基于K均值聚类的光伏电站运行状态模式识别研究.PDFVIP

第44 卷 第 14 期 电力系统保护与控制 Vol.44 No.14 2016 年 7 月 16 日 Power System Protection and Control Jul. 16, 2016 DOI: 10.7667/PSPC151425 基于 K 均值聚类的光伏电站运行状态模式识别研究 杨大勇，葛 琪，董永超，唐云龙，贺衬心 (许继集团有限公司，河南 许昌 461000) 摘要：在阐述光伏电站运行状态模式识别意义的基础上，提取了表征光伏电站运行状态的相关特征参量。基于 K-means 聚类原理，对广东佛山某光伏电站的实际运行数据进行相关数据处理得到相应的特征矩阵。利用 K 均值 算法进行聚类分析，结果表明 K 均值聚类算法在光伏电站运行状态的模式识别上具有良好的聚类综合能力，可有 效解决光伏电站运行状态模式分类处理的复杂性问题，具有重要的理论和应用价值。 关键词：光伏电站；K-means ；特征聚类；模式识别 Research on operation state pattern recognition of PV station based on the principle of K-means clustering YANG Dayong, GE Qi, DONG Yongchao, TANG Yunlong, HE Chenxin (XJ Group Corporation, Xuchang 461000, China) Abstract: Based on expounding the PV power plant state recognition, this paper extracts the relevant characteristics of the operating state of the PV station. Based on the principle of K-means clustering, through the actual operation data processing of a PV station in the city of Foshan, Guangdong Province, the corresponding feature matrix is obtained. Using K-means clustering analysis, the results show that it has important theoretical and applied value not only because the K-means clustering algorithm has a good effective on the pattern recognition of the PV station, but also can effectively solve the complexity problem of the PV station operation mode classification. Key words: PV station; K-means; feature clustering; pattern recognition 设备故障状态对电站运行特征的影响分析；文献 0 引言