Detection of anomalous consumers based on smart meter data

• Autorzy: Kaleta Joanna , Dubinski Jan , Wojdan Konrad , Swirski Konrad
• Języki publikacji: EN

Abstrakty

EN

The continuous smart grid development makes the advanced metering infrastructure an essential part of electricity management systems. Smart meters not only provide consumers with more economical and sustainable electricity consumption but also enable the energy supplier to identify suspicious behaviour or meter failure. In this work, a shape-based algorithm that indicates households with abnormal electricity consumption pattern within a given consumer group was proposed. The algorithm was developed under the assumption that the reason for unusual electricity consumption may not only be a meter failure or fraud, but also consumer’s individual preferences and lifestyle. In the presented methodology, five unsupervised anomaly detection methods were used: K Nearest Neighbors, Local Outlier Factor, Principal Component Analysis, Isolation Forest and Histogram Based Outlier Score. Two time series similarity measures were applied: basic Euclidean distance and Dynamic Time Warping, which allows finding the best alignment between two time series. The algorithm’s performance was tested with multiple parameter configurations on five different consumer groups. Additionally, an analysis of the individual types of anomalies and their detectability by the algorithm was performed.

Słowa kluczowe

EN

electric energy usage; smart grid; smart meter

PL

zużycie energii elektrycznej; inteligentne sieci; inteligentny licznik

• Wydawca: Institute of Heat Engineering, Warsaw University of Technology
• Czasopismo: Journal of Power Technologies
• Rocznik: 2021
• Tom: Vol. 101, nr 4
• Strony: 202--212
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Kaleta Joanna

• Institute of Heat Engineering, Warsaw University of Technology, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland

autor

Dubinski Jan

• Institute of Heat Engineering, Warsaw University of Technology, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland
• Institute of Computer Science, Warsaw University of Technology, 15/19 Nowowiejska Street, 00-665 Warsaw, Poland

autor

Wojdan Konrad

• Institute of Heat Engineering, Warsaw University of Technology, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland

autor

Swirski Konrad

• Institute of Heat Engineering, Warsaw University of Technology, 21/25 Nowowiejska Street, 00-665 Warsaw, Poland

Bibliografia

• [1] Institute for Renewable Energy EC BREC. Photovoltaic market in Poland 2021, 2021.
• [2] Northeast Group, LLC. Electricity Theft and Non-Technical Losses: Global Markets, Solutions, and Vendors, 2017.
• [3] Alexander Lavin and Diego Klabjan. Clustering time-series energy data from smart meters. Energy Efficiency, 8(4):681–689, nov 2014. DOI: 10.1007/s12053-014-9316-0.
• [4] Teemu Räsänen, Dimitrios Voukantsis, Harri Niska, Kostas Karatzas, and Mikko Kolehmainen. Data-based method for creating electricity use load profiles using large amount of customer-specific hourly measured electricity use data. Applied Energy, 87(11):3538–3545, nov 2010. DOI: 10.1016/j.apenergy.2010.05.015.
• [5] Thanchanok Teeraratkul, Daniel O'Neill, and Sanjay Lall. Shape-Based Approach to Household Electric Load Curve Clustering and Prediction. IEEE Transactions on Smart Grid, 9(5):5196–5206, sep 2018. DOI: 10.1109/tsg.2017.2683461.
• [6] William Hurst, Casimiro A. Curbelo Montañez, and Nathan Shone. Time-Pattern Profiling from Smart Meter Data to Detect Outliers in Energy Consumption. IoT, 1(1):92–108, sep 2020. DOI: 10.3390/iot1010006.
• [7] Ankur Sial, Amarjeet Singh, and Aniket Mahanti. Detecting anomalous energy consumption using contextual analysis of smart meter data. Wireless Networks, 27(6):4275–4292, jul 2019. DOI: 10.1007/s11276-019-02074-8.
• [8] Acorn - The smarter consumer classification - CACI, 2013. https://acorn.caci.co.uk/. Accessed on Tue, September 14, 2021.
• [9] Appendix on reproducibility, 2021. https://github.com/joaxkal/smart-metersanomalous-consumers.
• [10] Yue Zhao, Zain Nasrullah, and Zheng Li. PyOD: A Python Toolbox for Scalable Outlier Detection. Journal of Machine Learning Research, 20(96):1-7, 2019. http://jmlr.org/papers/v20/19-011.html.
• [11] Peng Yang and Biao Huang. KNN Based Outlier Detection Algorithm in Large Dataset. In 2008 International Workshop on Education Technology and Training & 2008 International Workshop on Geoscience and Remote Sensing. IEEE, dec 2008. DOI: 10.1109/ettandgrs.2008.306.
• [12] Markus M. Breunig, Hans-Peter Kriegel, Raymond T. Ng, and Jörg Sander. LOF: Identifying Density-Based Local Outliers. ACM SIGMOD Record, 29(2):93–104, jun 2000. DOI: 10.1145/335191.335388.
• [13] Mei-Ling Shyu, Shu-Ching Chen, Kanoksri Sarinnapakorn, and Liwu Chang. A Novel Anomaly Detection Scheme Based on Principal Component Classifier. 01 2003.
• [14] Fei Tony Liu, Kai Ming Ting, and Zhi-Hua Zhou. Isolation-Based Anomaly Detection. ACM Transactions on Knowledge Discovery from Data, 6(1):1-39, mar 2012. DOI: 10.1145/2133360.2133363.
• [15] Markus Goldstein and Andreas Dengel. Histogram-based Outlier Score (HBOS): A fast Unsupervised Anomaly Detection Algorithm. KI-2012: Poster and Demo Track, 09 2012.
• [16] H. Sakoe and S. Chiba. Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics Speech, and Signal Processing, 26(1):43-49, feb 1978. DOI: 10.1109/tassp.1978.1163055.
• [17] Chotirat Ann Ratanamahatana and Eamonn Keogh. Making Time-series Classification More Accurate Using Learned Constraints. In Proceedings of the 2004 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics, apr 2004. DOI: 10.1137/1.9781611972740.2.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2021).