中文摘要：

为准确分析风电场的动态特性,借助同调等值法的思想,提出了一种基于改进遗传KM聚类算法的机群划分方法。此方法通过构造有效的适应度函数,结合K-means聚类算法和遗传聚类算法的优点,以实测风速数据为分群指标,对风电场进行机群划分。将同群风电机组等值为1台风电机组,建立风电场动态等值模型,并与传统单机等值模型和K-means等值模型进行了比较分析。以某风电场为例进行的仿真验证结果表明,采用所提方法建立的等值模型能够较为准确地反映风电场的动态响应特性,从而提高等值模型的精确性。

英文摘要：

For accurately analyzing the dynamic characteristics of wind farm, with the thought of the coherency method, a method of wind turbines grouping is proposed based on improved genetic K-means （IGKM）algorithm. By constructing an effective fitness function,and combining the advantages of the K-means clustering algorithm and genetic algorithm, a method of wind turbines grouping is obtained. The measured wind speed data is adopted as a cluster-dependent index. An improved genetic K-means algorithm is used to divide wind turbines into groups and the wind turbine generators in same group are equivalent to a wind generator,hence,the dynamically equivalent model of wind farm is built. And it is also analyzed and compared with the traditional single equivalent model and the equivalent model based on K-means algorithm. The results of example simulation for an actual wind farm show that the method of wind turbines grouping can accurately reflect the dynamic response characteristics of wind farm,and improve the accuracy of equivalent model.