Using GANCNN and ERNET for Detection of Non Technical Losses to Secure Smart Grids

Abstract

In this paper, two supervised learning models based solutions are proposed for Electricity Theft Detection (ETD). In the first solution, Adaptive Synthetic Edited Nearest Neighbor (ADASYNENN) is used to solve class imbalanced problem. For feature extraction, Locally Linear Embedding (LLE) technique is utilized. Moreover, Self-Attention Generative Adversarial Network (SAGAN) is used in combination with Convolutional Neural Network (CNN) for the classification of electricity consumers. In the second solution, Synthetic Minority Oversampling Technique Edited Nearest Neighbor (SMOTEENN) is proposed. Moreover, a novel classification model, named as ERNET, which is based on EfficientNet, Residual Network (ResNet) and Gated Recurrent Unit (GRU), is used to detect Non-Technical Losses (NTLs). We also used a Sparse Auto Encoder (SAE) for effective feature extraction that makes the classification more robust and easy. Furthermore, a robust Root Mean Square Propagation (RMSProp) optimizer is used to improve the learning rate of the model. To validate the proposed models, simulations are performed using different performance metrics, such as precision, recall, F1-score, Area Under the Curve (AUC), FPR and Root Mean Square Error (RMSE). All simulations are performed using State Grid Corporation of China (SGCC) dataset. The proposed models are compared with benchmark models, such as SAGAN, Wide and Deep Convolutional Neural Network (WDCNN), CNN and Long Short Term Memory (LSTM). The simulation results prove that the proposed models outperform the existing models in terms of the aforementioned performance metrics.

Data-Driven Machine Learning Methods for Nontechnical Losses of Electrical Energy Detection: A State-of-the-Art Review

“…Weight coefficients emerge solely during the learning phase, culminating in the generation of a neuron activation signal destined for the subsequent layer of the network. Eventually, the neuron outputs' products are aggregated according to their respective weights, delineating the conclusive output, a process documented in [70,[73][74][75][76][77][78][79][80][81][82][83][84][85][86][87][88][89][90].…”

IoMT: A COVID-19 Healthcare System Driven by Federated Learning and Blockchain

“…The aim of generating synthetic data is because of the irregularity in the presentation of data by CDCs in terms of daily, weekly or monthly rhythms. In the literature, a generative adversary network has been employed to generate synthetic data for solving a data imbalanced problem [48]. FL, hybrid identity generation method and poison attack mechanism ✗ ✓ ✗ Tradeoff between efficiency and privacy protection is not considered.…”

A Comprehensive Investigation into the Application of Convolutional Neural Networks (ConvNet/CNN) in Smart Grids

“…This facilitates accurate and understandable short-term voltage stability testing when conducted online [119]. To identify non-technical losses, Self-Attention Generative Adversarial Network, Synthetic Minority Oversampling Technique Edited Nearest Neighbor, Residual Network, and GRU are combined [120]. A hybrid CNN generalizes local characteristics from one-dimensional data and a DNN memorizes global features from onedimensional data.…”