中文摘要：

为了解决传统的k-means算法对初始聚类中心的选择敏感,以及必须事先指定生成簇数目,提出了一种鲁棒的kmeans算法Rk-means。该算法使用改进的MaxMin初始化方法,解决了初始簇中心选择敏感问题。通过对海量用户信息进行关键聚类信息识别,进行自动聚类处理。实验结果表明了算法的有效性和鲁棒性,该算法被应用于电力客户细分,可帮助供电企业做出正确的电力市场营销策略。

英文摘要：

In order to solve the problem that the traditional k-means algorithm is sensitive to the selection of the initial clustering center and the number of clusters is specified in advance,a robust k-means（Rk-means）algorithm is proposed.The improved MaxMin initialization method is used to solve the initial cluster center selection sensitive problem.Through the mass of the user information critical clustering information identification,the automatic clustering is done.The experimental results show that the algorithm is effective and robust,and the algorithm is applied to the power customer segmentation,which can help the power supply enterprises to make the correct power marketing strategy.