Employing a Machine Learning Boosting Classifiers Based Stacking Ensemble Model for Detecting Non Technical Losses in Smart Grids

• Published in: IEEE access Vol. 10; pp. 121886 - 121899
• Main Authors: Pamir, Javaid, Nadeem, Akbar, Mariam, Aldegheishem, Abdulaziz, Alrajeh, Nabil, Mohammed, Emad A.
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: AdaBoost; Adaptation models; Adaptive sampling; Advanced metering infrastructure; Boosting; CatBoost; Classifiers; Consumers; Data acquisition; Data models; Deep learning; Electric power grids; Electricity; Electricity meters; electricity theft detection; Energy consumption; healthcare; HistBoost; Histograms; LGBoost; Machine learning; Neural networks; Performance evaluation; smart cities; Smart grid; Smart grids; Smart meters; Stacking; stacking ensemble model; state grid corporation of China dataset; Theft; XGBboost
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2022.3222883

In the modern world, numerous opportunities help detect electricity theft happening in electricity grids due to the widespread shifting of people from old metering infrastructure to advanced metering infrastructure (AMI). It is done by studying the consumers' energy consumption (EC) readings provided by smart meters (SM). The literature introduces a variety of machine learning (ML) and deep learning (DL) strategies to use EC data for identifying power theft in smart grids (SGs). However, the existing schemes provide low performance in electricity theft detection (ETD) due to the usage of imbalanced data and using schemes individually. Moreover, the existing detectors are validated using a limited number of performance evaluation measures, which are unsuitable for conducting the model's comprehensive validation. To tackle the problems mentioned above, an ML boosting classifiers-based stacking ensemble model (MLBCSM) is proposed followed by an adaptive synthetic sampling technique (ADASYN) in the underlying work. Data preprocessing, data balancing and classification are the three major parts of the model introduced in this work. Besides, the EC data acquired from the consumers' SMs is used for detecting electricity theft. Moreover, the simulation results reveal that MLBCSM combines the benefits of adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), histogram boosting (HistBoost), categorical boosting (CatBoost), and light gradient boosting (LGBoost). Additionally, the model's validation is ensured via different metrics. It is deduced via extensive simulations that the proposed model's outcomes are superior to those of the individual models in terms of ETD.