计算机工程与应用 ›› 2017, Vol. 53 ›› Issue (17): 260-265.DOI: 10.3778/j.issn.1002-8331.1603-0110

• 工程与应用 • 上一篇    下一篇

基于改进的并行K-Means算法的电力负荷聚类研究

许元斌1,李国辉2,3,郭  昆2,3,郭松荣2,3,林  炜2,3   

  1. 1.国网信通亿力科技有限责任公司,福州 350001
    2.福州大学 数学与计算机科学学院,福州 350116
    3.福建省网络计算与智能信息处理重点实验室,福州 350116
  • 出版日期:2017-09-01 发布日期:2017-09-12

Research on parallel clustering of power load based on improved K-Means algorithm

XU Yuanbin1, LI Guohui2,3, GUO Kun2,3, GUO Songrong2,3, LIN Wei2,3   

  1. 1.State Grid Electic Power Company, Fuzhou 350001, China
    2.College of Mathematics and Computer Science, Fuzhou University, Fuzhou 350116, China
    3.Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing, Fuzhou 350116, China
  • Online:2017-09-01 Published:2017-09-12

摘要: 电力企业通常根据电力负荷数据,采用传统的K-Means算法对客户进行划分,而这种方法最大的缺陷就是必须由用户手动指定聚类簇数。提出了一种将Canopy算法和K-Means算法结合应用于负荷聚类的方法,无需手动指定聚类簇数。收集到的用户历史用电数据,使用并行计算框架MapReduce对原始数据进行预处理。应用Canopy和K-Means算法建立自动负荷聚类模型。在真实用电数据上进行实证分析,通过使用Silhouette指标对结果进行评估,证明提出的方法更加稳定和具有广泛的适用性。

关键词: 负荷聚类, 并行计算, Canopy, K-Means

Abstract: The electrical power enterprise usually based on power load data, uses the traditional K-Means algorithm to classify the customers, but the biggest drawback of this method must be specified by the user manual clustering number of clusters. It proposes a method combining Canopy algorithm and K-Means algorithm based on load clustering, without the need to manually specify the number of clusters, the automatic division of the customer. First of all, it collects users’ electricity data, uses the parallel computing framework MapReduce to preprocess the original data. Then, it uses Canopy and K-Means algorithm to establish the clustering model of automatic load. Finally, in the real consumption data on the empirical analysis, by using the Silhouette index to evaluate, it shows that the proposed method is more stable and convenient, and has wider applicability.

Key words: load clustering, parallel computing, Canopy, K-Means