How Generalizable is a Machine-Learning Approach for Modeling Hub-Height Turbulence Intensity?

Nicola Bodini, Julie Lundquist, Hannah Livingston, Pat Moriarty

Research output: Contribution to journalArticlepeer-review

1 Scopus Citations

Abstract

Hub-height turbulence intensity is essential for a variety of wind energy applications. However, simulating it is a challenging task. Simple analytical models have been proposed in the literature, but they all come with significant limitations. Even state-of-the-art numerical weather prediction models, such as the Weather Research and Forecasting model, currently struggle to predict hub-height turbulence intensity. Here, we propose a machine-learning-based approach to predict hub-height turbulence intensity from other hub-height and ground-level atmospheric measurements, using observations from the Perdigão field campaign and the Southern Great Plains atmospheric observatory. We consider a random forest regression model, which we validate first at the site used for training and then under a more robust round-robin approach, and compare its performance to a multivariate linear regression. The random forest successfully outperforms the linear regression in modeling hub-height turbulence intensity, with a normalized root-mean-square error as low as 0.014 when using 30-minute average data. In order to achieve such low root-mean-square error values, the knowledge of hub-height turbulence kinetic energy (which can instead be modeled in the Weather Research and Forecasting model) is needed. Interestingly, we find that the performance of the random forest generalizes well when considering a round-robin validation (i.e., when the algorithm is trained at one site such as Perdigão or Southern Great Plains) and then applied to model hub-height turbulence intensity at the other location.

Original languageAmerican English
Article numberArticle No. 022028
Number of pages11
JournalJournal of Physics: Conference Series
Volume2265
Issue number2
DOIs
StatePublished - 2 Jun 2022
Event2022 Science of Making Torque from Wind, TORQUE 2022 - Delft, Netherlands
Duration: 1 Jun 20223 Jun 2022

Bibliographical note

Publisher Copyright:
© Published under licence by IOP Publishing Ltd.

NREL Publication Number

  • NREL/JA-5000-82312

Keywords

  • awaken
  • machine learning
  • turbulence intensity

Fingerprint

Dive into the research topics of 'How Generalizable is a Machine-Learning Approach for Modeling Hub-Height Turbulence Intensity?'. Together they form a unique fingerprint.

Cite this