A Hybrid Deep Learning Neural Network Model and Data-Driven Methods for Smart Grid Theft Detection

Smart grids are harmed by electricity theft, and electric companies lose a lot of money as a result. Recent research has looked at ways to use a mix of deep learning (DL), machine learning (ML), and statistical methods to spot anomalies and illegal tendencies in electrical consumption (EC) data collected by smart meters. In this research, we combine the best features of the convolutional neural network with the gated recurrent unit to create a unique hybrid model that we call the CNNGRU Model. Accurate power theft detection is one of the model's primary goals, along with resolving problems with previous attempts at this. Overfitting and an insensitivity to data imbalance are two of the problems. Despite its processing complexity, the proposed strategy exceeds its rivals in terms of accuracy. Scientists may dedicate their focus to finding ways that increase performance in the presence of enormous volumes of data as computers become more powerful. The efficacy of the hybrid DL model is studied using a variety of performance measures, including such as F1-score, precision, recall, accuracy, and false positive rate.