skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Data-driven wind turbine wake modeling via probabilistic machine learning

Journal Article · · Neural Computing and Applications

Wind farm design primarily depends on the variability of the wind turbine wake flows to the atmospheric wind conditions and the interaction between wakes. Physics-based models that capture the wake flow field with high-fidelity are computationally very expensive to perform layout optimization of wind farms, and, thus, data-driven reduced-order models can represent an efficient alternative for simulating wind farms. In this work, we use real-world light detection and ranging (LiDAR) measurements of wind-turbine wakes to construct predictive surrogate models using machine learning. Specifically, we first demonstrate the use of deep autoencoders to find a low-dimensional latent space that gives a computationally tractable approximation of the wake LiDAR measurements. Then, we learn the mapping between the parameter space and the (latent space) wake flow fields using a deep neural network. Additionally, we also demonstrate the use of a probabilistic machine learning technique, namely, Gaussian process modeling, to learn the parameter-space-latent-space mapping in addition to the epistemic and aleatoric uncertainty in the data. Finally, to cope with training large datasets, we demonstrate the use of variational Gaussian process models that provide a tractable alternative to the conventional Gaussian process models for large datasets. Furthermore, we introduce the use of active learning to adaptively build and improve a conventional Gaussian process model predictive capability. Overall, we find that our approach provides accurate approximations of the wind-turbine wake flow field that can be queried at an orders-of-magnitude cheaper cost than those generated with high-fidelity physics-based simulations.

Research Organization:
Argonne National Laboratory (ANL), Argonne, IL (United States)
Sponsoring Organization:
USDOE Office of Science (SC); USDOE Office of Science - Office of Advanced Scientific Computing Research (ASCR); Argonne National Laboratory - Laboratory Directed Research and Development (LDRD); National Science Foundation (NSF)
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1890486
Journal Information:
Neural Computing and Applications, Vol. 34, Issue 8
Country of Publication:
United States
Language:
English

References (39)

Universal approximation bounds for superpositions of a sigmoidal function journal May 1993
Quantifying the Impact of Wind Turbine Wakes on Power Output at Offshore Wind Farms journal August 2010
A new analytical model for wind-turbine wakes journal October 2014
Variational Inference: A Review for Statisticians journal July 2016
A survey of modelling methods for high-fidelity wind farm simulations using large eddy simulation
  • Breton, S. -P.; Sumner, J.; Sørensen, J. N.
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 375, Issue 2091 https://doi.org/10.1098/rsta.2016.0097
journal March 2017
An advanced hybrid deep adversarial autoencoder for parameterized nonlinear fluid flow modelling journal December 2020
A numerical study of the effects of atmospheric and wake turbulence on wind turbine dynamics journal January 2012
Active Learning with Statistical Models journal January 1996
Aeroelastic load validation in wake conditions using nacelle-mounted lidar measurements journal January 2020
Classes of Nonseparable, Spatio-Temporal Stationary Covariance Functions journal December 1999
Approximation by superpositions of a sigmoidal function journal December 1989
Quantification of power losses due to wind turbine wake interactions through SCADA, meteorological and wind LiDAR data: Power losses due to wake interactions through SCADA, met and LiDAR data journal June 2017
Analytical modelling of wind speed deficit in large offshore wind farms journal January 2006
Convolutional neural network based hierarchical autoencoder for nonlinear mode decomposition of fluid field data journal September 2020
Bayesian Data Analysis book June 1995
Volumetric Lidar Scanning of Wind Turbine Wakes under Convective and Neutral Atmospheric Stability Regimes journal October 2014
Parabolic RANS solver for low-computational-cost simulations of wind turbine wakes: Parabolic RANS solver for low-computational-cost simulations of wind turbine wakes journal December 2017
LiSBOA (LiDAR Statistical Barnes Objective Analysis) for optimal design of lidar scans and retrieval of wind statistics – Part 1: Theoretical framework journal March 2021
An experimental and numerical study of the atmospheric stability impact on wind turbine wakes: Experimental and numerical study of the atmospheric stability impact on wake journal December 2015
Reduced-order modeling of advection-dominated systems with recurrent neural networks and convolutional autoencoders journal March 2021
Cluster analysis of wind turbine wakes measured through a scanning Doppler wind LiDAR conference January 2021
Large Eddy Simulation of wind farm aerodynamics: A review journal October 2014
Nonlinear mode decomposition with convolutional neural networks for fluid dynamics journal November 2019
Wind-Turbine and Wind-Farm Flows: A Review journal September 2019
Empirical Assessment of Deep Gaussian Process Surrogate Models for Engineering Problems journal January 2021
Deep Gaussian Process Enabled Surrogate Models for Aerodynamic Flows conference January 2020
Koopman-Based Approach to Nonintrusive Reduced Order Modeling: Application to Aerodynamic Shape Optimization and Uncertainty Propagation journal March 2020
Koopman-Based Approach to Nonintrusive Projection-Based Reduced-Order Modeling with Black-Box High-Fidelity Models journal October 2018
Enhanced data efficiency using deep neural networks and Gaussian processes for aerodynamic design optimization journal April 2021
Machine learning for nonintrusive model order reduction of the parametric inviscid transonic flow past an airfoil journal April 2020
The Design and Analysis of Computer Experiments book January 2003
One‐way mesoscale‐microscale coupling for simulating a wind farm in North Texas: Assessment against SCADA and LiDAR data journal March 2020
Mesoscale to microscale wind farm flow modeling and evaluation: Mesoscale to Microscale Wind Farm Models
  • Sanz Rodrigo, Javier; Chávez Arroyo, Roberto Aurelio; Moriarty, Patrick
  • Wiley Interdisciplinary Reviews: Energy and Environment, Vol. 6, Issue 2 https://doi.org/10.1002/wene.214
journal August 2016
Data analysis and simulation of the Lillgrund wind farm journal November 2020
Grand challenges in the science of wind energy journal October 2019
A dynamic masking technique for particle image velocimetry using convolutional autoencoders journal July 2020
Reduced order model using convolutional auto-encoder with self-attention journal July 2021
Optimal tuning of engineering wake models through lidar measurements journal January 2020
LiDAR measurements for an onshore wind farm: Wake variability for different incoming wind speeds and atmospheric stability regimes journal December 2019