Electricity Theft Research Articles

Mitigating Class Imbalance Issues in Electricity Theft Detection via a Sample-Weighted Loss

Mitigating Class Imbalance Issues in Electricity Theft Detection via a Sample-Weighted Loss

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

Reducing Annotation Efforts in Electricity Theft Detection Through Optimal Sample Selection

Feature Attention Distillation Defense for Backdoor Attack in Artificial Neural Network-Based Electricity Theft Detection

Feature Attention Distillation Defense for Backdoor Attack in Artificial Neural Network-Based Electricity Theft Detection

Dynamic Generative Residual Graph Convolutional Neural Networks for Electricity Theft Detection

Dynamic Generative Residual Graph Convolutional Neural Networks for Electricity Theft Detection

Electricity Theft Detection in Smart Grids Based on Omni-Scale CNN and AutoXGB

Electricity Theft Detection in Smart Grids Based on Omni-Scale CNN and AutoXGB

Electricity Theft Detection for Smart Homes: Harnessing the Power of Machine Learning With Real and Synthetic Attacks

Electricity Theft Detection for Smart Homes: Harnessing the Power of Machine Learning With Real and Synthetic Attacks

IOT based Smart Unlawful Electricity Usage Surveillance and Warning System

The global issue of electricity theft has a negative impact on both the utilities and the people who use the energy. It impairs utility company economic growth, creates electrical risks, and has an effect on consumers' expenses for electricity. The emergence of smart grids is crucial for the detection of power theft as they provide vast amounts of data, including information on consumer consumption that can be used to identify theft using over voltage and over current detection methods. The solution presented in this article employs an Arduino uno micro controller board and IOT to monitor and maintain surveillance on power theft. An alarm with SMS notification will be sent to the officials and the power will be shut off whenever there is a power outage or tampering with an energy meter.

Corrigendum: Deep learning-based meta-learner strategy for electricity theft detection

Corrigendum: Deep learning-based meta-learner strategy for electricity theft detection

A new electricity theft detection method using hybrid adaptive sampling and pipeline machine learning

A new electricity theft detection method using hybrid adaptive sampling and pipeline machine learning

Detecting anomalous electricity consumption with transformer and synthesized anomalies

Non-technical losses are consistently a troubling issue for power suppliers. With the application and popularization of smart grid and advanced measurement systems, it has become possible to use data-driven methods to detect anomalous electricity consumption to reduce non-technical losses. A range of machine learning models have been utilized for detecting anomalous electricity consumption and have achieved promising results. However, with the evolution of techniques like electricity theft, coupled with the exponential increase in electricity consumption data, new challenges are constantly being posed for anomalous electricity consumption detection. We propose a Transformer-based method for detecting anomalous electricity consumption. The Transformer is composed of multi-head attention, layer normalization, point-wise feed-forward network, etc., which can effectively handle electricity consumption time-series data. Meanwhile, to alleviate the problem of imbalanced training data between anomalous and normal electricity consumption, we propose a method for synthesizing anomalies. The experimental results demonstrate that our proposed Transformer-based method outperforms the state-of-the-art methods in detecting anomalous electricity consumption, achieving a precision of 93.9%, a recall of 96.3%, an F1-score of 0.951, and an accuracy of 95.6% on a dataset released by the State Grid Corporation of China.

A novel and effective method based deep learning model for detecting non-technical electricity losses

<p>This study focused on non-technical electricity loss detection. As mentioned, non-technical losses (NTLs) affect utilities and economies financially. Electricity theft, fraud, and metering issues can create NTLs. NTL generate most distribution losses in electrical power networks, costing utilities a lot. NTL detection approaches are data-focused, network-oriented, or hybrid. Data-oriented writing dominated this analysis. After data collection and cleaning and labeling the unlabeled dataset with a target, a methodology was supplied that used four machine learning techniques random forest, decision tree, KNN, and logistic regression and four neural network models-DNN, CNN, CNN-LSTM, and CNN-GRU. The CNN and DNN model have the best accuracy, stability, fast learning, and training time.</p>

Practical prototype for energy management system in smart microgrid considering uncertainties and energy theft

The conventional electrical grid faces significant issues, which this paper aims to address one of most of them using a proposed prototype of a smart microgrid energy management system. In addition to relying too heavily on fossil fuels, electricity theft is another great issue. The proposed energy management system can simultaneously detect electricity theft and implement demand response tactics by employing time-of-use pricing principles and comparing real electricity consumption with grid data. The system uses the Al-Biruni earth radius (BER) optimization algorithm to make smart choices about how to distribute the load, intending to reduce energy consumption and costs without sacrificing comfort. As a bonus, it considers limitations imposed by battery charging/discharging and decentralized power generation. Incorporating sensors and SCADA-based monitoring, the system provides accurate measurement and management of energy usage through load monitoring and control. An intuitive mobile app also helps consumers connect, allowing for more active participation and better control over energy use. Extensive field testing of the prototype shows that by moving loads from peak period to another off-peak period, electricity expenditures can be reduced by up to 48.45%. The energy theft value was calculated to be 1199 W, proving that the system's theft detection model was effective.

Deep semi-supervised electricity theft detection in AMI for sustainable and secure smart grids

Electricity theft is a major issue that affects the sustainability and security of smart grids. This paper proposes a deep semi-supervised method for electricity theft detection in the Advanced Metering Infrastructure (AMI) of smart grids. By only using normal samples to train the detection model, the proposed method has the capability of detecting unknown attacks in a short time frame. The method utilizes the ratio profile generated from the readings of the observer meter and the user’s smart meter as the input, to reduce false positives, which is then transformed into a 2D image with the continuous wavelet transform (CWT) to capture the time–frequency information. Discriminative features are extracted from the CWT image with a deep convolutional autoencoder (CAE) and principal component analysis (PCA), which are fed into a semi-supervised autoencoder for classification. The performance of the proposed method was evaluated and compared with a set of baselines and four supervised machine learning and deep learning methods under 11 different false data injection (FDI) attacks using smart meter data from both business and residential users. The results show that the proposed method significantly outperforms the baselines and is more capable of detecting unknown attacks than supervised methods.

Theft or norm? A tale of electricity theft in rural Kwaximba, eThekwini region of South Africa

Theft or norm? A tale of electricity theft in rural Kwaximba, eThekwini region of South Africa

Federated split learning for sequential data in satellite–terrestrial integrated networks

Satellite–terrestrial integrated networks (STINs) have been proposed for B5G/6G mobile communication, and the increase in the computation and communication capacities of satellites opens the door for satellite edge computing in space. The requirements of privacy protection and communication efficiency lead to the inefficiency or deficiency of traditional learning approaches in STINs. This study incorporates federated learning and split learning paradigms with STINs and introduces a split-then-federated learning framework and federated split learning with long short-term memory to handle sequential data in STINs. A case study of electricity theft detection based on a real-world sequential power load dataset is utilized to demonstrate the effectiveness of the proposed solution. Numerical experiments show that the proposed FedSL-LSTM model is an effective federated learning solution and a competitive solution compared with centralized models in terms of classification performance evaluation metrics.

A deep learning technique Alexnet to detect electricity theft in smart grids

Electricity theft (ET), which endangers public safety, creates a problem with the regular operation of grid infrastructure and increases revenue losses. Numerous machine learning, deep learning, and mathematical-based algorithms are available to find ET. Still, these models do not produce the best results due to problems like the dimensionality curse, class imbalance, improper hyper-parameter tuning of machine learning and deep learning models, etc. We present a hybrid deep learning model for effectively detecting electricity thieves in smart grids while considering the abovementioned concerns. Pre-processing techniques are first employed to clean up the data from the smart meters. Then, the feature extraction technique, like AlexNet, addresses the curse of dimensionality. The effectiveness of the proposed method is evaluated through simulations using a real dataset of Chinese intelligent meters. To conduct a comparative analysis, various benchmark models are implemented as well. Our proposed model achieves accuracy, precision, recall, and F1, up to 86%, 89%, 86%, and 84%, respectively.

Lightweight Multi-Class Support Vector Machine-Based Medical Diagnosis System with Privacy Preservation.

Machine learning, powered by cloud servers, has found application in medical diagnosis, enhancing the capabilities of smart healthcare services. Research literature demonstrates that the support vector machine (SVM) consistently demonstrates remarkable accuracy in medical diagnosis. Nonetheless, safeguarding patients' health data privacy and preserving the intellectual property of diagnosis models is of paramount importance. This concern arises from the common practice of outsourcing these models to third-party cloud servers that may not be entirely trustworthy. Few studies in the literature have delved into addressing these issues within SVM-based diagnosis systems. These studies, however, typically demand substantial communication and computational resources and may fail to conceal classification results and protect model intellectual property. This paper aims to tackle these limitations within a multi-class SVM medical diagnosis system. To achieve this, we have introduced modifications to an inner product encryption cryptosystem and incorporated it into our medical diagnosis framework. Notably, our cryptosystem proves to be more efficient than the Paillier and multi-party computation cryptography methods employed in previous research. Although we focus on a medical application in this paper, our approach can also be used for other applications that need the evaluation of machine learning models in a privacy-preserving way such as electricity theft detection in the smart grid, electric vehicle charging coordination, and vehicular social networks. To assess the performance and security of our approach, we conducted comprehensive analyses and experiments. Our findings demonstrate that our proposed method successfully fulfills our security and privacy objectives while maintaining high classification accuracy and minimizing communication and computational overhead.

Electricity Theft Detection Based on Contrastive Learning and Non-Intrusive Load Monitoring

Electricity theft has caused enormous damage to grids safety and economy globally, bringing plentiful attention to electricity theft detection. However, the inherent problems of data imbalance, data sparsity, and data shift due to the residents will or the seasons remain challenges. Besides, there is a lack of appliance-level information provided by non-intrusive load monitoring to improve the data graininess in electricity theft detection. To address these problems, an electricity theft detection algorithm based on contrastive learning and non-intrusive load monitoring is proposed. Firstly, a semi-supervised learning architecture composed of Gramian angular field encoding for sequence visualization and contrastive learning architecture featuring few-shot learning is established for load monitoring and initial detection considering the inherent operating characteristics of appliances. Furthermore, after the filtration of typical regular-switched appliances by Kendalls coefficient of concordance, in-depth detection of abnormal operation routines of appliances is conducted for suspicious residents, aiming to improve the fault-tolerant ability and resist the emergence of unknown electricity theft methods. Finally, the electricity theft probability is computed to confirm fraudulent users. Both the public and practical datasets are utilized to verify the effectiveness of the proposed study, and the results show an overall better performance compared to other state-of-the-art algorithms.

Multiverse Recurrent Expansion With Multiple Repeats: A Representation Learning Algorithm for Electricity Theft Detection in Smart Grids

Electricity theft, known as “Non-Technical Loss” (NTL) is certainly one of the priorities of power distribution utilities. Indeed, NTL could lead to serious damage ranging from massive financial losses to loss of reputation resulting from poor power quality. With advances in metering infrastructure technologies, the availability of user data has fueled the emergence of data-driven methods in NTL detection. Among these methods, deep learning (DL) is an indisputable alternative to conventional human-centric approaches. Typically, modeling based on NTL data is subject to three main challenges, including (i) missing information; (ii) class imbalance; and (iii) data complexity. In this context, this paper contributes to solving these three main problems while paying more attention to data complexity related to cardinality. Accordingly, a multiverse recurrent expansion with multiple repeats (MV-REMR) algorithm is proposed in this paper. MV-REMR is able to provide deeper representations than ordinary DL networks and take advantage of different trained deep network responses to build an efficient model. For MV-REMR efficiency analysis, a realistic NTL dataset is considered. As a result, MV-REMR has shown that it can achieve what is considered excellent feature mapping proven by both scatter visualization and variations in widely used classification metrics. Moreover, MV-REMR shows its ability to marginalize the distance of data classes with superior performance. In addition, thanks to the new mapping scheme, MV-REMR shows its ability to correct outliers resulting from errors in missing values filling techniques. Finally, a comparison with some recent successful works also confirms the superiority of the MV-REMR model.

Electricity theft recognition and time period detection considering based on multi-task learning

Electricity theft is an economic problem faced around the power companies. After the suspicious electricity theft users are recognized, the potentially stolen electricity (PSE) and the loss caused by the electricity theft needs to be accurately evaluated. In the actual inspection work, the key to evaluating PSE is electricity theft time period detection. However, most of the current electricity theft detection algorithms can only recognize electricity theft, which cannot detect the specific time period of electricity theft simultaneously. Therefore, this paper proposes a deep model named multi-task deep residual network (MDRN), which can simultaneously recognize electricity theft users and detect their electricity theft time period. The MDRN is constructed based on one-dimensional convolutional and residual network, which can effectively extract characteristics from power consumption data. To automatically balance the multiple tasks in training, a joint multi-task loss with task uncertainty is proposed. The experimental results based on the Irish dataset show that the proposed multi-task model obtains the highest Accuracy with 93.17% in electricity theft recognition and the highest intersection-over-union (IOU) with 76.58% in time period detection. It should be noted that the proposed method can be directly used to calculate the PSE to maximize economic return of electricity theft inspection.