###
上海电力大学学报:2019,35(4):327-332
本文二维码信息
码上扫一扫!
基于ISODATA的电力负荷曲线分类
(上海电力学院 电气工程学院)
A Load Curve Clustering Algorithm Based on ISODATA
(School of Electrical Engineering, Shanghai University of Electric Power, Shanghai 200090, China)
摘要
图/表
参考文献
本刊相似文献
All Journals 相似文献
All Journals 引证文献
本文已被:浏览 1589次   下载 521
投稿时间:2018-04-18    
中文摘要: 迭代自组织数据分析算法(ISODATA)是一种基于统计模式识别的非监督学习动态聚类算法。针对当前各算法初始聚类数取值困难、容易陷入局部最优等问题,介绍了ISODATA的原理和实现步骤,并将此算法应用于负荷分类中。在MATLAB中结合具体日负荷曲线样本进行聚类分析,结果证明聚类效果较好。将ISODATA与各种传统聚类方法进行了对比实验,比较各种算法的聚类效果、预定聚类数目对算法结果的影响,以及初始聚类中心的选择对结果的影响。对比结果证明,此方法适用于负荷分类的研究。
Abstract:Interative self-organization data analysis algorithm(ISODATA) is a kind of unsupervised learning dynamic clustering algorithm based on statistical pattern recognition.The principle and process of the ISODATA are introduced in detail.This algorithm is applied in load classification,combined with specific daily load curve samples in matlab for cluster analysis.ISODATA is compared with traditional clustering methods in the results of algorithm clustering and the effects of the clustering center are better.The result is compared with the traditional clustering effect of various clustering methods and proves to be relatively more accurate,which confirms this verified the applicability of method in the study of the load curve classification.
文章编号:20194005     中图分类号:TM769    文献标志码:
基金项目:国家电网公司科技项目(52090016002M);上海市科学技术委员会地方能力建设计划基金(16020500900)。
引用文本:
李仲恒,刘蓉晖.基于ISODATA的电力负荷曲线分类[J].上海电力大学学报,2019,35(4):327-332.
LI Zhongheng,LIU Ronghui.A Load Curve Clustering Algorithm Based on ISODATA[J].Journal of Shanghai University of Electric Power,2019,35(4):327-332.