Automatic Identification of Wind Turbine Models using Evolutionary Multiobjective Optimization

William La Cava, Kourosh Danai, Lee Spector, Paul Fleming, Alan Wright, Matthew Lackner

Research output: Contribution to journalArticlepeer-review

36 Scopus Citations

Abstract

Modern industrial-scale wind turbines are nonlinear systems that operate in turbulent environments. As such, it is difficult to characterize their behavior accurately across a wide range of operating conditions using physically meaningful models. Customarily, the models derived from wind turbine data are in 'black box' format, lacking in both conciseness and intelligibility. To address these deficiencies, we use a recently developed symbolic regression method to identify models of a modern horizontal-axis wind turbine in symbolic form. The method uses evolutionary multiobjective optimization to produce succinct dynamic models from operational data while making minimal assumptions about the physical properties of the system. We compare the models produced by this method to models derived by other methods according to their estimation capacity and evaluate the trade-off between model intelligibility and accuracy. Several succinct models are found that predict wind turbine behavior as well as or better than more complex alternatives derived by other methods. We interpret the new models to show that they often contain intelligible estimates of real process physics.

Original languageAmerican English
Pages (from-to)892-902
Number of pages11
JournalRenewable Energy
Volume87
Issue number2
DOIs
StatePublished - 1 Mar 2016

Bibliographical note

Publisher Copyright:
© 2015 Elsevier Ltd.

NREL Publication Number

  • NREL/JA-5000-65025

Keywords

  • Genetic programming
  • Multiobjective optimization
  • System identification
  • Wind energy

Fingerprint

Dive into the research topics of 'Automatic Identification of Wind Turbine Models using Evolutionary Multiobjective Optimization'. Together they form a unique fingerprint.

Cite this