中文摘要：

风电机组在实际运行时,受尾流效应和迟滞效应等因素的影响,场内机组运行状态并不相同,风电场采用传统的单机表征模型可能会产生较大误差。该文基于风电场实测运行数据,以风电机组具有相近运行点为机群划分原则,提出一种基于免疫离群数据和敏感初始中心的K-means算法的风电场机群划分方法。首先,针对风电场实测运行数据含有离群数据的问题,基于实测样本分布密度分析,对实测数据进行离群数据处理,免疫离群数据的干扰。其次,传统K-means算法对初始聚类中心的选取是随机的,划分结果容易陷入局部最优,基于改进的最大最小距离法对初始机群中心进行优化选择,免疫机群划分结果对初始机群中心随机选取的敏感性。最后,通过对某实际风电场的仿真分析,验证了所提机群划分方法的有效性,所建立的风电场等值模型能够较准确地反映风电场并网点的动态特性,模型的精确性有了较大的提高。

英文摘要：

Influenced by the park effect and wake effect, the operational points of all wind turbines in the wind farm are not the same and the one machine equivalent model is not applicable. In order to aggregate wind turbines in complex terrain or irregular layout, the clustering approach for wind farm based on the K-means clustering algorithm for wind farm based on immune-outlier data and immune-sensitive initial center. Firstly, considering the fact that the outliers were existed in the measured operating data of wind turbines, the data processing was performed to immune the outliers. Secondly, the traditional K-means algorithm was sensitive to the initial center and was easily getting to the trap of a local solution. To immune the sensitiveness, the improved max-min distance means was adopted to benefit the optimization of initial cluster centers. Finally, an actual wind farm was employed to the clustering and the dynamic simulation for the wind farm. Results show that the proposed multi-machine representation model can reflect the dynamic response of the wind farm more accurately. The proposed clustering method for wind farm is effective for power system simulation.