Journal cover Journal topic
Wind Energy Science The interactive open-access journal of the European Academy of Wind Energy
Journal topic
Discussion papers
https://doi.org/10.5194/wes-2020-2
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-2020-2
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 14 Jan 2020

Submitted as: research article | 14 Jan 2020

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Wind Energy Science (WES).

The importance of round-robin validation when assessing machine-learning-based vertical extrapolation of wind speeds

Nicola Bodini and Mike Optis Nicola Bodini and Mike Optis
  • National Renewable Energy Laboratory, Golden, Colorado, USA

Abstract. The extrapolation of wind speeds measured at a meteorological mast to wind turbine hub heights is a key component in a bankable wind farm energy assessment and a significant source of uncertainty. Industry-standard methods for extrapolation include the power law and logarithmic profile. The emergence of machine-learning applications in wind energy has led to several studies demonstrating substantial improvements in vertical extrapolation accuracy in machine-learning methods over these conventional power law and logarithmic profile methods. In all cases, these studies assess relative model performance at a measurement site where, critically, the machine-learning algorithm requires knowledge of the hub-height wind speeds in order to train the model. This prior knowledge provides fundamental advantages to the site-specific machine-learning model over the power law and log profile, which, by contrast, are not highly tuned to hub-height measurements but rather can generalize to any site. Furthermore, there is no practical benefit in applying a machine-learning model at a site where hub-height winds are known; rather, its performance at nearby locations (i.e., across a wind farm site) without hub-height measurements is of most practical interest. To more fairly and practically compare machine-learning-based extrapolation to standard approaches, we implemented a round-robin extrapolation model comparison, in which a random forest machine-learning model is trained and evaluated at different sites and then compared against the power law and logarithmic profile. We consider 20 months of lidar and sonic anemometer data collected at four sites between 50–100 kilometers apart in the central United States. We find that the random forest outperforms the standard extrapolation approaches, especially when incorporating surface measurements as inputs to include the influence of atmospheric stability. When compared at a single site (the traditional comparison approach), the machine-learning improvement in mean absolute error was 28 % and 23 % over the power law and logarithmic profile, respectively. Using the round-robin approach proposed here, this improvement drops to 19 % and 14 %, respectively. These latter values better represent practical model performance, and we conclude that round-robin validation should be the standard for machine-learning-based, wind-speed extrapolation methods.

Nicola Bodini and Mike Optis
Interactive discussion
Status: open (until 28 Feb 2020)
Status: open (until 28 Feb 2020)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Nicola Bodini and Mike Optis
Data sets

SGP dataset - Doppler Lidar (DLAUX) R. Newsom and R. Krishnamurthy https://doi.org/10.5439/1374838

SGP dataset - Eddy Correlation Flux Measurement System (30ECOR) R. Sullivan, M. Pekour, D. Cook, R. Sullivan, and E. Keeler https://doi.org/10.5439/1025039

SGP dataset - Surface Meteorological Instrumentation (MET) J. Kyrouac, M. Ritsche, N. Hickmon, and D. Holdridge https://doi.org/10.5439/1025220

SGP dataset - Carbon Dioxide Flux Measurement Systems (30CO2FLX4M) S. Biraud, D. Billesbach, and S. Chan https://doi.org/10.5439/1025036

Nicola Bodini and Mike Optis
Viewed  
Total article views: 135 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
110 25 0 135 0 0
  • HTML: 110
  • PDF: 25
  • XML: 0
  • Total: 135
  • BibTeX: 0
  • EndNote: 0
Views and downloads (calculated since 14 Jan 2020)
Cumulative views and downloads (calculated since 14 Jan 2020)
Viewed (geographical distribution)  
Total article views: 137 (including HTML, PDF, and XML) Thereof 137 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Cited  
Saved  
No saved metrics found.
Discussed  
No discussed metrics found.
Latest update: 26 Jan 2020
Publications Copernicus
Download
Short summary
An accurate assessment of the wind resource at hub-height is necessary for an efficient and bankable wind farm project. Conventional techniques for wind speed vertical extrapolation include a power law and a logarithmic law. Here, we propose a round-robin validation to assess the benefits that a machine learning-based approach can provide in vertically extrapolating wind speed at a location different from the training site – the most practically useful application for the wind energy industry.
An accurate assessment of the wind resource at hub-height is necessary for an efficient and...
Citation