Data-Driven Machine Learning for Wind Plant Flow Modeling
Abstract
In this study, we introduce a data-driven machine learning framework for improving the accuracy of wind plant flow models by learning turbulence model corrections based on data from higher-fidelity simulations. First, a high-dimensional PDE-constrained optimization problem is solved using gradient-based optimization with adjoints to determine optimal eddy viscosity fields that improve the agreement of a medium-fidelity Reynolds-Averaged Navier Stokes (RANS) model with large eddy simulations (LES). A supervised learning problem is then constructed to find general, predictive representations of the optimal turbulence closure. A machine learning technique using Gaussian process regression is trained to predict the eddy viscosity field based on local RANS flow field information like velocities, pressures, and their gradients. The Gaussian process is trained on LES simulations of a single turbine and implemented in a wind plant simulation with 36 turbines. We show improvement over the baseline RANS model with the machine learning correction, and demonstrate the ability to provide accurate confidence levels for the corrections that enable future uncertainty quantification studies.
- Authors:
-
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Massachusetts Inst. of Technology (MIT), Cambridge, MA (United States)
- Publication Date:
- Research Org.:
- National Renewable Energy Lab. (NREL), Golden, CO (United States)
- Sponsoring Org.:
- USDOE Office of Energy Efficiency and Renewable Energy (EERE), Wind and Water Technologies Office (EE-4W)
- OSTI Identifier:
- 1463077
- Report Number(s):
- NREL/JA-2C00-71454
Journal ID: ISSN 1742-6588; TRN: US1902254
- Grant/Contract Number:
- AC36-08GO28308
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Physics. Conference Series
- Additional Journal Information:
- Journal Volume: 1037; Journal ID: ISSN 1742-6588
- Publisher:
- IOP Publishing
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 17 WIND ENERGY; artificial intelligence; constrained optimization; Gaussian distribution; Gaussian noise (electronic); large eddy simulation; Navier Stokes equations; plant shutdowns; torque; turbines; turbulence models; viscosity
Citation Formats
King, Ryan N., Adcock, Christine, Annoni, Jennifer, and Dykes, Katherine L. Data-Driven Machine Learning for Wind Plant Flow Modeling. United States: N. p., 2018.
Web. doi:10.1088/1742-6596/1037/7/072004.
King, Ryan N., Adcock, Christine, Annoni, Jennifer, & Dykes, Katherine L. Data-Driven Machine Learning for Wind Plant Flow Modeling. United States. https://doi.org/10.1088/1742-6596/1037/7/072004
King, Ryan N., Adcock, Christine, Annoni, Jennifer, and Dykes, Katherine L. Tue .
"Data-Driven Machine Learning for Wind Plant Flow Modeling". United States. https://doi.org/10.1088/1742-6596/1037/7/072004. https://www.osti.gov/servlets/purl/1463077.
@article{osti_1463077,
title = {Data-Driven Machine Learning for Wind Plant Flow Modeling},
author = {King, Ryan N. and Adcock, Christine and Annoni, Jennifer and Dykes, Katherine L.},
abstractNote = {In this study, we introduce a data-driven machine learning framework for improving the accuracy of wind plant flow models by learning turbulence model corrections based on data from higher-fidelity simulations. First, a high-dimensional PDE-constrained optimization problem is solved using gradient-based optimization with adjoints to determine optimal eddy viscosity fields that improve the agreement of a medium-fidelity Reynolds-Averaged Navier Stokes (RANS) model with large eddy simulations (LES). A supervised learning problem is then constructed to find general, predictive representations of the optimal turbulence closure. A machine learning technique using Gaussian process regression is trained to predict the eddy viscosity field based on local RANS flow field information like velocities, pressures, and their gradients. The Gaussian process is trained on LES simulations of a single turbine and implemented in a wind plant simulation with 36 turbines. We show improvement over the baseline RANS model with the machine learning correction, and demonstrate the ability to provide accurate confidence levels for the corrections that enable future uncertainty quantification studies.},
doi = {10.1088/1742-6596/1037/7/072004},
journal = {Journal of Physics. Conference Series},
number = ,
volume = 1037,
place = {United States},
year = {Tue Jun 19 00:00:00 EDT 2018},
month = {Tue Jun 19 00:00:00 EDT 2018}
}
Web of Science