EOT). Firstly, high-resolution wind data observed from 39 wind turbines are collected and transformed according to the proposed SSP method to eliminate the non-Gaussian and non-stationary features. Then, several individual models are introduced to perform multi-step ahead wind speed prediction for the transformed wind data, and the prediction of transformed data should be recovered to wind speed. Finally, these single models are combined based on the proposed EOT theory for multi-step ahead wind speed prediction, and their accuracy and uncertainty are analyzed and compared with other existing models in depth. The results show that the proposed SSP method can reasonably identify non-Gaussian and non-stationary features of the original wind series, and the transformed data are more favorable for prediction. Furthermore, the suggested two-stage data-driven model can reduce prediction errors by 3%–20% compared with other models mentioned in this study, indicating that it is more effective and stable in terms of providing reasonable ultra-short-term wind speed prediction results.http://www.sciencedirect.com/science/article/pii/S2352484722013130Ultra-short-term predictionWind speedSmoothing spline preprocessingError optimization theory |
| spellingShingle | Weicheng Hu Qingshan Yang Pei Zhang Ziting Yuan Hua-Peng Chen Hongtao Shen Tong Zhou Kunpeng Guo Tian Li A novel two-stage data-driven model for ultra-short-term wind speed prediction Energy Reports Ultra-short-term prediction Wind speed Smoothing spline preprocessing Error optimization theory |
| title | A novel two-stage data-driven model for ultra-short-term wind speed prediction |
| title_full | A novel two-stage data-driven model for ultra-short-term wind speed prediction |
| title_fullStr | A novel two-stage data-driven model for ultra-short-term wind speed prediction |
| title_full_unstemmed | A novel two-stage data-driven model for ultra-short-term wind speed prediction |
| title_short | A novel two-stage data-driven model for ultra-short-term wind speed prediction |
| title_sort | novel two stage data driven model for ultra short term wind speed prediction |
| topic | Ultra-short-term prediction Wind speed Smoothing spline preprocessing Error optimization theory |
| url | http://www.sciencedirect.com/science/article/pii/S2352484722013130 |
| work_keys_str_mv | AT weichenghu anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT qingshanyang anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT peizhang anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT zitingyuan anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT huapengchen anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT hongtaoshen anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT tongzhou anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT kunpengguo anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT tianli anoveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT weichenghu noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT qingshanyang noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT peizhang noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT zitingyuan noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT huapengchen noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT hongtaoshen noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT tongzhou noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT kunpengguo noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction AT tianli noveltwostagedatadrivenmodelforultrashorttermwindspeedprediction |