• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

电力建设 ›› 2020, Vol. 41 ›› Issue (3): 31-38.doi: 10.3969/j.issn.1000-7229.2020.03.004

• 主动配电系统协同规划与技术评估 • 上一篇    下一篇

基于Apriori算法和卷积神经网络的配电设备运行效率主要影响因素挖掘

白浩1,袁智勇1,孙睿2,张强2,史训涛1   

  1. 1. 南方电网科学研究院,广州市 510663;2.智能电网教育部重点实验室(天津大学),天津市 300072
  • 出版日期:2020-03-01
  • 作者简介:白浩(1987),男, 博士,高级工程师,通信作者,主要从事配电自动化、主动配电网和人工智能应用等方面的研究工作; 袁智勇(1978),男,博士,高级工程师,主要从事智能配电网、微电网等方面的研究工作; 孙睿(1997),男,硕士研究生,主要从事配电网规划方面的研究工作; 张强(1979),男,博士,讲师,主要从事为配电网、综合能源系统规划及运行等方面的研究工作; 史训涛(1986),男,硕士,高级工程师, 主要从事智能配电网、配电网资产管理等方面的研究工作。
  • 基金资助:
    南方电网公司科技项目(ZBKJXM20180220)

Method Based on Apriori Algorithm and Convolution Neural  Network for Mining Main Influencing Factors of Distribution Equipment Operation Efficiency

BAI Hao1,YUAN Zhiyong 1,SUN Rui 2,ZHANG Qiang 2,SHI Xuntao1   

  1. 1. Electric Power Research Institute, China Southern Power Grid Co., Ltd., Guangzhou 510663, China;2. Key Laboratory of the Ministry of Education on Smart Power Grids (Tianjin University), Tianjin 300072, China
  • Online:2020-03-01
  • Supported by:
    This work is supported by Science and Technology Project of China Southern Power Grid (No.ZBKJXM20180220).

摘要: 针对目前配电系统运行效率研究方面缺少评价手段且缺少内在原因的探究方法的问题,提出了一种基于Apriori算法和卷积神经网络的配电设备运行效率主要影响因素挖掘方法。首先,提出配电设备日运行效率的计算方法;其次,分析可能影响运行效率的原因,提出基于K-means聚类和Apriori算法的运行效率主要影响因素的挖掘方法;然后,基于卷积神经网络,提出运行效率与主要影响因素之间关系的定量度量方法;最后利用算例分析,验证了该文方法的可行性。

关键词: 运行效率, 主要影响因素, Apriori算法, 卷积神经网络

Abstract:  In view of the lack of evaluation methods and  research methods for internal causes in current research of distribution system operation efficiency, this paper proposes a method based on Apriori algorithm and convolution neural network for mining the main influencial factors of distribution equipment operation efficiency. Firstly, according to the definition, the calculation method for daily operation efficiency of distribution equipment is proposed; Secondly, the reasons that may affect the operation efficiency are analyzed, and the method based on K-means clustering and Apriori algorithm for mining the main influencing factors of operation efficiency is proposed; Thirdly, the quantitative measurement method for the relationship between operation efficiency and main influencing factors is proposed on basis of convolution neural network; Finally, by using programming, the feasibility of this method is verified.  

Key words: operation efficiency, main influencial factors, apriori algorithm, convolutional neural network

中图分类号: