Wind Farm Power Production and Fatigue Load Optimization Through Wake Steering

Wake steering has proven potential to increase wind farm production. However, this control strategy prioritizes the maximum power without considering the effects of fatigue load, a remaining life indicator on a wind turbine component. Reducing fatigue loads is one of the most important goals of wind farm control, especially for long-established wind farms. Therefore, it is crucial to consider the fatigue load when optimizing the yaw angles. This paper proposes a multi-objective wake steering control strategy to balance power production and fatigue load. Firstly, a power production model based on Gauss-Curl Hybrid (GCH) wake model is introduced to estimate the farm power. Secondly, a fatigue load prediction model is proposed based on Gaussian Process Regression (GPR). Finally, the Particle Swarm Optimization (PSO) method is adopted to optimize the yaw offset by considering the trade-off between power production and fatigue load. The proposed balancing strategy shows an increase in power generation by 16% compared to the baseline strategy (Greedy strategy) while reducing the average and maximum fatigue load by 12% and 10%, respectively.