File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1016/j.renene.2023.119240
- Scopus: eid_2-s2.0-85171328358
- WOS: WOS:001080031700001
- Find via
Supplementary
- Citations:
- Appears in Collections:
Article: A data-driven layout optimization framework of large-scale wind farms based on machine learning
| Title | A data-driven layout optimization framework of large-scale wind farms based on machine learning |
|---|---|
| Authors | |
| Keywords | Artificial neural networks Layout optimization Machine learning Offshore wind farm Wake model |
| Issue Date | 6-Sep-2023 |
| Publisher | Elsevier |
| Citation | Renewable Energy, 2023, v. 218 How to Cite? |
| Abstract | This paper presents a data-driven wind farm layout optimization framework that uses a machine learning wake model that considers physical control stages. The machine learning wake model is trained using well-validated Computational Fluid Dynamics (CFD) simulation data, and consists of thousands of sub-models, each of which is an artificial neural network (ANN) wake model. The ANN wake models are trained separately for low-speed and high-speed inflows to ensure high accuracy of the predictions, with less than 2% error compared to CFD simulations. The accuracy and efficiency of the framework are validated, and the results show better agreement with CFD simulation than an analytical wake model developed in recent years. A parametric study on the number of wind turbines in the Horns Rev wind farm demonstrates that more wind turbines can be added with a minor decrease in average power, with more even and staggered layouts. Under full-wake uniform inflow, the selected analytical wake model exhibits a power prediction error of 5%–8%, while the differences between optimal layouts searched by different wake models range from 2% to 8%. When introducing a wider range of inflow direction sectors, the discrepancy between optimal layout performances decreases. |
| Persistent Identifier | http://hdl.handle.net/10722/339259 |
| ISSN | 2023 Impact Factor: 9.0 2023 SCImago Journal Rankings: 1.923 |
| ISI Accession Number ID |
| DC Field | Value | Language |
|---|---|---|
| dc.contributor.author | Yang, Kun | - |
| dc.contributor.author | Deng, Xiaowei | - |
| dc.contributor.author | Ti, Zilong | - |
| dc.contributor.author | Yang, Shanghui | - |
| dc.contributor.author | Huang, Senbin | - |
| dc.contributor.author | Wang, Yuhang | - |
| dc.date.accessioned | 2024-03-11T10:35:12Z | - |
| dc.date.available | 2024-03-11T10:35:12Z | - |
| dc.date.issued | 2023-09-06 | - |
| dc.identifier.citation | Renewable Energy, 2023, v. 218 | - |
| dc.identifier.issn | 0960-1481 | - |
| dc.identifier.uri | http://hdl.handle.net/10722/339259 | - |
| dc.description.abstract | <p>This paper presents a data-driven <a href="https://www.sciencedirect.com/topics/engineering/wind-turbine" title="Learn more about wind farm from ScienceDirect's AI-generated Topic Pages">wind farm</a> layout optimization framework that uses a machine learning wake model that considers physical control stages. The machine learning wake model is trained using well-validated Computational Fluid Dynamics (CFD) simulation data, and consists of thousands of sub-models, each of which is an <a href="https://www.sciencedirect.com/topics/engineering/artificial-neural-network" title="Learn more about artificial neural network from ScienceDirect's AI-generated Topic Pages">artificial neural network</a> (ANN) wake model. The ANN wake models are trained separately for low-speed and high-speed inflows to ensure high accuracy of the predictions, with less than 2% error compared to CFD simulations. The accuracy and efficiency of the framework are validated, and the results show better agreement with CFD simulation than an analytical wake model developed in recent years. A <a href="https://www.sciencedirect.com/topics/engineering/parametric-study" title="Learn more about parametric study from ScienceDirect's AI-generated Topic Pages">parametric study</a> on the number of wind turbines in the Horns Rev <a href="https://www.sciencedirect.com/topics/engineering/wind-turbine" title="Learn more about wind farm from ScienceDirect's AI-generated Topic Pages">wind farm</a> demonstrates that more wind turbines can be added with a minor decrease in average power, with more even and staggered layouts. Under full-wake uniform inflow, the selected analytical wake model exhibits a power prediction error of 5%–8%, while the differences between optimal layouts searched by different wake models range from 2% to 8%. When introducing a wider range of inflow direction sectors, the discrepancy between optimal layout performances decreases.<br></p> | - |
| dc.language | eng | - |
| dc.publisher | Elsevier | - |
| dc.relation.ispartof | Renewable Energy | - |
| dc.subject | Artificial neural networks | - |
| dc.subject | Layout optimization | - |
| dc.subject | Machine learning | - |
| dc.subject | Offshore wind farm | - |
| dc.subject | Wake model | - |
| dc.title | A data-driven layout optimization framework of large-scale wind farms based on machine learning | - |
| dc.type | Article | - |
| dc.identifier.doi | 10.1016/j.renene.2023.119240 | - |
| dc.identifier.scopus | eid_2-s2.0-85171328358 | - |
| dc.identifier.volume | 218 | - |
| dc.identifier.eissn | 1879-0682 | - |
| dc.identifier.isi | WOS:001080031700001 | - |
| dc.identifier.issnl | 0960-1481 | - |