Analysis of customers' electricity consumption behavior for peak load shifting

Bingxin WANG; Yan HOU; Hongwang FANG; Yuze CHEN; Jian LIU

doi:10.11959/j.issn.1000−0801.2017067

您当前的位置：

首页 >

文章列表页 >

Analysis of customers' electricity consumption behavior for peak load shifting

Power informatization column | 更新时间：2024-06-05

- Analysis of customers' electricity consumption behavior for peak load shifting
- Telecommunications Science Vol. 33, Issue 5, Pages: 164-170(2017)
- 作者机构：
  
  1. 国网福建省电力有限公司泉州供电公司，福建泉州 362000
  2. 北京中电普华信息技术有限公司，北京 100085
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000−0801.2017067
  CLC： TM732
- Published Online：2017-05，
  
  Published：15 May 2017
- 稿件说明：
移动端阅览
Bingxin WANG, Yan HOU, Hongwang FANG, et al. Analysis of customers' electricity consumption behavior for peak load shifting[J]. Telecommunications science, 2017, 33(5): 164-170.
DOI：

Bingxin WANG, Yan HOU, Hongwang FANG, et al. Analysis of customers' electricity consumption behavior for peak load shifting[J]. Telecommunications science, 2017, 33(5): 164-170. DOI： 10.11959/j.issn.1000−0801.2017067.

摘要

为对海量电力客户实施有针对性的“削峰填谷”措施，提出了一种面向“削峰填谷”的海量电力客户用电行为分析方法。首先，利用聚类算法对国网某省公司主网一年的日负荷曲线数据进行聚类分析，得到不同时期主网的负荷特征。然后，分别对每个时期下所有电力客户的日负荷曲线数据进行聚类分析，得到不同主网特征下用户群体的负荷特征，对比主网和用户的负荷特征得到用户群体的“削峰填谷”模式。最后，利用动态时间规整算法将未来日期与历史日期进行匹配，得到未来日期用户群体的“削峰填谷”模式。实证研究表明，分析结果可以为有序用电、峰谷电价等公司决策提供更有针对性的参考依据，以更进一步实现配电网负荷的“削峰填谷”和平稳运行。

Abstract

In order to implement well-directed peak load shifting for massive customers

a method for analyzing massive customers' electricity consumption behavior for peak load shifting was proposed.Firstly

clustering algorithm was used to cluster daily load curves of the main power grid in the previous year and get load characteristics in different dates.Then the load curves of all customers under every date cluster were clustered

the peak load shifting method was derived by comparing the load characteristics of the main power grid and customers.Finally

the peak load shifting method in a future day was given by date matching between the future day with a historical day using dynamic time warping (DTW).Empirical study shows that the method is conductive to peak-valley electricity pricing and orderly electricity consump-tion and can further achieve peak load shifting and stable operation of the main power grid.

关键词

Keywords

references

何永秀，王冰，熊威，等 . 基于模糊综合评价的居民智能用电行为分析与互动机制设计 [J ] . 电网技术， 2012 , 36 ( 10 ): 247 - 252 .

HE Y X , WANG B , XIONG W , et al . Analysis of residents' smart electricity consumption behavior based on fuzzy synthetic evaluation and the design of interactive mechanism [J ] . Power System Technology , 2012 , 36 ( 10 ): 247 - 252 .

黄瀚 . 智能用电中的客户行为分析 [J ] . 电气时代， 2014 ( 14 ): 28 - 32 .

HUANG H . Analysis of smart electricity consumption beha-vior [J ] . Electric Age , 2014 ( 14 ): 28 - 32 .

CHUAN L , UKIL A . Modeling and validation of electrical load profiling in residential buildings in Singapore [J ] . IEEE Trans-actions on Power Systems , 2015 , 30 ( 5 ): 2800 - 2809 .

ABREUA J M , PEREIRAB F C , FRRAO P . Using pattern recognition to identify habitual behavior in residential electrici-ty consumption [J ] . Energy and Buildings , 2012 , 49 ( 2 ): 479 - 487 .

宗柳，李扬，王蓓蓓 . 计及需求响应的多维度用电特征精细挖掘 [J ] . 电力系统自动化， 2012 , 36 ( 20 ): 54 - 58 .

ZONG L , LI Y , WANG B B . Fine-mining of multi-dimension electrical characteristics considering demand response [J ] . Au-tomation of Electric Power Systems , 2012 , 36 ( 20 ): 54 - 58 .

瞿海妮，张鹏飞，凌平，等 . 基于海量数据的电网需求侧用户行为分析研究 [J ] . 华东电力， 2014 , 42 ( 12 ): 2922 - 2925 .

QU H N , ZHANG P F , LING P , et al . Analysis of consumption behavior in power demand side based on massive data [J ] . East China Electric Power , 2014 , 42 ( 12 ): 2922 - 2925 .

张素香，刘建明，赵丙镇，等 . 基于云计算的居民用电行为分析模型研究 [J ] . 电网技术， 2013 , 37 ( 6 ): 1542 - 1546 .

ZHANG S X , LIU J M , ZHAO B Z , et al . Cloud compu-ting-based analysis on residential electricity consumption beha-vior [J ] . Power System Technology , 2013 , 37 ( 6 ): 1542 - 1546 .

HIDOT S , SAINT-JEAN C . An expectation-maximization algo-rithm for the wishart mixture model:application to movement clus-tering [J ] . Pattern Recognition Letters , 2010 , 31 ( 14 ): 2318 - 2324 .

JOLLOIS F X , NADIF M . Speed-up for the expecta-tion-maximization algorithm for clustering categorical data [J ] . Global Optimization , 2007 , 37 ( 4 ): 513 - 525 .

HOFMANS J , CEULEMANS E , STEINLEY D , et al . On the added value of bootstrap analysis for K-means clustering [J ] . Classification , 2015 , 32 ( 2 ): 268 - 284 .

GARCIA M L L , GARCIA-RODENAS R , GOMEZ A G . K-means algorithms for functional data [J ] . Neurocomputing , 2015 ( 151 ): 231 - 245 .

李小武，邵剑飞，廖秀玲 . 一种基于 K-means 的分布式聚类算法 [J ] . 桂林电子科技大学学报， 2011 , 31 ( 6 ): 460 - 463 .

LI X W , SHAO J F , LIAO X L . A distributed clustering algo-tithm based on K-means algorithm [J ] . Journal of Guilin Univer-sity of Electronic Technology , 2011 , 31 ( 6 ): 460 - 463 .

ARRIBAS-GIL A,HANS-GEORM . Pairwise dynamic time warping for event data [J ] . Computational Statistics＆Data Analysis , 2014 ( 69 ): 255 - 268 .

RASHIDI S , FALLAH A , TOWHIDKHAH F . Similarity evalua-tion of online signatures based on modified dynamic time warp-ing [J ] . Applied Artificial Intelligence , 2013 , 27 ( 7 ): 599 - 617 .

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Vibe++ background segmentation method combining MeanShift clustering analysis and convolutional neural network

Related Author

Zihao LIU

Xiaojun JIA

Sulan ZHANG

Zhiling XU

Jun ZHANG

Related Institution

College of Mathematics Physics and Information Engineering, Jiaxing University

College of Quality ＆Safty Engineering, China Jiliang University

College of Biosystems Engineering and Food Science, Zhejiang University

⁰