Wake modeling of wind turbines using machine learning

Abstract In the paper, a novel framework that employs the machine learning and CFD (computational fluid dynamics) simulation to develop new wake velocity and turbulence models with high accuracy and good efficiency is proposed to improve the turbine wake predictions. An ANN (artificial neural network) model based on the back-propagation (BP) algorithm is designed to build the underlying spatial relationship between the inflow conditions and the three-dimensional wake flows. To save the computational cost, a reduced-order turbine model ADM-R (actuator disk model with rotation), is incorporated into RANS (Reynolds-averaged Navier-Stokes equations) simulations coupled with a modified k - e turbulence model to provide big datasets of wake flow for training, testing, and validation of the ANN model. The numerical framework of RANS/ADM-R simulations is validated by a standalone Vestas V80 2 MW wind turbine and NTNU wind tunnel test of double aligned turbines. In the ANN-based wake model, the inflow wind speed and turbulence intensity at hub height are selected as input variables, while the spatial velocity deficit and added turbulence kinetic energy (TKE) in wake field are taken as output variables. The ANN-based wake model is first deployed to a standalone turbine, and then the spatial wake characteristics and power generation of an aligned 8-turbine row as representation of Horns Rev wind farm are also validated against Large Eddy Simulations (LES) and field measurement. The results of ANN-based wake model show good agreement with the numerical simulations and measurement data, indicating that the ANN is capable of establishing the complex spatial relationship between inflow conditions and the wake flows. The machine learning techniques can remarkably improve the accuracy and efficiency of wake predictions.

[1]  R. Barthelmie,et al.  Investigation and Validation of Wind Turbine Wake Models , 2008 .

[2]  C. Masson,et al.  An extended k–ε model for turbulent flow through horizontal-axis wind turbines , 2008 .

[3]  Chi Yan,et al.  Wind turbine wakes: from numerical modeling to machine learning , 2018 .

[4]  Gregor Giebel,et al.  Data-driven Wake Modelling for Reduced Uncertainties in short-term Possible Power Estimation , 2018, Journal of Physics: Conference Series.

[5]  Pierre-Elouan Réthoré,et al.  Wind Turbine Wake in Atmospheric Turbulence , 2009 .

[6]  Fernando Porté-Agel,et al.  Modeling turbine wakes and power losses within a wind farm using LES: An application to the Horns Rev offshore wind farm , 2015 .

[7]  J. Templeton,et al.  Reynolds averaged turbulence modelling using deep neural networks with embedded invariance , 2016, Journal of Fluid Mechanics.

[8]  F. Porté-Agel,et al.  Atmospheric Turbulence Effects on Wind-Turbine Wakes: An LES Study , 2012 .

[9]  N. Troldborg,et al.  An improved k‐ ϵ model applied to a wind turbine wake in atmospheric turbulence , 2015 .

[10]  Mergen H. Ghayesh,et al.  Modelling of wind turbine wake using large eddy simulation , 2018 .

[11]  Paul van der Laan,et al.  Wind turbine wake models developed at the Technical University of Denmark: A review , 2016 .

[12]  Hui Li,et al.  Prediction model of velocity field around circular cylinder over various Reynolds numbers by fusion convolutional neural networks based on pressure on the cylinder , 2018 .

[13]  Agnimitra Biswas,et al.  An Artificial Neural Network Based Methodology for the Prediction of Power & Torque Coefficients of a Two Bladed Airfoil Shaped H-Rotor , 2009 .

[14]  Fernando Porté-Agel,et al.  Large-eddy simulation of atmospheric boundary layer flow through wind turbines and wind farms , 2011 .

[15]  Lars Sætran,et al.  Blind Test 2 calculations for two in-line model wind turbines where the downstream turbine operates at various rotational speeds , 2014 .

[16]  P. Argyle,et al.  Modelling turbulence intensity within a large offshore wind farm , 2018, Wind Energy.

[17]  A. Crespo,et al.  Comparison of turbulence models for the computational fluid dynamics simulation of wind turbine wakes in the atmospheric boundary layer , 2011 .

[18]  Jan Michael Simon Bartl,et al.  Wake Measurements Behind an Array of Two Model Wind Turbines , 2012 .

[19]  F. Porté-Agel,et al.  Simulation of Turbulent Flow Inside and Above Wind Farms: Model Validation and Layout Effects , 2012, Boundary-Layer Meteorology.

[20]  Brendan D. Tracey,et al.  A Machine Learning Strategy to Assist Turbulence Model Development , 2015 .

[21]  Goran Nenadic,et al.  Machine learning methods for wind turbine condition monitoring: A review , 2019, Renewable Energy.

[22]  Rajeev Gupta,et al.  Application of artificial neural network for performance evaluation of vertical axis wind turbine rotor , 2016 .

[23]  Cristina H. Amon,et al.  A Novel Wake Interaction Model for Wind Farm Layout Optimization , 2014 .

[24]  Kai Wei,et al.  Numerical study on the stochastic response of a long-span sea-crossing bridge subjected to extreme nonlinear wave loads , 2019, Engineering Structures.

[25]  F. Porté-Agel,et al.  A new analytical model for wind-turbine wakes , 2013 .

[26]  F. Porté-Agel,et al.  Large-Eddy Simulation of Wind-Turbine Wakes: Evaluation of Turbine Parametrisations , 2011 .

[27]  F. Porté-Agel,et al.  Analytical Modeling of Wind Farms: A New Approach for Power Prediction , 2016 .

[28]  Yongqian Liu,et al.  A two-dimensional model based on the expansion of physical wake boundary for wind-turbine wakes , 2019, Applied Energy.

[29]  Farschad Torabi,et al.  Modeling of horizontal axis wind turbine wakes in Horns Rev offshore wind farm using an improved actuator disc model coupled with computational fluid dynamic , 2018, Energy Conversion and Management.

[30]  P. Zeng,et al.  Wake model for horizontal-axis wind and hydrokinetic turbines in yawed conditions , 2019, Applied Energy.

[31]  Ashraf S. Hussein,et al.  MODELING AND SIMULATION OF MICRO-SCALE WIND FARMS USING HIGH PERFORMANCE COMPUTING , 2012 .

[32]  E. S. Politis,et al.  Modelling and Measuring Flow and Wind Turbine Wakes in Large Wind Farms Offshore , 2009, Renewable Energy.

[33]  Seref Sagiroglu,et al.  Training multilayered perceptrons for pattern recognition: a comparative study of four training algorithms , 2001 .