Electricity Theft Detection Using Rule-Based Machine Leaning (rML) Approach

Abstract

Since electricity theft affects non-technical losses (NTLs) in power distribution systems, power companies are genuinely quite concerned about it. Power companies can use the information gathered by Advanced Metering Infrastructure (AMI) to create data-driven, machine learning-based approaches for Electricity Theft Detection (ETD) in order to solve this problem. The majority of data-driven methods for detecting power theft do take usage trends into account while doing their analyses. Even though consumption-based models have been applied extensively to the detection of power theft, it can be difficult to reliably identify theft instances based only on patterns of usage. In this paper, a novel rule-based combined machine learning (rML) technique is developed for power theft detection to address the drawbacks of systems that rely just on consumption patterns. This approach makes use of the load profiles of energy users to establish rules, identify the rule or rules that apply to certain situations, and classify the cases as either legitimate or fraudulent. The UEDAS smart business power consumption dataset's real-world data is used to assess the performance of the suggested technique. Our technique is an innovation in theft detection that combines years of intensive theft tracking with the use of rule-based systems as feature spaces for traditional machine learning models. With an astounding 93% recall rate for the rule-based feature space combination of the random forest classifier, this novel approach has produced outstanding results. The acquired results show a noteworthy accomplishment in the field of fraud detection, successfully detecting fraudulent consumers 77% of the time during on-site examination.

Keywords

• electricity theft dedection
• non-technical losses
• advanced metering infrastructure
• machine learning

Kaynakça

1. [1] Emadaleslami, M., Haghifam, M. R., & Zangiabadi, M. A two-stage approach to electricity theft detection in AMI using deep learning. International Journal of Electrical Power & Energy Systems, 150, 109088, (2023).
2. [2] Markovska, M., Gerazov, B., Zlatkova, A., & Taskovski, D. (2023, June). Electricity Theft Detection Based on Temporal Convolutional Networks with Self-Attention. In 2023 30th International Conference on Systems, Signals and Image Processing (IWSSIP) (pp. 1-5). IEEE.
3. [3] Taha, K. Semi-supervised and un-supervised clustering: A review and experimental evaluation. Information Systems, 102178, (2023).
4. [4] Zheng Z, Yang Y, Niu X, Dai HN, Zhou Y. Wide and deep convolutional neural networks for electricity-theft detection to secure smart grids. IEEE Transactions on Industrial Informatics. 2017 Dec 21;14(4):1606-15.
5. [5] Himeur Y, Ghanem K, Alsalemi A, Bensaali F, Amira A. Artificial intelligence-based anomaly detection of energy consumption in buildings: A review, current trends and new perspectives. Applied Energy. Apr 1;287:116601, (2021).
6. [6] Oprea SV, Bâra A. Feature engineering solution with structured query language analytic functions in detecting electricity frauds using machine learning. Scientific Reports. 28; 12(1):3257, (2022).
7. [7] Monedero I, Biscarri F, León C, Guerrero JI, Biscarri J, Millán R. Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees. International Journal of Electrical Power & Energy Systems. 34(1):90-8, (2012).
8. [8] Long H, Chen C, Gu W, Xie J, Wang Z, Li G. A data-driven combined algorithm for abnormal power loss detection in the distribution network. IEEE Access. 8:24675-86, (2020).

9. [9] Figueroa G, Chen YS, Avila N, Chu CC. Improved practices in machine learning algorithms for NTL detection with imbalanced data. In2017 IEEE Power & Energy Society General Meeting 2017 Jul 16 (pp. 1-5). IEEE.
10. [10] Krishna VB, Gunter CA, Sanders WH. Evaluating detectors on optimal attack vectors that enable electricity theft and DER fraud. IEEE Journal of Selected Topics in Signal Processing. 12(4):790-805, (2018).
11. [11] Razavi R, Gharipour A, Fleury M, Akpan IJ. A practical feature-engineering framework for electricity theft detection in smart grids. Applied energy. 238:481-94, (2019).
12. [12] Peng Y, Yang Y, Xu Y, Xue Y, Song R, Kang J, Zhao H. Electricity theft detection in AMI based on clustering and local outlier factor. IEEE Access. 2021 Jul 28;9:107250-9.
13. [13] Jindal A, Schaeffer-Filho A, Marnerides AK, Smith P, Mauthe A, Granville L. Tackling energy theft in smart grids through data-driven analysis. In2020 International Conference on Computing, Networking and Communications (ICNC) 2020 Feb 17 (pp. 410-414). IEEE.
14. [14] Angelos EW, Saavedra OR, Cortés OA, De Souza AN. Detection and identification of abnormalities in customer consumptions in power distribution systems. IEEE Transactions on Power Delivery. 26(4):2436-42, (2011).
15. [15] Blazakis KV, Kapetanakis TN, Stavrakakis GS. Effective electricity theft detection in power distribution grids using an adaptive neuro fuzzy inference system. Energies. 13(12):3110, (2020).
16. [16] Fernandes SE, Pereira DR, Ramos CC, Souza AN, Gastaldello DS, Papa JP. A probabilistic optimum-path forest classifier for non-technical losses detection. IEEE Transactions on Smart Grid. 10(3):3226-35, (2018).
17. [17] Ramos CC, Souza AN, Papa JP, Falcao AX. Fast non-technical losses identification through optimum-path forest. In2009 15th International Conference on Intelligent System Applications to Power Systems 2009 Nov 8 (pp. 1-5). IEEE.
18. [18] Ramos CC, Souza AN, Chiachia G, Falcão AX, Papa JP. A novel algorithm for feature selection using harmony search and its application for non-technical losses detection. Computers & Electrical Engineering. 37(6):886-94, (2011).
19. [19] Ramos CC, de Sousa AN, Papa JP, Falcao AX. A new approach for nontechnical losses detection based on optimum-path forest. IEEE Transactions on Power Systems. 26(1):181-9, (2010).
20. [20] Ramos CC, de Souza AN, Falcao AX, Papa JP. New insights on nontechnical losses characterization through evolutionary-based feature selection. IEEE Transactions on Power Delivery. 27(1):140-6, (2011).
21. [21] Xiao F, Ai Q. Electricity theft detection in smart grid using random matrix theory. IET Generation, Transmission & Distribution. 12(2):371-8, (2018).
22. [22] Depuru SS, Wang L, Devabhaktuni V, Green RC. High performance computing for detection of electricity theft. International Journal of Electrical Power & Energy Systems. 47:21-30, (2013).
23. [23] Jain S, Choksi KA, Pindoriya NM. Rule‐based classification of energy theft and anomalies in consumers load demand profile. IET Smart Grid. 2(4):612-24, (2019).
24. [24] Biswas PP, Cai H, Zhou B, Chen B, Mashima D, Zheng VW. Electricity theft pinpointing through correlation analysis of master and individual meter readings. IEEE Transactions on Smart Grid. 11(4):3031-42, (2019).
25. [25] Shah AL, Mesbah W, Al-Awami AT. An algorithm for accurate detection and correction of technical and nontechnical losses using smart metering. IEEE Transactions on Instrumentation and Measurement. 69(11):8809-20, (2020).
26. [26] Zheng K, Chen Q, Wang Y, Kang C, Xia Q. A novel combined data-driven approach for electricity theft detection. IEEE Transactions on Industrial Informatics. 15(3):1809-19, (2018).
27. [27] Tao J, Michailidis G. A statistical framework for detecting electricity theft activities in smart grid distribution networks. IEEE Journal on Selected Areas in Communications. 38(1):205-16, (2019).
28. [28] Xiang M, Rao H, Tan T, Wang Z, Ma Y. Abnormal behaviour analysis algorithm for electricity consumption based on density clustering. The Journal of Engineering. 2019(10):7250-5, (2019).
29. [29] Kharal AY, Khalid HA, Gastli A, Guerrero JM. A novel features-based multivariate Gaussian distribution method for the fraudulent consumers detection in the power utilities of developing countries. IEEE Access. 9:81057-67, (2021).
30. [30] Hock D, Kappes M, Ghita B. Using multiple data sources to detect manipulated electricity meter by an entropy-inspired metric. Sustainable Energy, Grids and Networks. 21:100290, (2020).
31. [31] Singh SK, Bose R, Joshi A. Entropy‐based electricity theft detection in AMI network. IET Cyber‐Physical Systems: Theory & Applications. 3(2):99-105, (2018).
32. [32] Jaiswal S, Ballal MS. Fuzzy inference based electricity theft prevention system to restrict direct tapping over distribution line. Journal of Electrical Engineering & Technology. 15:1095-106, (2020).
33. [33] Aligholian A, Farajollahi M, Mohsenian-Rad H. Unsupervised learning for online abnormality detection in smart meter data. In2019 IEEE Power & Energy Society General Meeting (PESGM) 2019 Aug 4 (pp. 1-5). IEEE.
34. [34] Feng Z, Huang J, Tang WH, Shahidehpour M. Data mining for abnormal power consumption pattern detection based on local matrix reconstruction. International Journal of Electrical Power & Energy Systems. 123:106315, (2020).
35. [35] Lu X, Zhou Y, Wang Z, Yi Y, Feng L, Wang F. Knowledge embedded semi-supervised deep learning for detecting non-technical losses in the smart grid. Energies. 12(18):3452, (2019).
36. [36] Hu T, Guo Q, Shen X, Sun H, Wu R, Xi H. Utilizing unlabeled data to detect electricity fraud in AMI: A semisupervised deep learning approach. IEEE transactions on neural networks and learning systems. 30(11):3287-99, (2019).
37. [37] Lu X, Zhou Y, Wang Z, Yi Y, Feng L, Wang F. Knowledge embedded semi-supervised deep learning for detecting non-technical losses in the smart grid. Energies. 12(18):3452, (2019).
38. [38] Javaid N, Gul H, Baig S, Shehzad F, Xia C, Guan L, Sultana T. Using GANCNN and ERNET for detection of non technical losses to secure smart grids. IEEE Access. 9:98679-700, (2021).
39. [39] Ismail M, Shaaban MF, Naidu M, Serpedin E. Deep learning detection of electricity theft cyber-attacks in renewable distributed generation. IEEE Transactions on Smart Grid. 11(4):3428-37, (2020).
40. [40] Charwand M, Gitizadeh M, Siano P, Chicco G, Moshavash Z. Clustering of electrical load patterns and time periods using uncertainty-based multi-level amplitude thresholding. International Journal of Electrical Power & Energy Systems. 117:105624, (2020).
41. [41] Xia R, Gao Y, Zhu Y, Gu D, Wang J. An attention-based wide and deep CNN with dilated convolutions for detecting electricity theft considering imbalanced data. Electric Power Systems Research. 214:108886, (2023).
42. [42] Messinis GM, Hatziargyriou ND. Unsupervised classification for non-technical loss detection. In2018 Power Systems Computation Conference (PSCC) 2018 Jun 11 (pp. 1-7). IEEE.
43. [43] Breiman L. (2001) Random forests. Machine learning. Oct; 45:5-32.
44. [44] Freund Y, Schapire RE. A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences. 55(1):119-39, (1997).
45. [45] Ghori KM, Abbasi RA, Awais M, Imran M, Ullah A, Szathmary L. Performance analysis of different types of machine learning classifiers for non-technical loss detection. IEEE Access. 26;8:16033-48,(2019).
46. [46] Raza M, Awais M, Ellahi W, Aslam N, Nguyen HX, Le-Minh H. Diagnosis and monitoring of Alzheimer's patients using classical and deep learning techniques. Expert Systems with Applications. 136:353-64, (2019).
47. [47] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by back-propagating errors. Nature. 323(6088):533-6, (1986).
48. [48] Mujeeb S, Javaid N, Ahmed A, Gulfam SM, Qasim U, Shafiq M, Choi JG. Electricity theft detection with automatic labeling and enhanced RUSBoost classification using differential evolution and Jaya algorithm. IEEE Access. 9:128521-39, (2021).
49. [49] Khan ZA, Adil M, Javaid N, Saqib MN, Shafiq M, Choi JG. Electricity theft detection using supervised learning techniques on smart meter data. Sustainability. 12(19):8023, (2020).
50. [50] Richardson C, Race N, Smith P. A privacy preserving approach to energy theft detection in smart grids. In2016 IEEE International Smart Cities Conference (ISC2) 2016 Sep 12 (pp. 1-4). IEEE.
51. [51] Qu Z, Li H, Wang Y, Zhang J, Abu-Siada A, Yao Y. Detection of electricity theft behavior based on improved synthetic minority oversampling technique and random forest classifier. Energies. 13(8):2039, (2020).
52. [52] Nagi J, Yap KS, Tiong SK, Ahmed SK, Nagi F. Improving SVM-based nontechnical loss detection in power utility using the fuzzy inference system. IEEE Transactions on power delivery. 26(2):1284-5, (2011).
53. [53] Punmiya R, Choe S. Energy theft detection using gradient boosting theft detector with feature engineering based preprocessing. IEEE Transactions on Smart Grid. 10(2):2326-9, (2019).