Multi-Task Optimisation-Based Yaw Control For Wind Farm Power Generation

Wind farms, designed based on certain assumed wind speed and direction patterns, may experience sub-optimal power generation in changing weather conditions due to turbine yaw misalignment. Accordingly, optimal control of turbine yaw angles to maximize overall power generation across all turbines in the farm, while mitigating wake effects caused by upstream turbines, becomes essential. It is typically formulated as a model predictive control (MPC) problem. A key module in this MPC problem is rolling horizon optimization, which is often nonlinear and non-convex, posing challenges to traditional mathematical programming solvers. This work reformulates rolling horizon optimization into a multi-task optimization (MTO) problem, where each component task is defined as maximizing the power generation of an individual turbine while accounting for wake effects from its upstream turbines. All component tasks are co-solved, with inter-task knowledge transfer and reuse, to enhance total power generation. We customize an existing evolutionary MTO method to solve the problem, using yaw angle adjustments as the means of knowledge transfer. The proposed approach is tested on the Penmanshiel wind farm layout with 14 turbines, outperforming the commonly used traditional solver.