Journal cover Journal topic
Wind Energy Science The interactive open-access journal of the European Academy of Wind Energy
Journal topic
Preprints
https://doi.org/10.5194/wes-2019-58
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/wes-2019-58
© Author(s) 2019. This work is distributed under
the Creative Commons Attribution 4.0 License.

Submitted as: research article 25 Sep 2019

Submitted as: research article | 25 Sep 2019

Review status
A revised version of this preprint was accepted for the journal WES and is expected to appear here in due course.

Decreasing Wind Speed Extrapolation Error via Domain-Specific Feature Extraction and Selection

Daniel Vassallo1, Raghavendra Krishnamurthy1,2, and Harindra J. S. Fernando1 Daniel Vassallo et al.
  • 1University of Notre Dame, Indiana, USA
  • 2Pacific Northwest National Laboratory, Washington, USA

Abstract. Model uncertainty is a significant challenge in the wind energy industry and can lead to mischaracterization of millions of dollars' worth of wind resource. Machine learning methods, notably deep artificial neural networks (ANNs), are capable of modeling turbulent and chaotic systems and offer a promising tool that can be used to produce high-accuracy wind speed forecasts and extrapolations. This paper quantifies the role of domain knowledge on ANN wind speed extrapolation accuracy using data collected using profiling lidars over three field campaigns. A series of 11 meteorological features are used as ANN inputs and the resulting output accuracy is compared with that of a simple power law extrapolation. It is found that normalized inputs, namely turbulence intensity, normalized current wind speed, and normalized previous wind speed, are the features that most reliably improve ANN accuracy, providing up to a 52 % increase in extrapolation accuracy over the power law predictions. The volume of input data is also deemed important for achieving robust results. One test case is analyzed in-depth using dimensional and non-dimensional features, showing that feature normalization drastically improves network accuracy and robustness for uncommon atmospheric cases.

Daniel Vassallo et al.

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Daniel Vassallo et al.

Daniel Vassallo et al.

Viewed

Total article views: 447 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
336 105 6 447 15 21
  • HTML: 336
  • PDF: 105
  • XML: 6
  • Total: 447
  • BibTeX: 15
  • EndNote: 21
Views and downloads (calculated since 25 Sep 2019)
Cumulative views and downloads (calculated since 25 Sep 2019)

Viewed (geographical distribution)

Total article views: 281 (including HTML, PDF, and XML) Thereof 280 with geography defined and 1 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved

No saved metrics found.

Discussed

No discussed metrics found.
Latest update: 29 May 2020
Publications Copernicus
Download
Short summary
Model error and uncertainty is a challenge in the wind energy industry, potentially leading to mischaracterization of millions of dollars' worth of wind resource. This paper combines meteorological knowledge with machine learning techniques, specifically artificial neural networks (ANNs), to better extrapolate wind speeds. It is found that ANNs can reduce power law extrapolation error by up to 52 % while simultaneously reducing uncertainty. A test case is shown to help decipher the ANN results.
Model error and uncertainty is a challenge in the wind energy industry, potentially leading to...
Citation