The power performance and the wind velocity field of an onshore wind farm are predicted with machine learning models and the pseudo‐2D RANS model, then assessed against SCADA data. The wind farm under investigation is one of the sites involved with the American WAKE experimeNt (AWAKEN). The performed simulations enable predictions of the power capture at the farm and turbine levels while providing insights into the effects on power capture associated with wake interactions that operating upstream turbines induce, as well as the variability caused by atmospheric stability. The machine learning models show improved accuracy compared to the pseudo‐2D RANS model in the predictions of turbine power capture and farm power capture with roughly half the normalized error. The machine learning models also entail lower computational costs upon training. Further, the machine learning models provide predictions of the wind turbulence intensity at the turbine level for different wind and atmospheric conditions with very good accuracy, which is difficult to achieve through RANS modeling. Additionally, farm‐to‐farm interactions are noted, with adverse impacts on power predictions from both models.
- Award ID(s):
- 1705837
- NSF-PAR ID:
- 10385133
- Date Published:
- Journal Name:
- Journal of Renewable and Sustainable Energy
- Volume:
- 14
- Issue:
- 2
- ISSN:
- 1941-7012
- Page Range / eLocation ID:
- 023301
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
Abstract -
null (Ed.)This work focuses on the optimization of performance and profitability of a wind farm carried out by means of an economic model and Reynolds-Averaged Navier-Stokes (RANS) simulations of wind turbine wakes. Axisymmetric RANS simulations of isolated wind turbine wakes are leveraged with a quadratic super-positioning model to estimate wake interactions within wind farms. The resulting velocity field is used with an actuator disk model to predict power production from each turbine in the wind farm. Design optimization is performed by considering a site in North Texas, whose wind resource statistics are obtained from a meteorological tower. The RANS solver provides capabilities to simulate different incoming wind turbulence intensities and, hence, the wind farm optimization is performed by taking the daily cycle of the atmospheric stability into account. The objective functional of the optimization problem is the levelized cost of energy (LCoE) encompassing capital cost, operation and maintenance costs, land cost and annual power production. At the first level of the optimization problem, the wind farm gross capacity is determined by considering three potential turbine types with different rated power. Subsequently, the optimal wind farm layout is estimated by varying the uniform spacing between consecutive turbine rows. It is found that increasing turbine rated power, the wind farm profitability is enhanced. Substituting a wind farm of 24 turbines of 2.3-MW rated power with 18, 3-MW turbines could reduce the LCoE of about 1.56 $/MWh, while maintaining a similar gross capacity factor. The optimization of the spacing between turbine rows was found to be sensitive to the land cost. For a land cost of 0.05 $/m2, the layout could be designed with a spacing between 6 to 15 rotor diameters without any significant effect on the LCoE, while an increased land cost of 0.1 $/m2 leads to an optimal spacing of about 6 rotor diameters.more » « less
-
null (Ed.)Abstract. Engineering wake models provide the invaluable advantage to predict wind turbine wakes, power capture, and, in turn, annual energy production for an entire wind farm with very low computational costs compared to higher-fidelity numerical tools. However, wake and power predictions obtained with engineering wake models can be insufficiently accurate for wind farm optimization problems due to the ad hoc tuning of the model parameters, which are typically strongly dependent on the characteristics of the site and power plant under investigation. In this paper, lidar measurements collected for individual turbine wakes evolving over a flat terrain are leveraged to perform optimal tuning of the parameters of four widely used engineering wake models. The average wake velocity fields, used as a reference for the optimization problem, are obtained through a cluster analysis of lidar measurements performed under a broad range of turbine operative conditions, namely rotor thrust coefficients, and incoming wind characteristics, namely turbulence intensity at hub height. The sensitivity analysis of the optimally tuned model parameters and the respective physical interpretation are presented. The performance of the optimally tuned engineering wake models is discussed, while the results suggest that the optimally tuned Bastankhah and Ainslie wake models provide very good predictions of wind turbine wakes. Specifically, the Bastankhah wake model should be tuned only for the far-wake region, namely where the wake velocity field can be well approximated with a Gaussian profile in the radial direction. In contrast, the Ainslie model provides the advantage of using as input an arbitrary near-wake velocity profile, which can be obtained through other wake models, higher-fidelity tools, or experimental data. The good prediction capabilities of the Ainslie model indicate that the mixing-length model is a simple yet efficient turbulence closure to capture effects of incoming wind and wake-generated turbulence on the wake downstream evolution and predictions of turbine power yield.more » « less
-
null (Ed.)Wind turbine wakes are responsible for power losses and added fatigue loads of wind turbines. Providing capabilities to predict accurately wind-turbine wakes for different atmospheric conditions and turbine settings with low computational requirements is crucial for the optimization of wind-farm layout, and for improving wind-turbine controls aiming to increase annual energy production (AEP) and reduce the levelized cost of energy (LCOE) for wind power plants. In this work, wake measurements collected with a scanning Doppler wind Li- DAR for broad ranges of the atmospheric static stability regime and incoming wind speed are processed through K-means clustering. For computational feasibility, the cluster analysis is performed on a low-dimensional embedding of the collected data, which is obtained through proper orthogonal decomposition (POD). After data compression, we perform K-means of the POD modes to identify cluster centers and corresponding members from the LiDAR data. The different cluster centers allow us to visualize wake variability over ranges of atmospheric, wind, and turbine parameters. The results show that accurate mapping of the wake variability can be achieved with K-means clustering, which represents an initial step to develop data-driven wake models for accurate and low-computational-cost simulations of wind farms.more » « less
-
The Weather Research and Forecasting (WRF) Model has been extensively used for wind energy applications, and current releases include a scheme that can be applied to examine the effects of wind turbine arrays on the atmospheric flow and electricity generation from wind turbines. Herein we present a high-resolution simulation using two different wind farm parameterizations: 1) the “Fitch” parameterization that is included in WRF releases and 2) the recently developed Explicit Wake Parameterization (EWP) scheme. We compare the schemes using a single yearlong simulation for a domain centered on the highest density of current turbine deployments in the contiguous United States (Iowa). Pairwise analyses are applied to diagnose the downstream wake effects and impact of wind turbine arrays on near-surface climate conditions. On average, use of the EWP scheme results in small-magnitude wake effects within wind farm arrays and faster recovery of full WT array wakes. This in turn leads to smaller impacts on near-surface climate variables and reduced array–array interactions, which at a systemwide scale lead to summertime capacity factors (i.e., the electrical power produced relative to nameplate installed capacity) that are 2%–3% higher than those from the more commonly applied Fitch parameterization. It is currently not possible to make recommendations with regard to which wind farm parameterization exhibits higher fidelity or to draw inferences with regard to whether the relative performance may vary with prevailing climate conditions and/or wind turbine deployment configuration. However, the sensitivities documented herein to the wind farm parameterization are of sufficient magnitude to potentially influence wind turbine array siting decisions. Thus, our research findings imply high value in undertaking combined long-term high-fidelity observational studies in support of model validation and verification.