Predictive Fraud Detection: An Intelligent Method for Internet of Smart Grid Things Systems
Keywords:Smart Grid, Non-technical losses, Ensemble, TSC, Edge Computing
Today, grid resilience as a feature has become non-negotiable, significantly when power interruptions can impact the economy. The widespread popularity of Intelligent Electronic Devices (IED) operating as smart meters enables an immense amount of fine-grained electricity consumption data to be collected. However, risk can still exist in the Smart Grid (SG), as valuable data are exchanged among SG systems; theft or alteration of this data could violate consumer privacy. The Internet of Things for Smart Grid (IoSGT) is a promising ecosystem of different technologies that coordinate with each other to pave the way for new SG applications and services. As a use case of IoSGT for future SG applications and services, fraud detection, ıNon-technical losses (NTL), emerges as an important application for Smart Grid (SG) scenarios. A substantial amount of electrical energy is lost throughout the distribution system, and these losses are divided into two types: technical and non-technical. Non-technical losses (NTL) are any electrical energy consumed and not invoiced. They may occur due to illegal connections, issues with energy meters such as delay in the installation or reading errors, contaminated, defective, or non-adapted measuring equipment, very low valid consumption estimates, faulty connections, and disregarded customers. Non-technical losses are the primary cause of revenue loss in the SG. According to a recent study, electrical utilities lose $89.3 Billion per year due to non-technical losses. This article proposes ensemble predictor-based time series classifiers for NTL detection. The proposed predictor ministers the user’s energy consumption as a data input for classification, from splitting the data to executing the classifier.It encompasses the temporal aspects of energy consumption data during preprocessing, training, testing, and validation stages. The suggested predictor is Time Series (TS) oriented, from data splitting to the classifier’s performance. Overall, our best results have been recorded in the fraud detection-based time series classifiers (TSC) model scoring an improvement in the empirical performance metrics by 10% or more over the other developed models.
Araujo, F., Araújo, F., Machado, K., Rosário, D., Cerqueira, E., and Villas, L. (2020). Ensemble mobility predictor based on random forest and markovian property using lbsn data. Journal of Internet Services and Applications, 11. DOI: 10.1186/s13174-020-00130-7.
Archive, I. S. S. D. (2012). Commission for energy regulation (cer) smart metering project - electricity customer behaviour trial, 2009-2010 [dataset]. Available online [link].
Barja-Martinez, S., Aragüés-Peñalba, M., Íngrid Munné-Collado, Lloret-Gallego, P., Bullich-Massagué, E., and Villafafila-Robles, R. (2021). Artificial intelligence techniques for enabling big data services in distribution networks: A review. Renewable and Sustainable Energy Reviews, 150:111459. DOI: 10.1016/j.rser.2021.111459.
Belhadi, A., Djenouri, Y., Djenouri, D., Srivastava, G., and Lin, J. C.-W. (2022). Group intrusion detection in the internet of things using a hybrid recurrent neural network. Cluster Computing, pages 1-12. DOI: s10586-022-03779-w.
Belhadi, A., Djenouri, Y., Srivastava, G., Djenouri, D., Lin, J. C.-W., and Fortino, G. (2021a). Deep learning for pedestrian collective behavior analysis in smart cities: A model of group trajectory outlier detection. Information Fusion, 65:13-20. DOI: 10.1016/j.inffus.2020.08.003.
Belhadi, A., Djenouri, Y., Srivastava, G., Jolfaei, A., and Lin, J. C.-W. (2021b). Privacy reinforcement learning for faults detection in the smart grid. Ad Hoc Networks, 119:102541. DOI: 10.1016/j.adhoc.2021.102541.
Chevyrev, I. and Kormilitzin, A. (2016). A primer on the signature method in machine learning. DOI: 10.48550/arXiv.1603.03788.
Chuwa, M. G. and Wang, F. (2021). A review of non-technical loss attack models and detection methods in the smart grid. Electric Power Systems Research, 199:107415. DOI: 10.1016/j.epsr.2021.107415.
de Souza, M. A., Pereira, J. L., Alves, G. d. O., de Oliveira, B. C., Melo, I. D., and Garcia, P. A. (2020). Detection and identification of energy theft in advanced metering infrastructures. Electric Power Systems Research, 182:106258. DOI: 10.1016/j.epsr.2020.106258.
de Souza Savian, F., Siluk, J. C. M., Garlet, T. B., do Nascimento, F. M., Pinheiro, J. R., and Vale, Z. (2021). Non-technical losses: A systematic contemporary article review. Renewable and Sustainable Energy Reviews, 147:111205. DOI: 10.1016/j.rser.2021.111205.
Dempster, A., Petitjean, F., and Webb, G. I. (2020). Rocket: exceptionally fast and accurate time series classification using random convolutional kernels. Data Mining and Knowledge Discovery, 34(5):1454-1495. DOI: 10.1007/s10618-020-00701-z.
Deng, D., Li, J., Jhaveri, R. H., Tiwari, P., Ijaz, M. F., Ou, J., and Fan, C. (2022). Reinforcement learning based optimization on energy efficiency in uav networks for iot. IEEE Internet of Things Journal. DOI: 10.1109/JIOT.2022.3214860.
Deng, H., Runger, G., Tuv, E., and Vladimir, M. (2013). A time series forest for classification and feature extraction. Information Sciences, 239:142-153. DOI: 10.1016/j.ins.2013.02.030.
Fersini, E., Messina, E., and Pozzi, F. (2014). Sentiment analysis: Bayesian ensemble learning. Decision Support Systems, 68:26-38. DOI: 10.1016/j.dss.2014.10.004.
Gunturi, S. K. and Sarkar, D. (2021). Ensemble machine learning models for the detection of energy theft. Electric Power Systems Research, 192:106904. DOI: 10.1016/j.epsr.2020.106904.
Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 2nd Edition. O'Reilly Media, Inc. Book.
Jokar, P., Arianpoo, N., and Leung, V. C. M. (2016). Electricity theft detection in ami using customers’ consumption patterns. IEEE Transactions on Smart Grid, 7(1):216-226. DOI: 10.1109/TSG.2015.2425222.
Krishna, V. B., Lee, K., Weaver, G. A., Iyer, R. K., and Sanders, W. H. (2016). F-deta: A framework for detecting electricity theft attacks in smart grids. In 2016 46th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), pages 407-418. DOI: 10.1109/DSN.2016.44.
Lobato, E., Prazeres, L., Medeiros, I., Araújo, F., Rosário, D., Cerqueira, E., Tostes, M., Bezerra, U., Fonseca, W., and Antloga, A. (2023). A monitoring system for electric vehicle charging stations: A prototype in the amazon. Energies, 16(1):152. DOI: 10.3390/en16010152.
Löning, M., Bagnall, A., Ganesh, S., Kazakov, V., Lines, J., and Király, F. J. (2019). sktime: A unified interface for machine learning with time series. arXiv preprint arXiv:1909.07872. DOI: 10.48550/arXiv.1909.07872.
Lubba, C. H., Sethi, S. S., Knaute, P., Schultz, S. R., Fulcher, B. D., and Jones, N. S. (2019). catch22: Canonical time-series characteristics. Data Mining and Knowledge Discovery, 33(6):1821-1852. DOI: 10.1007/s10618-019-00647-x.
Mahato, V., O'Reilly, M., and Cunningham, P. (2018). A comparison of k-nn methods for time series classification and regression. In AICS, pages 102-113. Available online [link].
Maleki, F., Muthukrishnan, N., Ovens, K., Reinhold, C., and Forghani, R. (2020). Machine learning algorithm validation: from essentials to advanced applications and implications for regulatory certification and deployment. Neuroimaging Clinics, 30(4):433-445. DOI: 10.1016/j.nic.2020.08.004.
Meena, R. C., Bhatia, S., Jhaveri, R. H., Shukla, P. K., Kumar, A., Varshney, N., and Malibari, A. A. (2023). Enhancing software-defined networks with intelligent controllers to improve first packet processing period. Electronics, 12(3):600. DOI: 10.3390/electronics12030600.
Messinis, G. M. and Hatziargyriou, N. D. (2018). Review of non-technical loss detection methods. Electric Power Systems Research, 158:250-266. DOI: 10.1016/j.epsr.2018.01.005.
Messinis, G. M., Rigas, A. E., and Hatziargyriou, N. D. (2019). A hybrid method for non-technical loss detection in smart distribution grids. IEEE Transactions on Smart Grid, 10(6):6080-6091. DOI: 10.1109/TSG.2019.2896381.
Modesto, W., Bastos, L., Venâncio Neto, A., Rosário, D., and Cerqueira, E. (2022). Towards automating the integration of legacy ieds into edge-supported internet of smart grid things. Journal of Internet Services and Applications, 12(1):33–46. DOI: 10.5753/jisa.2022.2374.
Passos Júnior, L. A., Oba Ramos, C. C., Rodrigues, D., Pereira, D. R., de Souza, A. N., Pontara da Costa, K. A., and Papa, J. P. (2016). Unsupervised non-technical losses identification through optimum-path forest. Electric Power Systems Research, 140:413-423. DOI: 10.1016/j.epsr.2016.05.036.
Punmiya, R. and Choe, S. (2019). Energy theft detection using gradient boosting theft detector with feature engineering-based preprocessing. IEEE Transactions on Smart Grid, 10(2):2326-2329. DOI: 10.1109/TSG.2019.2892595.
Ramana, K., Revathi, A., Gayathri, A., Jhaveri, R. H., Narayana, C. L., and Kumar, B. N. (2022). Wogru-ids—an intelligent intrusion detection system for iot assisted wireless sensor networks. Computer Communications, 196:195-206. DOI: 10.1016/j.comcom.2022.10.001.
Ramos, C. C., Rodrigues, D., de Souza, A. N., and Papa, J. P. (2018). On the study of commercial losses in brazil: a binary black hole algorithm for theft characterization. IEEE Transactions on Smart Grid, 9(2):676-683. DOI: 10.1109/TSG.2016.2560801.
Santos, H., Eugênio, P., Marques, L., Oliveira, H., Rosário, D., Nogueira, E., Neto, A., and Cerqueira, E. (2022). Internet of smart grid things (iosgt): Prototyping a real cloud-edge testbed. In Proceedings of the 14th Brazilian Symposium on Ubiquitous and Pervasive Computing (SBCUP), pages 111-120, Porto Alegre, RS, Brazil. SBC. DOI: 10.5753/sbcup.2022.223205.
Schäfer, P. and Leser, U. (2017). Fast and accurate time series classification with weasel. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pages 637-646. DOI: 10.1145/3132847.3132980.
Wang, Y., Chen, Q., Hong, T., and Kang, C. (2019). Review of smart meter data analytics: Applications, methodologies, and challenges. IEEE Transactions on Smart Grid, 10(3):3125-3148. DOI: 10.1109/TSG.2018.2818167.
Xi, X., Keogh, E., Shelton, C., Wei, L., and Ratanamahatana, C. A. (2006). Fast time series classification using numerosity reduction. In Proceedings of the 23rd International Conference on Machine Learning, ICML '06, page 1033–1040, New York, NY, USA. Association for Computing Machinery. DOI: 10.1145/1143844.1143974.
Yip, S.-C., Tan, W.-N., Tan, C., Gan, M.-T., and Wong, K. (2018). An anomaly detection framework for identifying energy theft and defective meters in smart grids. International Journal of Electrical Power & Energy Systems, 101:189-203. DOI: 10.1016/j.ijepes.2018.03.025.
Yip, S.-C., Wong, K., Hew, W.-P., Gan, M.-T., Phan, R. C.-W., and Tan, S.-W. (2017). Detection of energy theft and defective smart meters in smart grids using linear regression. International Journal of Electrical Power & Energy Systems, 91:230-240. DOI: 10.1016/j.ijepes.2017.04.00.
Zanetti, M., Jamhour, E., Pellenz, M., Penna, M., Zambenedetti, V., and Chueiri, I. (2019). A tunable fraud detection system for advanced metering infrastructure using short-lived patterns. IEEE Transactions on Smart Grid, 10(1):830-840. DOI: 10.1109/TSG.2017.2753738.
Zheng, Z., Yang, Y., Niu, X., Dai, H.-N., and Zhou, Y. (2017). Wide and deep convolutional neural networks for electricity-theft detection to secure smart grids. IEEE Transactions on Industrial Informatics, 14(4):1606-1615. DOI: 10.1109/TII.2017.2785963.