Abstract
Energy consumption is dependent on temperature, humidity, occupancy, occupant type, building area etc. All these factors collectively define the context of an energy meter. Once the context is known, the meters within the same context can be grouped and their behaviour can be analyzed together. This paper presents four heuristics, including one novel heuristic, to identify abnormal energy consumption. Using these heuristics, data collected from fifty smart meters deployed inside hostels of IIIT-Delhi was investigated for abnormal energy consumption detection. The anomalies and possible causes were discussed with IIIT-Delhi campus administrator. Energy consumption per occupant for one of the meters was found four times when compared to rest of the meters. The results demonstrated that the proposed heuristics successfully found abnormal energy consumption behaviour.
Similar content being viewed by others
References
Araya, D., Grolinger, K., ElYamany, H., Capretz, M., & Bitsuamlak, G. (2016). Collective contextual anomaly detection framework for smart buildings. In Proceedings of the international joint conference on neural networks.
Saad, A., & Sisworahardjo, N. (2017). Data analytics-based anomaly detection in smart distribution network. In Proceedings of the international conference on high voltage engineering and power system.
Rossi, B., Chren, S., Buhnova, B., Pitner, T. (2016). Anomaly detection in smart grid data: An experience report. In Proceedings of the IEEE international conference on systems, man, and cybernetics.
Ponocko, J., & Milanovic, J. (2017). Application of data analytics for advanced demand profiling of residential load using smart meter data. In Proceedings of the IEEE PowerTech conference.
Chandola, V., Banerjee, A., & Kumar, V. (2012). Anomaly detection for discrete sequences: A survey. IEEE Transactions on Knowledge and Data Engineering, 24(5), 823–839.
Chen, C., & Cook, D. (2011). Energy outlier detection in smart environments. In Artificial intelligence and smarter living 11.
Seem, J. (2007). Using intelligent data analysis to detect abnormal energy consumption in buildings. Energy and Buildings, 39(1), 52–58.
Bellala, G., Marwah, M., Arlitt, M., Lyon, G., & Bash, C. (2011). Towards an understanding of campus-scale power consumption. In Proceedings of the ACM workshop on embedded sensing systems for energy-efficiency in buildings.
Bellala, G., Marwah, M., Arlitt, M., Lyon, G., & Bash, C. (2012). Following the electrons: Methods for power management in commercial buildings. In Proceedings of the ACM SIGKDD international conference on knowledge discovery and data mining.
Fontugne, R., Ortiz, J., Tremblay, N., Borgnat, P., Flandrin, P., Fukuda, K., Culler, D., & Esaki, H. (2013). Strip, bind, and search: A method for identifying abnormal energy consumption in buildings. In Proceedings of the international conference on information processing in sensor networks.
Ismail, A., Abdullah, A., Bak, K., Ngadi, Md., Dahlan, D., & Chimphlee, W. (2008). A novel method for unsupervised anomaly detection using unlabelled data. In Proceedings of the international conference on computational sciences and its applications.
Qiu, H., Liu, Y., Subrahmanya, N., & Li, W. (2012). Granger causality for time-series anomaly detection. In Proceedings of the international conference on data mining.
Yip, S., Tan, W., Tan, C., Gan, M., & Wong, K. (2018). An anomaly detection framework for identifying energy theft and defective meters in smart grids. International Journal of Electrical Power and Energy Systems, 101, 189–203.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sial, A., Singh, A. & Mahanti, A. Detecting anomalous energy consumption using contextual analysis of smart meter data. Wireless Netw 27, 4275–4292 (2021). https://doi.org/10.1007/s11276-019-02074-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11276-019-02074-8