IDEAS home Printed from https://ideas.repec.org/a/gam/jeners/v12y2019i16p3144-d258038.html
   My bibliography  Save this article

AUD-MTS: An Abnormal User Detection Approach Based on Power Load Multi-Step Clustering with Multiple Time Scales

Author

Listed:
  • Rongheng Lin

    (State Key Lab of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China)

  • Fangchun Yang

    (State Key Lab of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China)

  • Mingyuan Gao

    (State Key Lab of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China)

  • Budan Wu

    (State Key Lab of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China)

  • Yingying Zhao

    (State Key Lab of Networking and Switching Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China)

Abstract

With the rapid growth of Smart Grid, electricity load analysis has become the simplest and most effective way to divide user groups and understand user behavior. This paper proposes an AUD-MTS (Abnormal User Detection approach based on power load multi-step clustering with Multiple Time Scales). Firstly, we combine RBM (Restricted Boltzmann Machine) hidden feature learning with K-Means clustering to extract typical load patterns in the short-term. Secondly, time scale conversion is performed so that the analysis subject can be transformed from load pattern to user behavior. Finally, a two-step clustering in long-term is adopted to divide users from both coarse-grained and fine-grained dimensions so as to detect abnormal users referring to customized OutlierIndex. Experiments are conducted using annual 24-point power load data of American users in all states. The accuracy of clustering methods in AUD-MTS reaches 87.5% referring to the 16 commercial building types defined by the U.S. Department of Energy, which outperforms other common clustering algorithms on AMI (Advanced Metering Infrastructure). After that, the OutlierIndex score of AUD-MTS can be increased by 0.16 compared with other outlier detection algorithms, which shows that the proposed method can detect abnormal users precisely and efficiently. Furthermore, we summarized possible causes including federal holidays, climate zones and summertime that may lead to abnormal behavior changes and discussed countermeasures respectively, which accounts for 82.3% of anomalies. The rest may be potential electricity stealing users, which requires further investigation.

Suggested Citation

  • Rongheng Lin & Fangchun Yang & Mingyuan Gao & Budan Wu & Yingying Zhao, 2019. "AUD-MTS: An Abnormal User Detection Approach Based on Power Load Multi-Step Clustering with Multiple Time Scales," Energies, MDPI, vol. 12(16), pages 1-19, August.
  • Handle: RePEc:gam:jeners:v:12:y:2019:i:16:p:3144-:d:258038
    as

    Download full text from publisher

    File URL: https://www.mdpi.com/1996-1073/12/16/3144/pdf
    Download Restriction: no

    File URL: https://www.mdpi.com/1996-1073/12/16/3144/
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Viegas, Joaquim L. & Vieira, Susana M. & Melício, R. & Mendes, V.M.F. & Sousa, João M.C., 2016. "Classification of new electricity customers based on surveys and smart metering data," Energy, Elsevier, vol. 107(C), pages 804-817.
    2. Blumsack, Seth & Fernandez, Alisha, 2012. "Ready or not, here comes the smart grid!," Energy, Elsevier, vol. 37(1), pages 61-68.
    3. Gouveia, João Pedro & Seixas, Júlia & Mestre, Ana, 2017. "Daily electricity consumption profiles from smart meters - Proxies of behavior for space heating and cooling," Energy, Elsevier, vol. 141(C), pages 108-122.
    4. Villar-Rodriguez, Esther & Del Ser, Javier & Oregi, Izaskun & Bilbao, Miren Nekane & Gil-Lopez, Sergio, 2017. "Detection of non-technical losses in smart meter data based on load curve profiling and time series analysis," Energy, Elsevier, vol. 137(C), pages 118-128.
    5. McLoughlin, Fintan & Duffy, Aidan & Conlon, Michael, 2015. "A clustering approach to domestic electricity load profile characterisation using smart metering data," Applied Energy, Elsevier, vol. 141(C), pages 190-199.
    6. Wang, Jianzhou & Xiong, Shenghua, 2014. "A hybrid forecasting model based on outlier detection and fuzzy time series – A case study on Hainan wind farm of China," Energy, Elsevier, vol. 76(C), pages 526-541.
    7. Ma, Zhenjun & Yan, Rui & Nord, Natasa, 2017. "A variation focused cluster analysis strategy to identify typical daily heating load profiles of higher education buildings," Energy, Elsevier, vol. 134(C), pages 90-102.
    8. Kovacic, Zora & Giampietro, Mario, 2015. "Empty promises or promising futures? The case of smart grids," Energy, Elsevier, vol. 93(P1), pages 67-74.
    9. Jalón, María L. & Baquerizo, Asunción & Losada, Miguel A., 2016. "Optimization at different time scales for the design and management of an oscillating water column system," Energy, Elsevier, vol. 95(C), pages 110-123.
    10. Capozzoli, Alfonso & Piscitelli, Marco Savino & Brandi, Silvio & Grassi, Daniele & Chicco, Gianfranco, 2018. "Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings," Energy, Elsevier, vol. 157(C), pages 336-352.
    11. Chicco, Gianfranco, 2012. "Overview and performance assessment of the clustering methods for electrical load pattern grouping," Energy, Elsevier, vol. 42(1), pages 68-80.
    12. Pan, Zhaoguang & Guo, Qinglai & Sun, Hongbin, 2016. "Interactions of district electricity and heating systems considering time-scale characteristics based on quasi-steady multi-energy flow," Applied Energy, Elsevier, vol. 167(C), pages 230-243.
    13. Ahmad, Tanveer & Chen, Huanxin, 2018. "Potential of three variant machine-learning models for forecasting district level medium-term and long-term energy demand in smart grid environment," Energy, Elsevier, vol. 160(C), pages 1008-1020.
    14. Huang, Shupei & An, Haizhong & Wen, Shaobo & An, Feng, 2017. "Revisiting driving factors of oil price shocks across time scales," Energy, Elsevier, vol. 139(C), pages 617-629.
    15. Bishnu P. Bhattarai & Kurt S. Myers & Birgitte Bak-Jensen & Sumit Paudyal, 2017. "Multi-Time Scale Control of Demand Flexibility in Smart Distribution Networks," Energies, MDPI, vol. 10(1), pages 1-18, January.
    16. Yu, Zhun (Jerry) & Haghighat, Fariborz & Fung, Benjamin C.M. & Morofsky, Edward & Yoshino, Hiroshi, 2011. "A methodology for identifying and improving occupant behavior in residential buildings," Energy, Elsevier, vol. 36(11), pages 6596-6608.
    17. Abdon, Andreas & Zhang, Xiaojin & Parra, David & Patel, Martin K. & Bauer, Christian & Worlitschek, Jörg, 2017. "Techno-economic and environmental assessment of stationary electricity storage technologies for different time scales," Energy, Elsevier, vol. 139(C), pages 1173-1187.
    Full references (including those not matched with items on IDEAS)

    Citations

    Citations are extracted by the CitEc Project, subscribe to its RSS feed for this item.
    as


    Cited by:

    1. Tomasz Śmiałkowski & Andrzej Czyżewski, 2022. "Detection of Anomalies in the Operation of a Road Lighting System Based on Data from Smart Electricity Meters," Energies, MDPI, vol. 15(24), pages 1-23, December.

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Li, Kehua & Yang, Rebecca Jing & Robinson, Duane & Ma, Jun & Ma, Zhenjun, 2019. "An agglomerative hierarchical clustering-based strategy using Shared Nearest Neighbours and multiple dissimilarity measures to identify typical daily electricity usage profiles of university library b," Energy, Elsevier, vol. 174(C), pages 735-748.
    2. Trotta, Gianluca, 2020. "An empirical analysis of domestic electricity load profiles: Who consumes how much and when?," Applied Energy, Elsevier, vol. 275(C).
    3. Capozzoli, Alfonso & Piscitelli, Marco Savino & Brandi, Silvio & Grassi, Daniele & Chicco, Gianfranco, 2018. "Automated load pattern learning and anomaly detection for enhancing energy management in smart buildings," Energy, Elsevier, vol. 157(C), pages 336-352.
    4. Li, Kehua & Ma, Zhenjun & Robinson, Duane & Ma, Jun, 2018. "Identification of typical building daily electricity usage profiles using Gaussian mixture model-based clustering and hierarchical clustering," Applied Energy, Elsevier, vol. 231(C), pages 331-342.
    5. Zhan, Sicheng & Liu, Zhaoru & Chong, Adrian & Yan, Da, 2020. "Building categorization revisited: A clustering-based approach to using smart meter data for building energy benchmarking," Applied Energy, Elsevier, vol. 269(C).
    6. Tang, Rui & Yildiz, Baran & Leong, Philip H.W. & Vassallo, Anthony & Dore, Jonathon, 2019. "Residential battery sizing model using net meter energy data clustering," Applied Energy, Elsevier, vol. 251(C), pages 1-1.
    7. Rajabi, Amin & Eskandari, Mohsen & Ghadi, Mojtaba Jabbari & Li, Li & Zhang, Jiangfeng & Siano, Pierluigi, 2020. "A comparative study of clustering techniques for electrical load pattern segmentation," Renewable and Sustainable Energy Reviews, Elsevier, vol. 120(C).
    8. Yilmaz, S. & Chambers, J. & Patel, M.K., 2019. "Comparison of clustering approaches for domestic electricity load profile characterisation - Implications for demand side management," Energy, Elsevier, vol. 180(C), pages 665-677.
    9. Yang, Ting & Ren, Minglun & Zhou, Kaile, 2018. "Identifying household electricity consumption patterns: A case study of Kunshan, China," Renewable and Sustainable Energy Reviews, Elsevier, vol. 91(C), pages 861-868.
    10. Roberts, Mike B. & Haghdadi, Navid & Bruce, Anna & MacGill, Iain, 2019. "Characterisation of Australian apartment electricity demand and its implications for low-carbon cities," Energy, Elsevier, vol. 180(C), pages 242-257.
    11. Gouveia, João Pedro & Seixas, Júlia & Mestre, Ana, 2017. "Daily electricity consumption profiles from smart meters - Proxies of behavior for space heating and cooling," Energy, Elsevier, vol. 141(C), pages 108-122.
    12. Xavier Serrano-Guerrero & Guillermo Escrivá-Escrivá & Santiago Luna-Romero & Jean-Michel Clairand, 2020. "A Time-Series Treatment Method to Obtain Electrical Consumption Patterns for Anomalies Detection Improvement in Electrical Consumption Profiles," Energies, MDPI, vol. 13(5), pages 1-23, February.
    13. Zhou, Kaile & Yang, Changhui & Shen, Jianxin, 2017. "Discovering residential electricity consumption patterns through smart-meter data mining: A case study from China," Utilities Policy, Elsevier, vol. 44(C), pages 73-84.
    14. Wen, Hanguan & Liu, Xiufeng & Yang, Ming & Lei, Bo & Xu, Cheng & Chen, Zhe, 2024. "A novel approach for identifying customer groups for personalized demand-side management services using household socio-demographic data," Energy, Elsevier, vol. 286(C).
    15. Rongheng Lin & Budan Wu & Yun Su, 2018. "An Adaptive Weighted Pearson Similarity Measurement Method for Load Curve Clustering," Energies, MDPI, vol. 11(9), pages 1-17, September.
    16. Gianluca Trotta & Kirsten Gram-Hanssen & Pernille Lykke Jørgensen, 2020. "Heterogeneity of Electricity Consumption Patterns in Vulnerable Households," Energies, MDPI, vol. 13(18), pages 1-17, September.
    17. Yildiz, B. & Bilbao, J.I. & Dore, J. & Sproul, A.B., 2017. "Recent advances in the analysis of residential electricity consumption and applications of smart meter data," Applied Energy, Elsevier, vol. 208(C), pages 402-427.
    18. Russo, Marianna & Bertsch, Valentin, 2020. "A looming revolution: Implications of self-generation for the risk exposure of retailers," Energy Economics, Elsevier, vol. 92(C).
    19. Li, Lanlan & Ming, Huayang & Fu, Weizhong & Shi, Quan & Yu, Shiwei, 2021. "Exploring household natural gas consumption patterns and their influencing factors: An integrated clustering and econometric method," Energy, Elsevier, vol. 224(C).
    20. Grillone, Benedetto & Mor, Gerard & Danov, Stoyan & Cipriano, Jordi & Sumper, Andreas, 2021. "A data-driven methodology for enhanced measurement and verification of energy efficiency savings in commercial buildings," Applied Energy, Elsevier, vol. 301(C).

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:gam:jeners:v:12:y:2019:i:16:p:3144-:d:258038. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: MDPI Indexing Manager (email available below). General contact details of provider: https://www.mdpi.com .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.