Using machine learning ensemble method for detection of energy theft in smart meters
Abstract Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)‐based model utilizing the consumers’ electricity consumption patterns for analysis is proposed for electricity theft d...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2023-11-01
|
| Series: | IET Generation, Transmission & Distribution |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/gtd2.12997 |
| _version_ | 1797640035117301760 |
|---|---|
| author | Asif Iqbal Kawoosa Deepak Prashar Muhammad Faheem Nishant Jha Arfat Ahmad Khan |
| author_facet | Asif Iqbal Kawoosa Deepak Prashar Muhammad Faheem Nishant Jha Arfat Ahmad Khan |
| author_sort | Asif Iqbal Kawoosa |
| collection | DOAJ |
| description | Abstract Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)‐based model utilizing the consumers’ electricity consumption patterns for analysis is proposed for electricity theft detection (ETD). To remove the imbalance in the real‐world electricity consumption dataset and ensure an even distribution of theft and non‐theft data instances, six different artificially created theft attacks were used. Moreover, the utilization of the XGBoost algorithm for classification, especially to identify malicious instances of electricity theft, yielded commendable accuracy rates and a minimal occurrence of false positives. The proposed model identifies electricity theft specific to the regions, utilizing electricity consumption parameters, and other variables as input features. The authors’ model outperformed existing benchmarks like k‐neural networks, light gradient boost, random forest, support vector machine, decision tree, and AdaBoost. The simulation results using the false attacks for balancing the dataset have improved the proposed model's performance, achieving a precision, recall, and F1‐score of 96%, 95%, and 95%, respectively. The results of the detection rate and the false positive rate (FPR) of the proposed XGBoost‐based detection model have achieved 96% and 3%, respectively. |
| first_indexed | 2024-03-11T13:26:07Z |
| format | Article |
| id | doaj.art-13305cfcf4fe4f87ab49c9c6abae4ed5 |
| institution | Directory Open Access Journal |
| issn | 1751-8687 1751-8695 |
| language | English |
| last_indexed | 2024-03-11T13:26:07Z |
| publishDate | 2023-11-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Generation, Transmission & Distribution |
| spelling | doaj.art-13305cfcf4fe4f87ab49c9c6abae4ed52023-11-03T06:13:53ZengWileyIET Generation, Transmission & Distribution1751-86871751-86952023-11-0117214794480910.1049/gtd2.12997Using machine learning ensemble method for detection of energy theft in smart metersAsif Iqbal Kawoosa0Deepak Prashar1Muhammad Faheem2Nishant Jha3Arfat Ahmad Khan4School of Computer Applications Lovely Professional University Phagwara Punjab IndiaSchool of Computer Science & Engineering Lovely Professional University Phagwara Punjab IndiaSchool of Technology and Innovations University of Vaasa Vaasa FinlandSchool of Computer Science & Engineering Lovely Professional University Phagwara Punjab IndiaDepartment of Computer Science College of Computing Khon Kaen University Khon Kaen ThailandAbstract Electricity theft is a primary concern for utility providers, as it leads to substantial financial losses. To address the issue, a novel extreme gradient boosting (XGBoost)‐based model utilizing the consumers’ electricity consumption patterns for analysis is proposed for electricity theft detection (ETD). To remove the imbalance in the real‐world electricity consumption dataset and ensure an even distribution of theft and non‐theft data instances, six different artificially created theft attacks were used. Moreover, the utilization of the XGBoost algorithm for classification, especially to identify malicious instances of electricity theft, yielded commendable accuracy rates and a minimal occurrence of false positives. The proposed model identifies electricity theft specific to the regions, utilizing electricity consumption parameters, and other variables as input features. The authors’ model outperformed existing benchmarks like k‐neural networks, light gradient boost, random forest, support vector machine, decision tree, and AdaBoost. The simulation results using the false attacks for balancing the dataset have improved the proposed model's performance, achieving a precision, recall, and F1‐score of 96%, 95%, and 95%, respectively. The results of the detection rate and the false positive rate (FPR) of the proposed XGBoost‐based detection model have achieved 96% and 3%, respectively.https://doi.org/10.1049/gtd2.12997electricity supply industrysmart meters |
| spellingShingle | Asif Iqbal Kawoosa Deepak Prashar Muhammad Faheem Nishant Jha Arfat Ahmad Khan Using machine learning ensemble method for detection of energy theft in smart meters IET Generation, Transmission & Distribution electricity supply industry smart meters |
| title | Using machine learning ensemble method for detection of energy theft in smart meters |
| title_full | Using machine learning ensemble method for detection of energy theft in smart meters |
| title_fullStr | Using machine learning ensemble method for detection of energy theft in smart meters |
| title_full_unstemmed | Using machine learning ensemble method for detection of energy theft in smart meters |
| title_short | Using machine learning ensemble method for detection of energy theft in smart meters |
| title_sort | using machine learning ensemble method for detection of energy theft in smart meters |
| topic | electricity supply industry smart meters |
| url | https://doi.org/10.1049/gtd2.12997 |
| work_keys_str_mv | AT asifiqbalkawoosa usingmachinelearningensemblemethodfordetectionofenergytheftinsmartmeters AT deepakprashar usingmachinelearningensemblemethodfordetectionofenergytheftinsmartmeters AT muhammadfaheem usingmachinelearningensemblemethodfordetectionofenergytheftinsmartmeters AT nishantjha usingmachinelearningensemblemethodfordetectionofenergytheftinsmartmeters AT arfatahmadkhan usingmachinelearningensemblemethodfordetectionofenergytheftinsmartmeters |