基于数据驱动方法的疫情阶段电力用户负荷特性画像模型

doi:10.12204/j.issn.1000-7229.2021.02.012

摘要/Abstract

摘要：

电力用户负荷画像建模是一种面向用户的、通过挖掘用电数据中的负荷特性建立差异化画像标签的重要方法,现有研究方法多侧重于画像方法的研究,而缺乏完善的负荷特性标签体系。文章提出了一种基于数据驱动的负荷特性分析通用方法,从调度部门最关注的用电规律性、平顺度、负荷调控能力以及疫情影响度四方面构建负荷特性标签体系。首先,采用模糊C均值聚类算法从海量实际负荷数据中提取行业典型负荷曲线,综合考虑各行业用电特性,从4个方面构建完善的负荷特性标签体系,并建立考虑疫情影响的多类型用户负荷特性画像模型。其次,细化负荷特性标签,给出相应指标定义和计算方法,并采用模糊聚类算法判定指标分界,采用熵权法对用电平顺度进行综合评分。最后,通过算例对各行业典型用户的用电数据进行分析,并给出普适的指标分界,为各行业电力用户负荷建模提供了一种新思路。

关键词: 数据驱动, 负荷特性画像模型, 负荷特性标签, 疫情影响度, 用电平顺度

Abstract:

Load portrait modeling of power user is an important user-oriented method to create differentiated labels by mining the load characteristics in power consumption data. Most of the existing research focuses on the study of portrait methods, but lacks comprehensive load characteristic label system. This paper proposes a general method of load characteristic analysis based on data-driven. The load characteristic label system is constructed from power consumption regularity, smoothness, load control capability and epidemic impact, which are most concerned by dispatching department. Firstly, the typical load curve is extracted from massive actual load data by using fuzzy C-means clustering algorithm. Considering the power consumption characteristics of each industry from above four aspects, a comprehensive load characteristic label system and the load characteristic portrait models of different power users are established. Secondly, the load characteristic label is refined and every definition and calculation method of corresponding index is given. Furthermore, the index boundary is determined by fuzzy clustering algorithm, and the smoothness label is scored by entropy weight method. Finally, the data of typical users in different industries are analyzed from an example, and universal index boundaries are given, which provide a new idea for load modeling of users in various industries.

Key words: data-driven, load characteristic portrait model, load characteristic label, epidemic impact degree, load smoothness

中图分类号:

TM714

陆晓, 徐春雷, 冷钊莹, 吴海伟, 陈中. 基于数据驱动方法的疫情阶段电力用户负荷特性画像模型[J]. 电力建设, 2021, 42(2): 93-106.

LU Xiao, XU Chunlei, LENG Zhaoying, WU Haiwei, CHEN Zhong. Load Characteristic Portrait Model of Power Users in Epidemic Stage Applying Data-Driven Method[J]. ELECTRIC POWER CONSTRUCTION, 2021, 42(2): 93-106.

图/表 36

表1 用电规律性标签

Table 1 Load regularity label

表2 用电平顺度标签

Table 2 Load smoothness label

表3 负荷调控能力标签

Table 3 Load control capability label

表4 疫情影响程度标签

Table 4 The impact of COVID-19 label

表5 日内工作时间特性判断标准

Table 5 Criteria for intraday working-time characteristic

表6 日夜用电特性判断标准

Table 6 Criteria for day-and-night electricity characteristic

表7 早晚高峰特性判断标准

Table 7 Criteria for morning-and-evening peak characteristic

图1 典型用户负荷曲线峰谷时段划分

Fig.1 Typical users'peak and valley period division

表8 交通运输业用户2一周负荷曲线相似度

Table 8 The similarity of weekly load curve of transportation user 2

表9 月用电相似度判断标准

Table 9 Criteria for monthly electricity similarity

表10 季度用电相似度判断标准

Table 10 Criteria for quarterly electricity similarity

表11 季节用电规律判断标准

Table 11 Criteria for seasonal electricity regularity

图2 典型用户夏季降温和冬季取暖负荷曲线

Fig.2 Cooling load curve in summer and heating load curve in winter for typical users

表12 典型用户的季节用电规律性指标计算

Table 12 Seasonal electricity regularity indexes of typical users

表13 用电平顺度标签各指标权重

Table 13 Weight of each index in load smoothness label

表14 用电平顺度综合得分和排序(由差到好)

Table 14 Comprehensive score and ranking of users'load smoothness (from bad to good)

表15 用电平顺度判断标准

Table 15 Criteria for load smoothness

图3 钢铁业用户2激励型负荷调控典型曲线

Fig.3 Typical load curves of steel industry user 2 under incentive load control

图4 钢铁业用户2价格型负荷调控典型曲线

Fig.4 Typical load curves of steel industry user 2 under price-based load control

表16 钢铁业用户2激励型负荷调控典型曲线指标

Table 16 Indices of typical load curves of steel industry user 2 under incentive load control

表17 钢铁业用户2价格型负荷调控典型曲线指标

Table 17 Indices of typical load curves of steel industry user 2 under price-based load control

表18 负荷调控能力判断标准

Table 18 Criteria for load control

表19 疫情影响度和疫情恢复度判断标准

Table 19 Criteria for epidemic impact degree and epidemic recovery degree

图5 商业用户1 2019年和2020年疫情同期典型曲线以及日用电量

Fig.5 Typical load curves and daily electricity consumption of commercial user1 in 2019 and 2020 epidemic period

图6 电子设备制造业用户2 2019年和2020年疫情同期典型曲线以及日用电量

Fig.6 Typical load curves and daily electricity consumption of electronic equipment manufacturing user 2 in 2019 and 2020 epidemic period

图7 信息传输软件和信息技术服务业用户1 2019年和2020年疫情同期日用电量

Fig.7 Daily electricity consumption of information transmission software and information technology service industry user 1 in 2019 and 2020

图8 钢铁冶炼业用户1的负荷特性标签

Fig.8 Load characteristic label for steel industry user 1

表A1 日内用电规律中日内用电特性指标计算结果

Table A1 Calculation results of intraday working-time characteristic

表A2 日内用电规律中日夜用电特性指标计算结果

Table A2 Calculation results of day-and-night electricity characteristic

表A3 日内用电规律中有无早晚高峰特性指标计算结果

Table A3 Calculation results of morning-and-evening peak characteristic

表A4 日内用电规律中峰谷特性显现性指标计算结果

Table A4 Calculation results of peak-valley visibility characteristic

表A5 月用电相似度指标计算结果

Table A5 Calculation results of monthly electricity similarity

表A6 季度用电相似度指标计算结果

Table A6 Calculation results of quarterly electricity similarity

表A7 季节用电规律指标计算结果

Table A7 Calculation results of seasonal electricity similarity

表A8 用电平顺度标签各指标计算结果

Table A8 Calculation results of load smoothness label

表A9 疫情影响程度标签各指标计算结果

Table A9 Calculation results of epidemic impact degree

参考文献 20

[1]	栾开宁, 鲍敏, 易永仙, 等. 基于用电模式数的大用户负荷短期预测技术研究[J]. 电力工程技术, 2018,37(3):33-37.
	LUAN Kaining, BAO Min, YI Yongxian, et al. Study on short-term forecasting of large users load based on power consumption model numbers[J]. Electric Power Engineering Technology, 2018,37(3):33-37.
[2]	王珂, 姚建国, 姚良忠, 等. 电力柔性负荷调度研究综述[J]. 电力系统自动化, 2014,38(20):127-135. doi: 10.7500/AEPS20140422005 URL
	WANG Ke, YAO Jianguo, YAO Liangzhong, et al. Survey of research on flexible loads scheduling technologies[J]. Automation of Electric Power Systems, 2014,38(20):127-135.
[3]	刘洋, 高丽霞, 刘璐. 考虑样本不平衡的并行化用户负荷类型辨识方法[J]. 电网技术, 2020,44(11):4310-4317.
	LIU Yang, GAO Lixia, LIU Lu. Parallel load type identification algorithm considering sample class imbalance[J]. Power System Technology, 2020,44(11):4310-4317.
[4]	王成山, 孙充勃, 李鹏. 主动配电网优化技术研究现状及展望[J]. 电力建设, 2015,36(1):8-15.
	WANG Chengshan, SUN Chongbo, LI Peng. Review and perspective on the optimization of active distribution network[J]. Electric Power Construction, 2015,36(1):8-15.
[5]	张小斐, 魏玲, 王自强, 等. 基于负荷特性的大用户业扩辅助分析方法[J]. 电测与仪表, 2019,56(12):44-48, 84.
	ZHANG Xiaofei, WEI Ling, WANG Ziqiang, et al. Auxiliary analysis method of power supply access for large consumers based on load characteristics[J]. Electrical Measurement & Instrumentation, 2019,56(12):44-48, 84.
[6]	RAJABI A, ESKANDARI M, GHADI M J, et al. A comparative study of clustering techniques for electrical load pattern segmentation[J]. Renewable and Sustainable Energy Reviews, 2020,120:109628.
[7]	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.
	FANG Chao, ZHONG Chunlin, JI Cong. Analytical method of the industry which public transformers belong based on load data mining[J]. Electric Power Engineering Technology, 2018,37(5):115-120.
[8]	蔡学文. 负荷特性多维度分析方法与典型用户筛选策略研究[D]. 北京: 华北电力大学, 2013.
	CAI Xuewen. Research on load characteristics multi-dimension analysis method and typical consumers screening strategy[D]. Beijing: North China Electric Power University, 2013.
[9]	刘鹏. 基于Spark的数据管理平台的设计与实现[D]. 杭州: 浙江大学, 2016.
	LIU Peng. Design and implementation of data management platform based on Spark[D]. Hangzhou: Zhejiang University, 2016.
[10]	徐涛, 黄莉, 李敏蕾, 等. 基于多维细粒度行为数据的居民用户画像方法研究[J]. 电力需求侧管理, 2019,21(3):47-52, 58.
	XU Tao, HUANG Li, LI Minlei, et al. Research on portrait method of residential users based on multi-dimensional fine-grained behavior data[J]. Power Demand Side Management, 2019,21(3):47-52, 58.
[11]	王成亮, 郑海雁. 基于模糊聚类的电力客户用电行为模式画像[J]. 电测与仪表, 2018,55(18):77-81.
	WANG Chengliang, ZHENG Haiyan. A portrait of electricity consumption behavior mode of power users based on fuzzy clustering[J]. Electrical Measurement & Instrumentation, 2018,55(18):77-81.
[12]	傅军, 许鑫, 罗迪, 等. 电力用户行为画像构建技术研究[J]. 电气应用, 2018,37(13):18-23.
[13]	赵永柱, 马霁讴, 张可心. 基于电力资产全寿命周期的标签画像技术研究[J]. 电网与清洁能源, 2018,34(1):51-58.
	ZHAO Yongzhu, MA Ji’ou, ZHANG Kexin. Researchonthe label portrait technology basedon life cycleof electricity assets[J]. Power System and Clean Energy, 2018,34(1):51-58.
[14]	周光耀. 负荷建模中的负荷特性分类与综合方法的研究[D]. 济南: 山东大学, 2016.
	ZHOU Guangyao. Research on classification and synthesis method of load characteristics in load modeling[D]. Jinan: Shan Dong University, 2016.
[15]	翟娜娜. 基于用户需求响应的峰谷时段划分研究[D]. 北京: 华北电力大学, 2011.
	ZHAI Nana. Research on peak and valley time division based on user demand response[D]. Beijing: North China Electric Power University, 2011.
[16]	唐伟斌, 李涛, 邹品晶, 等. 基于皮尔逊相关系数的电网夏季空调负荷预测研究[J]. 电力需求侧管理, 2017,19(6):7-13.
	TANG Weibin, LI Tao, ZOU Pinjing, et al. Air-condition load forecasting in summer of power grid using Pearson correlation coefficient[J]. Power Demand Side Management, 2017,19(6):7-13.
[17]	罗滇生, 杜乾, 别少勇, 等. 基于负荷分解的居民差异化用电行为特性分析[J]. 电力系统保护与控制, 2016,44(21):29-33.
	LUO Diansheng, DU Qian, BIE Shaoyong, et al. Analysis of differentiation residential electricity consumption characteristic based on power load decomposition[J]. Power System Protection and Control, 2016,44(21):29-33.
[18]	欧阳森, 石怡理. 改进熵权法及其在电能质量评估中的应用[J]. 电力系统自动化, 2013,37(21):156-159, 164.
	OUYANG Sen, SHI Yili. A new improved entropy method and its application in power quality evaluation[J]. Automation of Electric Power Systems, 2013,37(21):156-159, 164.
[19]	孙洁, 王增平, 王英男, 等. 含分布式电源的复杂配电网故障恢复[J]. 电力系统保护与控制, 2014,42(2):56-62.
	SUN Jie, WANG Zengping, WANG Yingnan, et al. Service restoration of complex distribution system with distributed generation[J]. Power System Protection and Control, 2014,42(2):56-62.
[20]	张钦, 王锡凡, 王建学, 等. 电力市场下需求响应研究综述[J]. 电力系统自动化, 2008,32(3):97-106.
	ZHANG Qin, WANG Xifan, WANG Jianxue, et al. Survey of demand response research in deregulated electricity markets[J]. Automation of Electric Power Systems, 2008,32(3):97-106.