skip to main content
10.1145/3570236.3570280acmotherconferencesArticle/Chapter ViewAbstractPublication PagesiciipConference Proceedingsconference-collections
research-article

Detection of abnormal Electricity Consumption Behavior of Users Based on K-means Clustering Algorithm Fusion and Improved SVM

Published: 27 January 2023 Publication History

Abstract

As the energy internet continues to advance, the degree of informatization of the power system has been continuously improved. However, finding out users' abnormal electricity consumption behavior is particularly important when there is a large amount of data about electricity consumption. As a solution to the above problems, this paper proposes a model for detecting abnormal consumption patterns of power users using k-means clustering algorithm and improved SVM. As a result of the experimental results, the model is able to detect abnormal consumption patterns of electricity by users very well.

References

[1]
Ma Zhao, Zhou Xiaoxin, Shang Yuwei, Exploration of Energy Internet Concept, Key Technologies and Development Mode [J]. Power Grid Technology, 2015, 39(011):3014-3022.
[2]
Xiao Zeqing, Hua Haochen, Cao Junwei. A review of the application of artificial intelligence in energy internet [J]. Electric Power Construction, 2019(5):8.
[3]
Yu Xiaodan, Xu Xiandong, Chen Shuoyi, Brief introduction of integrated energy system and energy internet [J]. Journal of Electrotechnical Technology, 2016, 31(1):13.
[4]
Chen Qixin, Zheng Kedi, Kang Chongqing, Detection methods for abnormal power consumption: review and prospect [J]. Automation of Electric Power Systems, 2018, 42(17):11.
[5]
Li Pei, Hu Guoping, Huang Yaolian, Intelligent Identification of Suspected Users of Electricity Stealing in Distribution Network Based on Integrated ELM [J]. Science and Technology Bulletin, 2018.
[6]
Leite J B, Mantovani J . Detecting and Locating Non-technical Losses in Modern Distribution Networks[J]. IEEE Transactions on Smart Grid, 2018:1-1.
[7]
Yang Ting, Sun Zhaoshuai, Ji Hao, Power consumption data quality improvement algorithm based on matrix norm optimization theory [J]. Chinese Journal of Electrical Engineering, 2022, 42(10):11.
[8]
Han Xiaohong, Hu Yu. Research on K-means Clustering Algorithm[J]. Journal of Taiyuan University of Technology, 2009(3):4.
[9]
Chen Yongyi, Yu Xiaoding, Gao Xuehao, A New Method for Handling Nonlinear Classification and Regression Problems (I)–Introduction to Support Vector Machine Method [J]. Chinese Journal of Applied Meteorology, 2004, 015(003):345-354.
[10]
Hu J, Fichtner M, Baricco M . Preparation of Li-Mg-N-H hydrogen storage materials for an auxiliary power unit[J]. International Journal of Hydrogen Energy, 2017, 42(27):17144-17148.
[11]
Jia Z W, Wang L J, Zhang J C, High Efficiency, Low Power-Consumption DFB Quantum Cascade Lasers Without Lateral Regrowth.[J]. Springer US, 2017(1).
[12]
Xia Jing, Liang Wei, Wu Zhuying. Research on Automatic Identification Algorithm of Power Monitoring Abnormal Data Based on Moving Wavelet Tree [J]. Electronic Design Engineering, 2020, 28(18):5.
[13]
Zhou Taoli. Research on multi-classification method based on support vector machine [D]. University of Electronic Science and Technology of China.
[14]
Yan Chongxi, Chen Hao. Research on optimization of LSSVM short-term power load forecasting method based on improved beetle search algorithm [J]. Electrical Measurement and Instrumentation, 2020, 57(6):7.
[15]
Zhai Yuan. Research on power big data analysis technology and application based on cloud computing [J]. Electronic World, 2015(20):2.
[16]
Yu Xiang, Chen Guohong, Li Ting, Research on Anomaly Detection of Electricity Consumption Data Based on Isolation Forest Algorithm [J]. Information Technology, 2018, 42(12):5.
[17]
Zhou Cheng, He Renmu, Wang Chunhua. The influence of model structure on the generalization ability of load model[J]. Automation of Electric Power Systems, 2008, 32(14):5.
[18]
Wang Yong, Hu Baogang. Research on the Nonlinear Relationship between Normalized Information Gain Criterion and Accuracy, Precision and Recall[C]// National Conference on Pattern Recognition. 2009.
[19]
Wang Li, Guo Zhenhua, Cao Fang, Gao Kai, Zhao Yaqian, Zhao Kun. Automatic Generation of Model Splitting Strategy for Model Parallel Training [J]. Computer Engineering and Science, 2020, 42(9):9.
[20]
Koc C, Koc D G, Eminolu M B, Classification of hazelnut cultivars: comparison of DL4J ensemble learning algorithms[J]. Notulae Botanicae Horti Agrobotanici Cluj-Napoca, 2020, 48(4):2316-2327.
[21]
Guo, H.-B., Yue, X.-G., Lu, Y., Memonen, T., Xiao, F., Cañiv, M.V. Research on SOFMNN in coal and gas outburst safety prediction (2016) Recent Patents on Computer Science, 9 (1), pp. 55-61.
[22]
Yang, M., Chen, X., Wang, Y., Yue, X. Thermal oxidation kinetics analysis of ferrous sulfide under different heating rates (2016) Acta Technica CSAV (Ceskoslovensk Akademie Ved), 61 (4), pp. 19-28.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICIIP '22: Proceedings of the 7th International Conference on Intelligent Information Processing
September 2022
367 pages
ISBN:9781450396714
DOI:10.1145/3570236
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 27 January 2023

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. Abnormal Power Consumption by Users
  2. Detection Model
  3. Improve SVM
  4. K-means Clustering Algorithm

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICIIP '22

Acceptance Rates

Overall Acceptance Rate 87 of 367 submissions, 24%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 19
    Total Downloads
  • Downloads (Last 12 months)5
  • Downloads (Last 6 weeks)0
Reflects downloads up to 19 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media