This article investigates the optimization of yaw control inputs of a nine-turbine wind farm. The wind farm is simulated using the high-fidelity simulator SOWFA. The optimization is performed with a modifier adaptation scheme based on Gaussian processes. Modifier adaptation corrects for the mismatch between plant and model and helps to converge to the actual plan optimum. In the case study the modifier adaptation approach is compared with the Bayesian optimization approach. Moreover, the use of two different covariance functions in the Gaussian process regression is discussed. Practical recommendations concerning the data preparation and application of the approach are given. It is shown that both the modifier adaptation and the Bayesian optimization approach can improve the power production with overall smaller yaw misalignments in comparison to the Gaussian wake model.
Argonne National Laboratory（阿贡国家实验室）；The University of Texas at Dallas（德克萨斯大学达拉斯分校）
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…
The University of Texas at Dallas（德克萨斯大学达拉斯分校）；Argonne National Laboratory（阿贡国家实验室）
Different machine learning (ML) models are trained on SCADA and meteorological data collected at an onshore wind farm and then assessed in terms of fidelity and accuracy for predictions of wind speed, turbulence intensity, and power capture at the turbine and wind farm levels for different wind and atmospheric conditions. ML methods for data quality control and pre-processing are applied to the data set under investigation and found to outperform standard statistical methods. A hybrid model, comprised of a linear interpolation model, Gaussian process, deep neural network (DNN), and support vec…
In computational fluid dynamics, there is an inevitable trade off between accuracy and computational cost. In this work, a novel multi-fidelity deep generative model is introduced for the surrogate modeling of high-fidelity turbulent flow fields given the solution of a computationally inexpensive but inaccurate low-fidelity solver. The resulting surrogate is able to generate physically accurate turbulent realizations at a computational cost magnitudes lower than that of a high-fidelity simulation. The deep generative model developed is a conditional invertible neural network, built with normal…
This work presents a combined feedforward-feedback wake redirection framework for wind farm control. The FLORIS wake model, a control-oriented steady-state wake model is used to calculate optimal yaw angles for a given wind farm layout and atmospheric condition. The optimal yaw angles, which maximize the total power output, are applied to the wind farm. Further, the lidar-based closed-loop wake redirection concept is used to realize a local feedback on turbine level. The wake center is estimated from lidar measurements \unit[3]{D} downwind of the wind turbines. The dynamical feedback controlle…
Dynamic induction control is a wind farm flow control strategy that utilises wind turbine thrust variations to accelerate breakdown of the aerodynamic wake and improve downstream turbine performance. However, when floating wind turbines are considered, additional dynamics and challenges appear that make optimal control difficult. In this work, we propose an adjoint optimisation framework for non-linear economic model-predictive control, which utilises a novel coupling of an existing aerodynamic wake model to floating platform hydrodynamics. Analysis of the frequency response for the coupled mo…
This paper presents a closed-loop controller for wind farms to provide active power control services using a high-fidelity computational fluid dynamics based wind plant simulator. The proposed design enhances power tracking stability and allows for simple understanding, where each turbine is considered as a pure time-delay system. The paper investigates the control performance with different nominal power distributions in a fully waked condition and limited power availability. Results demonstrate the improvement in power production obtained by closing the control loop, compared to greedy opera…
To provide automatic generation control (AGC) service, wind farms (WFs) are required to control their operation dynamically to track the time-varying power reference. Wake effects impose significant aerodynamic interactions among turbines, which remarkably influence the WF dynamic power production. The nonlinear and high-dimensional nature of dynamic wake model, however, brings extremely high computation complexity and obscure the design of WF controllers. This paper overcomes the control difficulty brought by the dynamic wake model by proposing a novel control-oriented reduced order WF model …
Active power control regulates the total power generated by wind farms with the power consumed on the electricity grid. Due to wake effects, the available power is reduced and turbulence is increased at downstream wind turbines. Such effects lead to a design challenge for wind farm control, where the delicate balance between supply and demand should be maintained, while considering the load balancing in the wind turbine structures. We propose a control architecture based on simple feedback controllers that adjusts the demanded power set points of individual wind turbines to compensate for turb…
