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

doi:10.3969/j.issn.1000－7229.2020.03.004

PDF(1136 KB)

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

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

作者信息 +

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

Author information +

文章历史 +

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。

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.

导出引用

白浩，袁智勇，孙睿，张强，史训涛. 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[J]. 电力建设. 2020, 41(3): 31-38 https://doi.org/10.3969/j.issn.1000－7229.2020.03.004

BAI Hao，YUAN Zhiyong,SUN Rui,ZHANG Qiang,SHI Xuntao1BAI Hao，YUAN Zhiyong,SUN Rui,ZHANG Qiang,SHI Xuntao. Method Based on Apriori Algorithm and Convolution Neural Network for Mining Main Influencing Factors of Distribution Equipment Operation Efficiency[J]. Electric Power Construction. 2020, 41(3): 31-38 https://doi.org/10.3969/j.issn.1000－7229.2020.03.004

中图分类号： TM 73

参考文献

［1］叶霞, 熊雪晨, 高华淑, 等. 可国际比较的中国医院运行效率实证调查［J］. 卫生经济研究, 2019（10）： 44-47, 51.
YE Xia, XIONG Xuechen, GAO Huashu, et al. An empirical survey on the operating efficiency of chinese hospitals compared with international hospitals ［J］. Health Economics Research, 2019（10）：44-47, 51.
［2］况爱武, 杨欢. 考虑需求不确定性的路网运行效率评价［J］. 系统工程, 2019, 37（5）： 80-86.
KUANG Aiwu, YANG Huan. Evaluation of the road network operation efficiency with uncertainty in traffic demands ［J］. Systems Engineering, 2019,37（5）：80-86.
［3］刘洪, 杨卫红, 王成山, 等. 配电网设备利用率评价标准与提升措施［J］. 电网技术, 2014, 38（2）： 419-423.
LIU Hong, YANG Weihong, WANG Chengshan, et al. Assessment criteria and improvement measures of equipment utilization on distribution network［J］. Power System Technology, 2014, 38（2）： 419-423.
［4］盛万兴, 陈海, 王军, 等. 基于负荷持续曲线的配电网运行效率评价［J］. 电网技术, 2016, 40（4）： 1237-1242.
SHENG Wanxing, CHEN Hai, WANG Jun, et al. Operation efficiency evaluation of distribution network based on load duration curve［J］. Power System Technology, 2016, 40（4）： 1237-1242.
［5］韩震焘, 黄志伟, 葛少云, 等. 城市配电网综合评价体系［J］. 电网技术, 2012, 36（8）： 95-99.
HAN Zhentao, HUANG Zhiwei, GE Shaoyun, et al. A comprehensive evaluation system of urban distribution network［J］. Power System Technology, 2012, 36（8）： 95-99.
［6］张粒子, 扶柠柠, 王春丽, 等. 基于回归分析的电网运行维护费合理性评估［J］. 电力系统自动化, 2014, 38（13）： 140-144.
ZHANG Lizi, FU Ningning, WANG Chunli, et al. Rationality evaluation of power grid operation and maintenance costs based on regression analysis［J］. Automation of Electric Power Systems, 2014, 38（13）： 140-144.
［7］卫泽晨, 赵凤展, 王佳慧, 等. 网格化中低压智能配电网评价指标体系与方法［J］. 电网技术, 2016, 40（1）： 249-255.
WEI Zechen, ZHAO Fengzhan, WANG Jiahui, et al. Gridding evaluation index system and method of MV and LV intelligent distribution network［J］. Power System Technology, 2016, 40（1）： 249-255.
［8］周念成, 廖建权, 王强钢, 等. 深度学习在智能电网中的应用现状分析与展望［J］. 电力系统自动化, 2019, 43（4）： 180-191.
ZHOU Niancheng, LIAO Jianquan, WANG Qianggang, et al. Analysis and prospect of deep learning application in smart grid［J］. Automation of Electric Power Systems, 2019, 43（4）： 180-191.
［9］陆继翔, 张琪培, 杨志宏, 等. 基于CNN-LSTM混合神经网络模型的短期负荷预测方法［J］. 电力系统自动化, 2019, 43（8）： 131-137.
LU Jixiang, ZHANG Qipei, YANG Zhihong, et al. Short-term load forecasting method based on CNN-LSTM hybrid neural network model［J］. Automation of Electric Power Systems, 2019, 43（8）： 131-137.
［10］吴潇雨, 和敬涵, 张沛, 等. 基于灰色投影改进随机森林算法的电力系统短期负荷预测［J］. 电力系统自动化, 2015, 39（12）： 50-55.
WU Xiaoyu, HE Jinghan, ZHANG Pei, et al. Power system short-term load forecasting based on improved random forest with grey relation projection［J］. Automation of Electric Power Systems, 2015, 39（12）： 50-55.
［11］李勇, 何蕾, 庞传军, 等. 基于层次分析法的火电厂运行情况量化评价方法［J］. 电网技术, 2015, 39（2）： 500-504.
LI Yong, HE Lei, PANG Chuanjun, et al. An analytical hierarchy process based quantitative method to evaluate operating condition of thermal power plant［J］. Power System Technology, 2015, 39（2）： 500-504.
［12］郑翔, 赵凤展, 杨仁刚, 等. 基于大数据的低压配电网无功运行评价体系［J］. 电网技术, 2017, 41（1）： 272-278.
ZHENG Xiang, ZHAO Fengzhan, YANG Rengang, et al. An evaluation system to reactive power operation in LV distribution network based on big data［J］. Power System Technology, 2017, 41（1）： 272-278.
［13］王雁凌, 吴梦凯, 周子青, 等. 基于改进灰色关联度的电力负荷影响因素量化分析模型［J］. 电网技术, 2017, 41（6）： 1772-1778.
WANG Yanling, WU Mengkai, ZHOU Ziqing, et al. Quantitative analysis model of power load influencing factors based on improved grey relational degree［J］. Power System Technology, 2017, 41（6）： 1772-1778.
［14］黄进, 尹治本. 关联规则挖掘的Apriori算法的改进［J］. 电子科技大学学报, 2003, 32（1）： 76-79.
HUANG Jin, YIN Zhiben. Improvement of Apriori algorithm for mining association rules ［J］. Journal of UEST of China, 2003, 32（1）： 76-79.
［15］胡丽娟, 刁赢龙, 刘科研, 等. 基于大数据技术的配电网运行可靠性分析［J］. 电网技术, 2017, 41（1）： 265-271.
HU Lijuan, DIAO Yinglong, LIU Keyan, et al. Operational reliability analysis of distribution network based on big data technology［J］. Power System Technology, 2017, 41（1）： 265-271.
［16］HONG T, PINSON P, FAN S. Global energy forecasting competition 2012［J］. International Journal of Forecasting, 2014, 30（2）： 357-363.