Against the background that the wind direction and speed in an offshore wind farm are relatively stable and the wake effect has a significant impact on the power of the wind farm, the yaw angles and active powers among the units are comprehensively coordinated to improve the aerodynamic coupling among the units and increase the sum of the active powers of each unit. A wake model considering yaw is presented, which overcomes the problem of difficulty in optimizing the power of the wind farm caused by the discontinuity at the boundary of the classical wake model. Then an active power optimization model of the wind farm with the yaw angles and induction factors of the units as adjustment means is established. Subsequently, based on the wake propagation path, the units are grouped, and the overall optimization problem of the wind farm is transformed into the internal optimization problems of each group, reducing the number of optimization objects and the scale of the problem. Focusing on combining online simulation and machine learning techniques, a solution method for the internal power optimization problem of each group is proposed. Finally, the optimization results are set as the reference active power and reference yaw angle of the units, and each unit operates accordingly. This scheme has a small computational cost, does not require additional computational resources for the wind farm control system, and has no special requirements for the communication environment. At the same time, the simulation results show that the proposed scheme can effectively increase the active power of the offshore wind farm and improve the economic benefits of the wind farm.
以海上风电场风向和风速较稳定,尾流效应对风电场功率影响明显为背景,综合协调机组间偏航角、有功功率,改善机组间气动耦合,提高各机组有功功率之和。给出了考虑偏航的尾流模型,克服了经典尾流模型边界处不连续导致风电场功率优化困难的问题。然后建立以机组偏航角和诱导因子为调节手段的风电场有功功率优化模型。继而,基于尾流传播路径,对机组进行分群,将风电场整场优化问题转化为各群内部优化问题,减少优化对象数,降低问题规模。重点结合在线仿真和机器学习技术,提出各群内部功率优化问题求解方法。最后将优化结果整定为机组参考有功功率和参考偏航角,各机组据此运行。该方案计算开销小,无需额外增加风电场控制系统计算资源,对通信环境无特殊要求,同时,仿真结果表明,提出的方案能有效提升海上风电场有功功率,提高风电场经济效益。