Optimization of wind turbine yaw angles in a wind farm using a three-dimensional yawed wake model

Wind-Farm Power Tracking Via Preview-Based Robust Reinforcement Learning

“…A commonly-used wind farm control strategy is to establish analytical or parametric wind-farm models firstly and then design controllers based on them. Following this pattern, many model-based methods have been proposed to optimize the power generation of wind farms [1], [2]. However, due to high system complexities, modelbased wind farm control methods suffer from uncertainties and unmodelled dynamics, and thus in practice they could have quite different performance compared with theoretical results.…”

“…The proposed PR-DRL method addresses this challenging problem by employing only the system's input & output data without requiring any analytical model. It overcomes the drawbacks of model-based wind farm control methods [1], [2], [9], [12], [13], [14], [15], [16] that are sensitive to modelling errors and uncertainties.…”

Wind Farm Power Generation Control Via Double-Network-Based Deep Reinforcement Learning

“…The induction control can also mitigate wake effects and enhance generation efficiency by adjusting the turbines' axial induction factors or alternatively controlling power/thrust coefficients. A yaw-angle optimization strategy was introduced in [12] for improving the power gains. An induction control method was described in [13] by taking the induction factor as the control variable.…”

Fast Yaw Optimization for Wind Plant Wake Steering Using Boolean Yaw Angles

“…In addition to being nonintuitive, this optimization problem involves complex interactions because slightly adjusting the yaw angle of a single turbine can have effects that propagate to the rest of the wind turbines in the plant-both in their power production and in the wakes that they produce. To solve this optimization problem, the yaw angles of each wind turbine are either formulated as continuous between the upper and lower bounds (Gebraad et al, 2014;Fleming et al, 2016b;Gebraad et al, 2017) or with finely discretized yaw angle selections (Dar et al, 2016;Dou et al, 2020). The problem is then solved with a gradientbased (Fleming et al, 2016b;Gebraad et al, 2017) or gradient-free (Gebraad et al, 2014;Dar et al, 2016;Dou et al, 2020) optimization algorithm that determines the best combination of yaw angles in the wind power plant.…”

“…To solve this optimization problem, the yaw angles of each wind turbine are either formulated as continuous between the upper and lower bounds (Gebraad et al, 2014;Fleming et al, 2016b;Gebraad et al, 2017) or with finely discretized yaw angle selections (Dar et al, 2016;Dou et al, 2020). The problem is then solved with a gradientbased (Fleming et al, 2016b;Gebraad et al, 2017) or gradient-free (Gebraad et al, 2014;Dar et al, 2016;Dou et al, 2020) optimization algorithm that determines the best combination of yaw angles in the wind power plant. While effective and relatively efficient for a one-off wind power plant analysis, there are some shortcomings to this problem formulation.…”