一种基于DTW的改进K-means的日负荷曲线聚类方法

• Format: Patent
• Language: Chinese
• Published: 07.11.2023
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

本发明公开了一种基于DTW的改进K-means的日负荷曲线聚类方法，采用密度函数分别选取初始分布特性聚类中心曲线与动态特性聚类中心曲线，并初始化聚类数目及算法迭代次数。随后，分别采用欧氏距离与DTW综合衡量负荷曲线的分布特性及动态特性，并分别以所得动态特性数值与分布特性数值对各自特性聚类中心进行更新，此过程以每条日负荷曲线分布特性与动态特性相似度衡量值的加权值作为负荷曲线关于聚类中心曲线相似度衡量的手段。最后以聚类结果与聚类离散度的误差值作为算法是否得出聚类结果的判断依据，并基于DBI指标确定最佳聚类数及相应的聚类中心曲线。本方法可以有效改善K-means聚类计算效果与效率，且聚类结果与实际工程相符，具有一定的工程价值。 The invention discloses an improved K-means daily load curve clustering method based on DTW, and the method comprises the steps of selecting an initial distribution characteristic clustering center curve and a dynamic characteristic clustering center curve through employing a density function, and initializing the clustering number and algorithm iteration times; then, using the Euclidean distanceand the DTW respectively for comprehensively measuring the distribution characteristic and the dynamic characteristic of the load curve; and updating respective characteristic clustering centers by using the obtained dynamic characteristic values and distribution characteristic values respectively, wherein in