Early Warning Method for Electricity Safety Hazards in High-density Residential Communities Based on Electric Power Big Data

Wu Di; Lü Yuchen; Ye Liangbing; Liu Xu; Gong Liwu; Fu Chenyue

doi:10.13882/j.cnki.ncdqh.2606F004

English Version Journal Login

您当前的位置：

首页 >

文章列表页 >

Early Warning Method for Electricity Safety Hazards in High-density Residential Communities Based on Electric Power Big Data

更新时间：2026-10-07

- Early Warning Method for Electricity Safety Hazards in High-density Residential Communities Based on Electric Power Big Data
- Rural Electrification Issue 9, Pages: 80-85(2026)
- 作者机构：
  
  国网浙江省电力有限公司平湖市供电公司，浙江平湖,314200
- 作者简介：
- 基金信息：
- DOI：10.13882/j.cnki.ncdqh.2606F004
  CLC： TM763
- Published：2026
- 稿件说明：
移动端阅览
吴迪, 吕妤宸, 叶良兵, 柳旭, 龚利武, 傅辰玥. 基于电力大数据的高密度集居小区用电隐患预警方法[J]. 农村电气化, 2026, (9): 80-85.

Wu Di, Lü Yuchen, Ye Liangbing, et al. Early Warning Method for Electricity Safety Hazards in High-density Residential Communities Based on Electric Power Big Data[J]. Rural Electrification, 2026, (9): 80-85.
吴迪, 吕妤宸, 叶良兵, 柳旭, 龚利武, 傅辰玥. 基于电力大数据的高密度集居小区用电隐患预警方法[J]. 农村电气化, 2026, (9): 80-85. DOI： 10.13882/j.cnki.ncdqh.2606F004.

Wu Di, Lü Yuchen, Ye Liangbing, et al. Early Warning Method for Electricity Safety Hazards in High-density Residential Communities Based on Electric Power Big Data[J]. Rural Electrification, 2026, (9): 80-85. DOI： 10.13882/j.cnki.ncdqh.2606F004.

摘要

针对高密度集居小区因人口密集、用电需求激增导致的供电压力与安全隐患问题，文章提出了一种基于电力大数据的用电隐患预警方法。通过整合户均月用电量、户均容量、电量容量比值等多维指标，结合K-means聚类算法对辖域内小区的用电数据进行分析，划分出高密度集居、潜在风险、高负荷风险、高户数风险及低风险5种类别，构建差异化风险预警规则，并提出精准治理措施。

Abstract

To address power supply pressure and safety hazards in high-density residential communities caused by dense population and surging electricity demand

this paper proposes an early warning method for electricity safety hazards based on electric power big data. It integrates multidimensional indicators

including average monthly electricity consumption per household

average capacity per household

and the ratio of electricity consumption to capacity

and applies the K-means clustering algorithm to analyze electricity consumption data of communities within the service area. The communities are divided into five categories

including high-density residential community

potential risk

high-load risk

high household count risk

and low risk. Differentiated risk early warning rules are established

and targeted governance measures are proposed.

关键词

Keywords

references

宫德锋,于睿,董旭柱.智能配电技术创新成果报告[M].北京:中国水利水电出版社,2023.

马皓宸.基于期刊文献统计的我国城市更新发展演变研究[D].西安:西安建筑科技大学,2022.

刘莉,王刚,翟登辉.K-means聚类算法在负荷曲线分类中的应用[J].电力系统保护与控制,2011,39(23):65-68,73.

孙毅,毛烨华,李泽坤,等.面向电力大数据的用户负荷特性和可调节潜力综合聚类方法[J].中国电机工程学报,2021,41(18):6259-6270.

吕雪.基于时间序列聚类的独居老人用电行为模式分析[D].成都:西南财经大学,2022.

王小明.全景数字化配电网关键技术及示范应用[J].农村电气化,2025(11):49-53.

秦雷,敖刚,杨捷,等.数字化智能配电台区建构研究[J].农村电气化,2023(3):27-31.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Load Forecasting for Rural Feeders in Drought Periods Based on ‌User Behavior Profiling and Hybrid Models

Multidimensional Comparison and Decision Model of Transportation Modes for Mountainous Transmission Projects

Exploration of Transformer Fault Diagnosis and Condition Assessment Methods Based on Acoustic-vibration Signatures

Research on a Few-shot Fault Prediction Method for Transformers and High-voltage Circuit Breakers Based on Transfer Learning

Optimization Configuration Strategy for Distribution Network Graded Protection

Related Author

Weiyong CHEN

Yiwen LI

Aiguo YAN

Related Institution

State Grid Hubei Electric Power Co., Ltd.

AI问答

⁰