基于改进密度峰值优化全局K-means的风电典型场景聚类方法  

Typical wind power scene clustering method based on improved density peak optimization global K-means

作　　者：陈将宏 胡佳慧 时康昊 郑新超 敖志强 Chen Jianghong;Hu Jiahui;Shi Kanghao;Zheng Xinchao;Ao Zhiqiang(College of Electrical Engineering and New Energy,China Three Gorges University,Yichang 443002,China;Hubei Provincial Engineering Technology Research Center for Transmission Line,Yichang 443002,China)

机构地区：[1]三峡大学电气与新能源学院,宜昌443002 [2]湖北省输电线路工程技术研究中心,宜昌443002

出　　处：《国外电子测量技术》2024年第12期71-82,共12页Foreign Electronic Measurement Technology

摘　　要：为准确获取具有代表性的风电出力场景,提出了一种基于改进密度峰值优化全局K-means算法的典型风电场景聚类方法。首先通过密度峰值聚类算法(density peak clustering,DPC)初步确定聚簇中心,而后运用全局K-means(global K-means,GKM)进行迭代聚类;随后,引入具有全局搜索能力的斑马优化(zebra optimization,ZO)方法,用于寻找DPC中的截断距离的最优值;然后,为全面评估所得场景集的稳定性和有效性,选取了3个聚类有效性指标并采用熵权Topsis法来进行综合评价;最后,使用实际风电数据进行大量的仿真实验与分析。结果表明,方法的综合得分为0.444,优于其他优化方法,能更准确地提取和划分典型的风电场景。In order to accurately obtain representative wind power output scenarios,this paper proposes a typical wind power scenario clustering method based on the improved density peak optimization global K-means algorithm.Firstly,the density peak clustering algorithm(DPC)is used to preliminarily determine the cluster center,and then the global Kmeans(GKM)is used for iterative clustering.Subsequently,a zebra optimization(ZO)method with global search capability is introduced to find the optimal value of the truncation distance in the DPC.Then,in order to comprehensively evaluate the stability and effectiveness of the obtained scenario set,three clustering effectiveness indexes are selected and the entropy weight Topsis method is used for comprehensive evaluation.Finally,a large number of simulation experiments and analyses are carried out using actual wind power data.The results show that the comprehensive score of the proposed method is 0.444,which is better than other optimization methods,and can more accurately extract and divide typical wind power scenarios.

关 键 词：聚簇中心提取 场景生成 全局K-means 密度峰值聚类 典型场景集评价 

分 类 号：TM614[电气工程—电力系统及自动化] TN06[电子电信—物理电子学]