Preprints
https://doi.org/10.5194/wes-2023-175
https://doi.org/10.5194/wes-2023-175
03 Jan 2024
 | 03 Jan 2024
Status: a revised version of this preprint is currently under review for the journal WES.

Development and validation of a hybrid data-driven model-based wake steering controller and its application at a utility-scale wind plant

Peter Bachant, Peter Ireland, Brian Burrows, Chi Qiao, James Duncan, Danian Zheng, and Mohit Dua

Abstract. Despite the promise of wind farm control through wake steering to reduce wake losses, the deployment of the technology to wind plants has historically been limited to small and simple demonstrations. In this study, we develop and deploy a wake steering control system to 10 turbines within a complex 58 turbine wind plant. A multi-month data collection campaign was used to develop a closed-loop tuning and validation process for the eventual deployment of the system to 165 turbines on this and two neighboring wind plants. The system employs a novel actuation strategy, using absolute nacelle position control instead of yaw sensor offsets, along with a model in the loop performing real-time prediction and optimization. The novel model architecture, which employs data-driven input estimation and calibration of an engineering wake model along with a neural network-based output correction, is examined in a validation framework that tests predictive capabilities in both a dynamic (i.e., time series) and aggregate sense. It is demonstrated that model accuracy can be significantly increased through this architecture, which will facilitate effective wake steering control in plant layouts and atmospheric conditions whose complexities are difficult to resolve using an engineering wake model alone.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Peter Bachant, Peter Ireland, Brian Burrows, Chi Qiao, James Duncan, Danian Zheng, and Mohit Dua

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on wes-2023-175', Anonymous Referee #1, 07 Feb 2024
  • RC2: 'Comments on wes-2023-175', Anonymous Referee #2, 13 Feb 2024
  • AC1: 'Comment on wes-2023-175: Response to RC1', Peter Bachant, 28 Apr 2024
  • AC2: 'Comment on wes-2023-175: Response to RC2', Peter Bachant, 28 Apr 2024
Peter Bachant, Peter Ireland, Brian Burrows, Chi Qiao, James Duncan, Danian Zheng, and Mohit Dua
Peter Bachant, Peter Ireland, Brian Burrows, Chi Qiao, James Duncan, Danian Zheng, and Mohit Dua

Viewed

Total article views: 438 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
344 77 17 438 12 8
  • HTML: 344
  • PDF: 77
  • XML: 17
  • Total: 438
  • BibTeX: 12
  • EndNote: 8
Views and downloads (calculated since 03 Jan 2024)
Cumulative views and downloads (calculated since 03 Jan 2024)

Viewed (geographical distribution)

Total article views: 409 (including HTML, PDF, and XML) Thereof 409 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 23 May 2024
Download
Short summary
Intentional misalignment of upstream turbines in wind plants in order to steer wakes away from downstream turbines has been a topic of research interest for years, but has not yet achieved widespread commercial adoption. We deploy one such wake steering system to a utility-scale wind plant, then create a model to predict plant behavior and enable successful control. We apply calibrations to a physics-based model and use machine learning to correct its outputs to improve predictive capability.
Altmetrics