Deep learning-based meta-learner strategy for electricity theft detection
Electricity theft damages power grid infrastructure and is also responsible for huge revenue losses for electric utilities. Integrating smart meters in traditional power grids enables real-time monitoring and collection of consumers’ electricity consumption (EC) data. Based on the collected data, it...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-09-01
|
| Series: | Frontiers in Energy Research |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1232930/full |
| _version_ | 1827592771459874816 |
|---|---|
| author | Faisal Shehzad Zahid Ullah Musaed Alhussein Khursheed Aurangzeb Sheraz Aslam Sheraz Aslam |
| author_facet | Faisal Shehzad Zahid Ullah Musaed Alhussein Khursheed Aurangzeb Sheraz Aslam Sheraz Aslam |
| author_sort | Faisal Shehzad |
| collection | DOAJ |
| description | Electricity theft damages power grid infrastructure and is also responsible for huge revenue losses for electric utilities. Integrating smart meters in traditional power grids enables real-time monitoring and collection of consumers’ electricity consumption (EC) data. Based on the collected data, it is possible to identify the normal and malicious behavior of consumers by analyzing the data using machine learning (ML) and deep learning methods. This paper proposes a deep learning-based meta-learner model to distinguish between normal and malicious patterns in EC data. The proposed model consists of two stages. In Fold-0, the ML classifiers extract diverse knowledge and learns based on EC data. In Fold-1, a multilayer perceptron is used as a meta-learner, which takes the prediction results of Fold-0 classifiers as input, automatically learns non-linear relationships among them, and extracts hidden complicated features to classify normal and malicious behaviors. Therefore, the proposed model controls the overfitting problem and achieves high accuracy. Moreover, extensive experiments are conducted to compare its performance with boosting, bagging, standalone conventional ML classifiers, and baseline models published in top-tier outlets. The proposed model is evaluated using a real EC dataset, which is provided by the Energy Informatics Group in Pakistan. The model achieves 0.910 ROC-AUC and 0.988 PR-AUC values on the test dataset, which are higher than those of the compared models. |
| first_indexed | 2024-03-09T01:59:29Z |
| format | Article |
| id | doaj.art-3a67dae5be4f4f36a30d763e1c6ff544 |
| institution | Directory Open Access Journal |
| issn | 2296-598X |
| language | English |
| last_indexed | 2024-03-09T01:59:29Z |
| publishDate | 2023-09-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Energy Research |
| spelling | doaj.art-3a67dae5be4f4f36a30d763e1c6ff5442023-12-08T05:47:58ZengFrontiers Media S.A.Frontiers in Energy Research2296-598X2023-09-011110.3389/fenrg.2023.12329301232930Deep learning-based meta-learner strategy for electricity theft detectionFaisal Shehzad0Zahid Ullah1Musaed Alhussein2Khursheed Aurangzeb3Sheraz Aslam4Sheraz Aslam5University of Klagenfurt, Klagenfurt am Wörthersee, AustriaDipartimento di Elettronica, Informazione e Bioingegneria, Politecnico di Milano, Milano, MI, ItalyDepartment of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Computer Engineering, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Electrical Engineering, Computer Engineering, and Informatics, Cyprus University of Technology, Limassol, CyprusDepartment of Computer Science, CTL Eurocollege, Limassol, CyprusElectricity theft damages power grid infrastructure and is also responsible for huge revenue losses for electric utilities. Integrating smart meters in traditional power grids enables real-time monitoring and collection of consumers’ electricity consumption (EC) data. Based on the collected data, it is possible to identify the normal and malicious behavior of consumers by analyzing the data using machine learning (ML) and deep learning methods. This paper proposes a deep learning-based meta-learner model to distinguish between normal and malicious patterns in EC data. The proposed model consists of two stages. In Fold-0, the ML classifiers extract diverse knowledge and learns based on EC data. In Fold-1, a multilayer perceptron is used as a meta-learner, which takes the prediction results of Fold-0 classifiers as input, automatically learns non-linear relationships among them, and extracts hidden complicated features to classify normal and malicious behaviors. Therefore, the proposed model controls the overfitting problem and achieves high accuracy. Moreover, extensive experiments are conducted to compare its performance with boosting, bagging, standalone conventional ML classifiers, and baseline models published in top-tier outlets. The proposed model is evaluated using a real EC dataset, which is provided by the Energy Informatics Group in Pakistan. The model achieves 0.910 ROC-AUC and 0.988 PR-AUC values on the test dataset, which are higher than those of the compared models.https://www.frontiersin.org/articles/10.3389/fenrg.2023.1232930/fullpower systemadvanced metering infrastructuredeep learningmetaheuristicssmart grids |
| spellingShingle | Faisal Shehzad Zahid Ullah Musaed Alhussein Khursheed Aurangzeb Sheraz Aslam Sheraz Aslam Deep learning-based meta-learner strategy for electricity theft detection Frontiers in Energy Research power system advanced metering infrastructure deep learning metaheuristics smart grids |
| title | Deep learning-based meta-learner strategy for electricity theft detection |
| title_full | Deep learning-based meta-learner strategy for electricity theft detection |
| title_fullStr | Deep learning-based meta-learner strategy for electricity theft detection |
| title_full_unstemmed | Deep learning-based meta-learner strategy for electricity theft detection |
| title_short | Deep learning-based meta-learner strategy for electricity theft detection |
| title_sort | deep learning based meta learner strategy for electricity theft detection |
| topic | power system advanced metering infrastructure deep learning metaheuristics smart grids |
| url | https://www.frontiersin.org/articles/10.3389/fenrg.2023.1232930/full |
| work_keys_str_mv | AT faisalshehzad deeplearningbasedmetalearnerstrategyforelectricitytheftdetection AT zahidullah deeplearningbasedmetalearnerstrategyforelectricitytheftdetection AT musaedalhussein deeplearningbasedmetalearnerstrategyforelectricitytheftdetection AT khursheedaurangzeb deeplearningbasedmetalearnerstrategyforelectricitytheftdetection AT sherazaslam deeplearningbasedmetalearnerstrategyforelectricitytheftdetection AT sherazaslam deeplearningbasedmetalearnerstrategyforelectricitytheftdetection |