基于负荷数据挖掘的公变用途分类方法研究
作者:
作者单位:

作者简介:

通讯作者:

中图分类号:

基金项目:


Analytical Method of the Industry Which Public Transformers Belong Based on Load Data Mining
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 图/表
  • |
  • 访问统计
  • |
  • 参考文献
  • |
  • 相似文献
  • |
  • 引证文献
  • |
  • 资源附件
  • |
  • 文章评论
    摘要:

    为了从公变行业特性角度对配电网进行有效的投资经济效益分析,需要对公变进行用途划分。文中先利用大数据技术对行业负荷特性进行分析,再通过基于Canopy的改进K-means聚类方法分析公变负荷特性,进而根据余弦相似度算法分别从四季负荷特性及节假日负荷特性等角度分析公变所属行业,最后利用行业拟合方法从不同维度匹配出公变的所属行业。采用该方法对江苏省公变设备进行用途划分取得了较高的准确率,实现了较为准确的公变设备用途划分。基于负荷数据挖掘的公变用途划分方法为配电网投资效益评价提供了有力的支撑。

    Abstract:

    In order to effectively analyze the economic benefits of investment of the electricity distribution network from the perspective of the characteristics of the public transformer industry,it is necessary to classify the industry of public transformers.In this paper,the use of big data technology to analyze the industry load characteristics,and then the improved K-means algorithm based on canopy is used to analyze the characteristics of the public transformer load.After that,according to the cosine similarity algorithm,from the perspective of the characteristics of the four seasons load and the characteristics of holiday load,he analysis of public transformers belong to which industry.Finally,the industry fitting method from different dimensions is used to match the industry which public transformers belong.For public transformers in Jiangsu province,the use of the method has been achieved after the high accuracy rate,to achieve a more accurate analytical method of the public transformers industry.The analytical method of the industry which public transformers belong based on load data mining provide a strong support for the evaluation of economic benefits of investment of the electricity distribution network.

    参考文献
    相似文献
    引证文献
引用本文

方超,仲春林,季聪.基于负荷数据挖掘的公变用途分类方法研究[J].电力工程技术,2018,37(5):115-120

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2018-04-18
  • 最后修改日期:2018-05-23
  • 录用日期:2017-11-03
  • 在线发布日期: 2018-09-28
  • 出版日期:
文章二维码