基于决策树和数据驱动的零电量用户筛选方法

doi:10.6040/j.issn.1672-3961.0.2019.116

山东大学学报 (工学版) ›› 2019, Vol. 49 ›› Issue (5): 29-36.doi: 10.6040/j.issn.1672-3961.0.2019.116

• 电气工程———人工智能应用专题 • 上一篇下一篇

基于决策树和数据驱动的零电量用户筛选方法

章博¹(),卢峰²,董寒宇²,陈清泰³,林振智^1,^4,*(),王洪涛⁴

1. 浙江大学电气工程学院, 浙江杭州 310027
2. 国网浙江省电力公司湖州供电公司, 浙江湖州 313000
3. 浙江华云信息科技有限公司, 浙江杭州 310012
4. 山东大学电气工程学院, 山东济南 250061

收稿日期:2019-03-25 出版日期:2019-10-20 发布日期:2019-10-18
通讯作者: 林振智 E-mail:zhbzju@163.com;linzhenzhi@zju.edu.cn
作者简介:章博(1995—)，男，湖北襄阳人，硕士研究生，主要研究方向为电力大数据和配电网络重构.E-mail：zhbzju@163.com
基金资助:
国家重点研发计划(2016YFB0901100);国家自然科学基金资助项目(51777185)

None-consumption users filtering algorithm based on decision tree and data-driven methods

Bo ZHANG¹(),Feng LU²,Hanyu DONG²,Qingtai CHEN³,Zhenzhi LIN^1,^4,*(),Hongtao WANG⁴

1. School of Electrical Engineering, Zhejiang University, Hangzhou 310027, Zhejiang, China
2. Huzhou Power Supply Company, State Gird Zhejiang Electric Power Company, Huzhou 313000, Zhejiang, China
3. Zhejiang Huayun Information Technology Co., Ltd., Hangzhou 310012, Zhejiang, China
4. School of Electrical Engineering, Shandong University, Jinan 250061, Shandong, China

Received:2019-03-25 Online:2019-10-20 Published:2019-10-18
Contact: Zhenzhi LIN E-mail:zhbzju@163.com;linzhenzhi@zju.edu.cn
Supported by:
国家重点研发计划(2016YFB0901100);国家自然科学基金资助项目(51777185)

摘要/Abstract

摘要：

随着电力系统中用电客户的增多及客户用电形式的多样化,零电量用户(none-consumption user, NCU)逐渐增多,对零电量用户进行排查耗费了电网公司大量的人力物力。在此背景下,基于电力用户用电信息采集系统(electricity information acquisition system, EIAS)的零电量用户信息,提出了一种零电量用户筛选的数据驱动算法,判断正常零电量用户和异常零电量用户。采用决策树对电力用户用电信息采集系统数据进行分析,确定零电量用户异常类型;对决策树无法辨别的用户类型,通过分析零电量用户计量采集数据和营销数据,提取适用于零电量用户筛选的关键因子,进而构建零电量用户筛选评价体系;在此基础上,采用(criteria importance though intercrieria correlation, CRITIC)法确定关键因子的权重,并采用雷达图法对零电量用户进行筛选分类。以浙江省某供电所管辖下的零电量用户为例对所提出的方法进行说明,并通过现场排查进行校验,结果表明所提出的零电量用户筛选方法具有一定的有效性。

关键词: 零电量用户, 筛选, 决策树, CRITIC法, 雷达图法

Abstract:

With the increasing of power consumers and diversification of power consumption in power systems, the number of none-consumption users (NCUs) was also increasing rapidly. Thus, lots of manpower and material resources of power supply companies were arranged to perform troubleshooting on NCUs. Given this background, a data-driven method based on the electricity information of NCUs collected by electricity information acquisition system (EIAS) was proposed to determine the filtering results of normal NCUs and abnormal NCUs. The decision tree was utilized to analyze the electricity data of NCUs, and determine the types of NCUs. The key factors suitable for NCUs filtering were determined based on the original data to filter the NCUs that could not be screened by the decision tree, and the evaluation system for NCUs filtering was constructed. On this basis, CRITIC and radar chart methods were adopted to determine the weights of the key factors and to determine the filtering results of NCUs, respectively. The NCUs power-supplied by an actual power supply station in Zhejiang Province were served for demonstrating the proposed algorithm of NCUs filtering, and the simulation and on-site inspection results showed that the proposed data-driven method was effective for screening out the abnormal NCUs.

Key words: none-consumption user, troubleshoot priority, decision tree, CRITIC method, radar chart method

中图分类号:

TM933.4

章博,卢峰,董寒宇,陈清泰,林振智,王洪涛. 基于决策树和数据驱动的零电量用户筛选方法[J]. 山东大学学报 (工学版), 2019, 49(5): 29-36.

Bo ZHANG,Feng LU,Hanyu DONG,Qingtai CHEN,Zhenzhi LIN,Hongtao WANG. None-consumption users filtering algorithm based on decision tree and data-driven methods[J]. Journal of Shandong University(Engineering Science), 2019, 49(5): 29-36.

图/表 6

图1

图2

表1

图3

图4

图5

参考文献 20

1	FANG Xi , MISRA Satyajayant , XUE Guoliang , et al. Smart grid—the new and improved power grid: a survey[J]. IEEE Communications Surveys & Tutorials, 2012, 14 (4): 944- 980.
2	宋亚奇, 周国亮, 朱永利. 智能电网大数据处理技术现状与挑战[J]. 电网技术, 2013, 37 (4): 927- 935.
	SONG Yaqi , ZHOU Guoliang , ZHU Yongli . Present status and challenges of big data processing in smart grid[J]. Power System Technology, 2013, 37 (4): 927- 935.
3	YANG Hongming , ZHANG Jun , QIU Jing , et al. A practical pricing approach to smart grid demand response based on load classification[J]. IEEE Transactions on Smart Grid, 2018, 9 (1): 179- 190. doi: 10.1109/TSG.2016.2547883
4	李海石, 徐向艺, 张磊. "一带一路"背景下全球能源互联网运行机制构建[J]. 山东大学学报(工学版), 2017, 47 (6): 134- 142.
	LI Haishi , XU Xiangyi , ZHANG Lei . Operating mechanism establishment of the global energy interconnection under "the Belt and Road Initiative" situation[J]. Journal of Shandong University (Engineering Science), 2017, 47 (6): 134- 142.
5	LUAN Wenpeng, PENG Joshua, MARAS Mirjana, et al. Distribution network topology error correction using smart meter data analytics[C]//2013 IEEE Power & Energy Society General Meeting. Ottawa, Canada: IEEE, 2013: 1-5.
6	WU Jinsong , GUO Song , LI Jie , et al. Big data meet green challenges: big data toward green applications[J]. IEEE Systems Journal, 2016, 10 (3): 888- 900. doi: 10.1109/JSYST.2016.2550530
7	丁杰, 奚后玮, 韩海韵, 等. 面向智能电网的数据密集型云存储策略[J]. 电力系统自动化, 2012, 36 (12): 66- 70.
	DING Jie , XI Houwei , HAN Haiyun , et al. A smart grid-oriented data placement strategy for data-intensive cloud environment[J]. Automation of Electric Power Systems, 2012, 36 (12): 66- 70.
8	刘洋, 刘博, 王峰. 基于Parameter Server框架的大数据挖掘优化算法[J]. 山东大学学报(工学版), 2017, 47 (4): 1- 6.
	LIU Yang , LIU Bo , WANG Feng . Optimization algorithm for big data mining based on parameter server framework[J]. Journal of Shandong University (Engineering Science), 2017, 47 (4): 1- 6.
9	王德文, 孙志伟. 电力用户侧大数据分析与并行负荷预测[J]. 中国电机工程学报, 2015, 35 (3): 527- 537.
	WANG Dewen , SUN Zhiwei . Big data analysis and parallel load forecasting of electric power user side[J]. Proceedings of the CSEE, 2015, 35 (3): 527- 537.
10	黄小庆, 陈颉, 陈永新, 等. 大数据背景下的充电站负荷预测方法[J]. 电力系统自动化, 2016, 40 (12): 68- 74. doi: 10.7500/AEPS20160323001
	HUANG Xiaoqing , CHEN Jie , CHEN Yongxin , et al. Load forecasting method for electric vehicle charging station based on big data[J]. Automation of Electric Power Systems, 2016, 40 (12): 68- 74. doi: 10.7500/AEPS20160323001
11	ZHANG Pei , WU Xiaoyu , WANG Xiaojun , et al. Short-term load forecasting based on big data technologies[J]. CSEE Journal of Power and Energy Systems, 2015, 1 (3): 59- 67. doi: 10.17775/CSEEJPES.2015.00036
12	WANG Kun , LI Huining , FENG Yixiong , et al. Big data analytics for system stability evaluation strategy in the energy internet[J]. IEEE Transactions on Industrial Informatics, 2017, 13 (4): 1969- 1978. doi: 10.1109/TII.2017.2692775
13	刘羽霄, 张宁, 康重庆. 数据驱动的电力网络分析与优化研究综述[J]. 电力系统自动化, 2018, 42 (6): 157- 167.
	LIU Yuxiao , ZHANG Ning , KANG Chongqing . A review on data-driven analysis and optimization of power grid[J]. Automation of Electric Power Systems, 2018, 42 (6): 157- 167.
14	马纪, 刘希喆. 基于G2-熵权法的低压配网台区状态特性评估[J]. 电力自动化设备, 2017, 37 (1): 41- 46.
	MA Ji , LIU Xizhe . Conditional characteristic evaluation based on G2-entropy weight method for low-voltage distribution network[J]. Electric Power Automation Equipment, 2017, 37 (1): 41- 46.
15	TSANG S , KAO B , YIP K Y , et al. Decision trees for uncertain data[J]. IEEE Transactions on Knowledge and Data Engineering, 2011, 23 (1): 64- 78. doi: 10.1109/TKDE.2009.175
16	张小峰, 张志旺, 逄珊. 基于通信系统的决策树构造算法[J]. 山东大学学报(工学版), 2011, 41 (4): 79- 84.
	ZHANG Xiaofeng , ZHANG Zhiwang , PANG Shan . Algorithm based on a communication system for constructing a decision tree[J]. Journal of Shandong University (Engineering Science), 2011, 41 (4): 79- 84.
17	MURPHY O J , MCCRAW R L . Designing storage efficient decision trees[J]. IEEE Transactions on Computers, 1991, 40 (3): 315- 320. doi: 10.1109/12.76408
18	朱凌, 林冠强, 叶晓君, 等. 联合采用客观赋权和夹角度量法的电力系统关键线路辨识[J]. 电力建设, 2018, 39 (3): 49- 56. doi: 10.3969/j.issn.1000-7229.2018.03.006
	ZHU Ling , LIN Guanqiang , YE Xiaojun , et al. Critical line identification in power systems by combined use of objective weighting and inter-degree measure methods[J]. Electric Power Construction, 2018, 39 (3): 49- 56. doi: 10.3969/j.issn.1000-7229.2018.03.006
19	LIN Zhenzhi , WEN Fushuan , WANG Huifang , et al. CRITIC-based node importance evaluation in skeleton-network reconfiguration of power grids[J]. IEEE Transactions on Circuits and Systems Ⅱ: Express Briefs, 2018, 65 (2): 206- 210. doi: 10.1109/TCSII.2017.2703989
20	韩畅, 林振智, 杨莉, 等. 台风条件下区域电力系统的重要线路多维度辨识[J]. 电力系统自动化, 2018, 42 (15): 118- 125. doi: 10.7500/AEPS20170715001
	HAN Chang , LIN Zhenzhi , YANG Li , et al. Multi-dimensional critical line identification for regional power system under typhoon[J]. Automation of Electric Power Systems, 2018, 42 (15): 118- 125. doi: 10.7500/AEPS20170715001

多维度评价

Viewed

Full text

Abstract

Cited

Shared

Discussed

户号	居民类型	合同容量/(kVA)	电压等级/V	信用等级	异常事件/件	环比电量/(kW·h)	同比电量/(kW·h)	离散系数/(p.u.)	台区线损变化率/(p.u.)	评分/(p.u.)
****050083	城镇居民	4	380	最高信用等级	4	0.00	2 808.39	0.92	0.02	57.61
****051024	城镇居民	45	380	最高信用等级	4	119.00	13 234.20	0.94	0.11	67.12
****019099	乡村居民	6	220	-	4	0.00	899.79	1.44	0.14	39.15
****020500	乡村居民	6	220	-	4	4.85	394.30	1.84	0.13	39.15
****021224	乡村居民	6	220	-	4	0.00	393.31	1.09	0.02	38.80
…	…	…	…	…	…	…	…	…	…	…
****063612	城镇居民	10	380	-	4	0.00	598.80	1.24	0.05	96.55
****064572	乡村居民	8	220	-	4	0.00	982.82	1.27	0.17	39.38
****064986	城镇居民	20	380	-	4	0.00	681.71	1.33	0.07	97.95
****064987	城镇居民	20	380	-	4	0.00	7 197.39	0.84	0.01	100.00

[1]	潘盼1,王熙照2,翟俊海2. 基于有序决策树的改进归纳算法[J]. 山东大学学报(工学版), 2014, 44(1): 41-44.
[2]	许春耀1,2, 陈明志3*, 余轮1. 适应用户需求变化的前摄推荐模型[J]. 山东大学学报(工学版), 2013, 43(3): 1-6.
[3]	张小峰,张志旺,逄珊. 基于通信系统的决策树构造算法[J]. 山东大学学报(工学版), 2011, 41(4): 79-84.
[4]	陈朋胡文容裴海燕. 一株反硝化细菌LZ-14的筛选及其脱氮特性[J]. 山东大学学报(工学版), 2009, 39(5): 133-138.

基于决策树和数据驱动的零电量用户筛选方法

None-consumption users filtering algorithm based on decision tree and data-driven methods

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 6

参考文献 20

相关文章 4

多维度评价

本文评价

推荐阅读 10