Electricity Theft Detection Research Articles

XAI-Based Accurate Anomaly Detector That Is Robust Against Black-Box Evasion Attacks for the Smart Grid

In the realm of smart grids, machine learning (ML) detectors—both binary (or supervised) and anomaly (or unsupervised)—have proven effective in detecting electricity theft (ET). However, binary detectors are designed for specific attacks, making their performance unpredictable against new attacks. Anomaly detectors, conversely, are trained on benign data and identify deviations from benign patterns as anomalies, but their performance is highly sensitive to the selected threshold values. Additionally, ML detectors are vulnerable to evasion attacks, where attackers make minimal changes to malicious samples to evade detection. To address these limitations, we introduce a hybrid anomaly detector that combines a Deep Auto-Encoder (DAE) with a One-Class Support Vector Machine (OCSVM). This detector not only enhances classification performance but also mitigates the threshold sensitivity of the DAE. Furthermore, we evaluate the vulnerability of this detector to benchmark evasion attacks. Lastly, we propose an accurate and robust cluster-based DAE+OCSVM ET anomaly detector, trained using Explainable Artificial Intelligence (XAI) explanations generated by the Shapley Additive Explanations (SHAP) method on consumption readings. Our experimental results demonstrate that the proposed XAI-based detector achieves superior classification performance and exhibits enhanced robustness against various evasion attacks, including gradient-based and optimization-based methods, under a black-box threat model.

An effective ensemble electricity theft detection algorithm for smart grid

AbstractSeveral machine learning and deep learning algorithms have been presented to detect the criminal behaviours in a smart grid environment in recent studies because of many successful results. However, most learning algorithms for the electricity theft detection have their pros and cons; hence, a critical research issue nowadays has been how to develop an effective detection algorithm that leverages the strengths of different learning algorithms. To demonstrate the performance of such an integrated detection model, the algorithm proposed first builds on deep neural networks, a meta‐learner for determining the weights of detection models for the construction of an ensemble detection algorithm and then uses a promising metaheuristic algorithm named search economics to optimise the hyperparameters of the meta‐learner. Experimental results show that the proposed algorithm is able to find better results and outperforms all the other state‐of‐the‐art detection algorithms for electricity theft detection compared in terms of the accuracy, F1‐score, area under the curve of precision‐recall (AUC‐PR), and area under the curve of receiver operating characteristic (AUC‐ROC). Since the results show that the meta‐learner of the proposed algorithm can improve the accuracy of deep learning algorithms, the authors expect that it will be used in other deep learning‐based applications.

Detection Method for Three-Phase Electricity Theft Based on Multi-Dimensional Feature Extraction.

The advent of smart grids has facilitated data-driven methods for detecting electricity theft, with a preponderance of research efforts focused on user electricity consumption data. The multi-dimensional power state data captured by Advanced Metering Infrastructure (AMI) encompasses rich information, the exploration of which, in relation to electricity usage behaviors, holds immense potential for enhancing the efficiency of theft detection. In light of this, we propose the Catch22-Conv-Transformer method, a multi-dimensional feature extraction-based approach tailored for the detection of anomalous electricity usage patterns. This methodology leverages both the Catch22 feature set and complementary features to extract sequential features, subsequently employing convolutional networks and the Transformer architecture to discern various types of theft behaviors. Our evaluation, utilizing a three-phase power state and daily electricity usage data provided by the State Grid Corporation of China, demonstrates the efficacy of our approach in accurately identifying theft modalities, including evasion, tampering, and data manipulation.

Developing and Implementing an Artificial Intelligence (AI)-Driven System For Electricity Theft Detection

Electricity theft is a significant challenge for utility companies worldwide, leading to substantial economic losses and inefficiencies in power distribution. Traditional methods of detecting electricity theft, such as manual inspections and routine audits, are often inefficient and ineffective. To address this issue, this study aims to develop and implement an artificial intelligence (AI)-driven system for electricity theft detection. Methodology used are data collection, data analysis, feature selection with Chi-Square, feature transformation with Principal Component Analysis (PCA), Support Vector Machine (SVM) and model for electricity theft detection. To achieve this, a Particle Swarm Optimization Algorithm (PSO) was applied to improve training performance of the SVM, using data of meter recharge information collected from Enugu Electricity Distribution Company (EEDC). The system effectiveness is validated through extensive testing using real-world data from various regions and scenarios, demonstrating its robustness and adaptability. The system result considering FDR reported that 0.11 was achieved for the particle swarm based SVM model. When TPR was considered for analysis, it was observed that particle swarm based SVM attained a score of 0.89. In addition, Particle swarm based SVM attained PPV of 0.895. In terms of accuracy, the particle swarm based SVM reported an accuracy of 0.857. The result showed that the particle swarm based SVM performed better from the system validation achieved through comparative analysis, hence it is recommended for use to develop the new software for energy theft investigation. The implementation of this AI-driven solution offers numerous benefits, including enhanced detection accuracy, reduced operational costs, and improved overall efficiency of power distribution networks. Moreover, it enables utility companies to take proactive measures to prevent theft, ensuring a more reliable and secure electricity supply for consumers.

Machine-learning techniques for enhancing electricity theft detection considering transformer reliability and supply interruptions

Machine-learning techniques are extensively used in fraud detection and have a huge potential application in electricity theft detection. Electricity theft occurs when consumers manipulate their electricity consumption to be recorded as lower than the actual, resulting in reduced revenue for the electricity supplier. This study explores the application of advanced machine-learning techniques to detect electricity theft, focusing on the impact on supply of electricity to electricity usage pattern. We used a dataset that contains supply interruptions influenced by transformer reliability to construct a robust detection model. This model integrates data analytic techniques from decision trees, support vector machines, k-nearest neighbors, and logistic regression classifiers. After selecting the optimal classifier, we used aggregated parameters to improve theft-detection accuracy. A comprehensive sensitivity analysis was used to evaluate the effects of variations in transformer reliability factors on interruption, interruption costs, electricity revenue, and theft-detection performance. Our findings indicate that using optimal aggregated parameters significantly enhances detection accuracy 10.709 percent, 11.435 percent, 4.909 percent, and 2.097 percent from original parameters depend on the number of aggregation in 2-hour, 4-hour, 6-hour, and 12-hour, respectively. The lower transformer reliability leads to increased loss with percentage 66.87 percent, 46.98 percent, 17.22 percent and reduced theft-detection efficiency by 27.32 percent, 19.23 percent, 6.20 percent. depend on reliability factor20 percent, 50 percent, and 80 percent, respectively.

Electricity theft detection model based on the CEEMDAN-CNN-ViT

Abstract Most of the traditional power theft detection methods construct the model directly on the basis of the original power sequences, and do not simultaneously consider the long-period dependencies in the long-time sequences and the local connectivity features between periods, which limits the deep excavation of the behavioral laws of power users. In order to further improve the accuracy of power theft detection, this paper proposes a high-precision power theft detection model that integrates local anomaly filtering, energy consumption decomposition, and multi-feature fusion strategies. First, local anomaly filtering is used to eliminate local anomalies in the normalized energy consumption data to avoid the misleading effect of short-term abnormal behavior on the model. Then, the energy consumption decomposition based on CEEMDAN selects specific frequency band data that can accurately characterize the pattern of power theft users to improve the accuracy of power theft detection. Next, the long-time periodic features in the two-dimensional data and the short-time local features in the one-dimensional sequences are integrated by multi-feature fusion to enhance the adaptability of the model. The results show that the proposed model can effectively improve the detection accuracy, detection completeness, F1 score, and accuracy compared with the existing methods.

Research on the identification and detection technology of electricity theft in power distribution areas under a smart grid environment

Abstract With the extensive application of smart meters, power companies can access a wealth of customer electricity usage data, which has not yet been fully utilized. This paper proposes a substation area user identification and electricity theft detection method based on smart meter data, aiming to enhance the level of intelligent management of power grid enterprises and reduce operational costs. By using the grey relational analysis method, analyzing the measurement data collected by smart meters at different time points, it is possible to determine the substation area and phase to which the user belongs and to detect electricity theft behavior. Finally, through simulation, the effectiveness of the proposed method is verified.

Review on Temporal Convolutional Networks for Electricity Theft Detection with Limited Data

Electricity theft detection using artificial intelligence (AI) and machine learning techniques have shown significant promise in recent research. However, practical implementation and widespread adoption of these advanced methods face several persistent challenges, particularly when dealing with limited data. This review delves into the computational complexity, data requirements, overfitting issues, and scalability and generalizability concerns associated with popular techniques such as Temporal Convolutional Networks (TCN), Long Short-Term Memory (LSTM), Deep Convolutional Neural Networks (DCNN), Multi-Layer Perceptron (MLP), Gated Recurrent Unit (GRU), and Artificial Neural Networks (ANN). Computational complexity and resource constraints affect the training times and convergence of TCN, LSTM, and DCNN, while high data needs and parameter tuning hinder MLP and GRU. The ANN-based method utilized by the Electricity Company of Ghana underscores overfitting and data duplication, further exacerbated by limited data availability. Moreover, the scalability and generalizability of TCN, LSTM, and DCNN across different regions and larger datasets are limited, with effectiveness varying based on electricity consumption patterns and theft tactics. Addressing these challenges through optimizing computational efficiency, improving data quality and utilization, and enhancing scalability and generalizability is crucial, especially in data-constrained environments. Continued research and development in these areas will be essential for realizing the full potential of AI-based electricity theft detection systems with limited data.

Deep learning-based electricity theft prediction in non-smart grid environments

In developing countries, smart grids are nonexistent, and electricity theft significantly hampers power supply. This research introduces a lightweight deep-learning model using monthly customer readings as input data. By employing careful direct and indirect feature engineering techniques, including Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), UMAP (Uniform Manifold Approximation and Projection), and resampling methods such as Random-Under-Sampler (RUS), Synthetic Minority Over-sampling Technique (SMOTE), and Random-Over-Sampler (ROS), an effective solution is proposed. Previous studies indicate that models achieve high precision, recall, and F1 score for the non-theft (0) class, but perform poorly, even achieving 0 %, for the theft (1) class. Through parameter tuning and employing Random-Over-Sampler (ROS), significant improvements in accuracy, precision (89 %), recall (94 %), and F1 score (91 %) for the theft (1) class are achieved. The results demonstrate that the proposed model outperforms existing methods, showcasing its efficacy in detecting electricity theft in non-smart grid environments.

Electricity Theft Detection Using Rule-Based Machine Leaning (rML) Approach

Since electricity theft affects non-technical losses (NTLs) in power distribution systems, power companies are genuinely quite concerned about it. Power companies can use the information gathered by Advanced Metering Infrastructure (AMI) to create data-driven, machine learning-based approaches for Electricity Theft Detection (ETD) in order to solve this problem. The majority of data-driven methods for detecting power theft do take usage trends into account while doing their analyses. Even though consumption-based models have been applied extensively to the detection of power theft, it can be difficult to reliably identify theft instances based only on patterns of usage. In this paper, a novel rule-based combined machine learning (rML) technique is developed for power theft detection to address the drawbacks of systems that rely just on consumption patterns. This approach makes use of the load profiles of energy users to establish rules, identify the rule or rules that apply to certain situations, and classify the cases as either legitimate or fraudulent. The UEDAS smart business power consumption dataset's real-world data is used to assess the performance of the suggested technique. Our technique is an innovation in theft detection that combines years of intensive theft tracking with the use of rule-based systems as feature spaces for traditional machine learning models. With an astounding 93% recall rate for the rule-based feature space combination of the random forest classifier, this novel approach has produced outstanding results. The acquired results show a noteworthy accomplishment in the field of fraud detection, successfully detecting fraudulent consumers 77% of the time during on-site examination.

Electricity Theft Detection in Smart Grids Using Sarimax and OCR

This study proposes a novel approach to detect electricity theft in smart grids by combining SARIMAX (Seasonal Autoregressive Integrated Moving Average with Exogenous Factors) models with Optical Character Recognition (OCR) techniques. Electricity theft remains a significant challenge in smart grid systems, leading to revenue losses and operational inefficiencies. Traditional methods often fall short in accurately identifying and addressing such illicit activities. The integration of SARIMAX models leverages time-series data, capturing patterns and anomalies indicative of electricity theft. These models incorporate exogenous factors such as weather conditions, economic indicators, and historical consumption patterns, enhancing the detection accuracy. Additionally, OCR technology is applied to analyze meter readings and identify discrepancies or irregularities that may signal potential theft instances. The synergy between SARIMAX and OCR offers a comprehensive solution for electricity theft detection in smart grids. By harnessing advanced analytics and machine learning algorithms, this approach enables utility providers to proactively identify suspicious activities, mitigate revenue losses, and ensure the integrity of their grid infrastructure

Improving Electricity Theft Detection Using Electricity Information Collection System and Customers’ Consumption Patterns

Electricity theft detection (ETD) techniques employed to identify fraudulent consumers often fail to accurately pinpoint electricity thieves in real time. The patterns associated with electricity use are leveraged to identify anomalies indicative of electricity theft. However, challenges in the benchmark ETD include overfitting and a high incidence of false positives (FPs) resulting from incorrect usage patterns formed by considering only electricity consumption patterns without accounting for external factors that contribute to variations in normal consumption patterns. Further investigation is required to precisely detect instances of electricity theft, thereby minimizing nontechnical losses and forecasting future electricity demand to maintain a stable supply. This study employs a master energy meter located on the transformer side to monitor the amount of energy distributed to the region. Zones with a high likelihood of energy theft are detected by comparing the sum of readings from all the smart meters with the readings from the master energy meter installed on the HV of the substation transformer within the same electric feeder. Ensemble XGBoost machine-learning algorithm and K-Means algorithm are used for the classification of malicious and nonmalicious samples and grouping similar types of consumers together, respectively. This makes the proposed model resistant to false-positive rates caused by changes in usage patterns that aren’t done on purpose. Furthermore, energy thieves are identified by detecting anomalies in consumption behavior while maintaining constant internal and external environmental variables. This novel model proposed here mitigates the FP rate found in the present research of electricity usage data. Our approach outperforms support vector machines, convolution neural network, and logistic regression in simulations. Precision, F1-score, recall, Matthews Correlation Coefficient, Receiver Operating Characteristics (ROC)-Area Under The Curve (AUC), and Precision Recal (PR)-Area Under The Curve (AUC) validate our model. The simulation results show that the proposed K-Means-LSTM-XGBoost model improved the classifier’s F1-score, precision, and recall to 93.75%, 95.16%, and 92.38%, respectively. Our model classifies huge time series data with high precision and can be utilized by the utility for real time electricity theft detection.

Deep Anomaly Detection Framework Utilizing Federated Learning for Electricity Theft Zero-Day Cyberattacks.

Smart power grids suffer from electricity theft cyber-attacks, where malicious consumers compromise their smart meters (SMs) to downscale the reported electricity consumption readings. This problem costs electric utility companies worldwide considerable financial burdens and threatens power grid stability. Therefore, several machine learning (ML)-based solutions have been proposed to detect electricity theft; however, they have limitations. First, most existing works employ supervised learning that requires the availability of labeled datasets of benign and malicious electricity usage samples. Unfortunately, this approach is not practical due to the scarcity of real malicious electricity usage samples. Moreover, training a supervised detector on specific cyberattack scenarios results in a robust detector against those attacks, but it might fail to detect new attack scenarios. Second, although a few works investigated anomaly detectors for electricity theft, none of the existing works addressed consumers' privacy. To address these limitations, in this paper, we propose a comprehensive federated learning (FL)-based deep anomaly detection framework tailored for practical, reliable, and privacy-preserving energy theft detection. In our proposed framework, consumers train local deep autoencoder-based detectors on their private electricity usage data and only share their trained detectors' parameters with an EUC aggregation server to iteratively build a global anomaly detector. Our extensive experimental results not only demonstrate the superior performance of our anomaly detector compared to the supervised detectors but also the capability of our proposed FL-based anomaly detector to accurately detect zero-day attacks of electricity theft while preserving consumers' privacy.

Detection of electricity theft based on Minimal Gated Memory network combined adaptive synthesis sampling and decision tree

Advanced metering infrastructure is the foundation for recording and analyzing the massive, high-frequency electricity consumption data. With the increasing number of electricity theft issues caused by tampering with smart meters, it is necessary to detect electricity theft anomalies. For effective electricity theft inspection, an electricity theft detection method based on Minimal Gated Memory（MGM） network combined Adaptive Synthesis (ADASYN) sampling and Decision Tree (DT) is proposed in this paper. The proposed method considers that the number of electricity theft consumers is far less than that of honest consumers, and the electricity theft detection is a problem of data imbalance. From the perspective of data, ADASYN sampling method is selected to process the sample data of electricity theft consumers. In order to detect electricity theft effectively, the DT is further introduced for feature selection, and combined with the newly proposed MGM network to distinguish honest consumers and electricity theft consumers. Six forms of electricity theft attacks are introduced in this research. Based on real data from smart meters in Ireland, two experiments are designed to demonstrate the effectiveness of the proposed method. The results show that our proposed method perform the best in Precision, Recall, F1-score and Area Under the Curve (AUC) when detecting electricity theft. The method proposed in this research can provide a new idea and approach for the detection of electricity theft and maintain the electricity supply quality and safety of smart grid.

Utilizing Machine Learning for Detecting Electricity Theft in Smart Grids

Smart grids, which provide several advantages, such as improved energy efficiency, less power outages, and higher security, are growing in popularity as a result of the rising need for electricity. But one of the biggest problems with smart grids is power theft, which costs utility companies a lot of money. Therefore, electric power distribution firms are quite concerned about theft of power. The purpose of this study is to offer an effective technique based on artificial neural networks (ANNs) for identifying Smart grid electricity theft. After training on a dataset of acceptable consumption patterns, the ANN model will be evaluated on information about energy theft events. The design will be tested using test data in order to assess the effectiveness of the suggested strategy. The outcomes that we anticipated from our suggested ANN-based method for Smart grid detection of electricity theft are favourable. 99% Training Accuracy and 99% Validation Accuracy were attained by our method. The performance measures that will be employed include F1-score, recall, accuracy, and precision. Additionally, we created the proposed system that makes use of the Flask Web framework to make it easier to use and provide a better user interface for outcome prediction. The research will likely produce an efficient method for employing ANN to identify energy theft in smart grids, which utility companies can utilise to increase revenue collection and fortify the security of the smart grid. This research may potentially be expanded to other fields, such intrusion detection in computer networks and fraud detection in financial systems, that entail anomaly identification in large-scale datasets

A self-decision ant colony clustering algorithm for electricity theft detection

The load data features of some electricity-theft consumers during the theft period are similar to those of normal consumers, making these electricity-theft consumers outliers from the cluster of electricity-theft. The current classification method, which uses the mean value to determine the cluster centers, is vulnerable to the influence of outliers. Therefore, this paper proposes a self-decision ant colony clustering algorithm for electricity theft detection method that is targeted to self-decision which samples are used to update the cluster centers. The method constructs a dynamic weighting approach to determine the cluster centers based on the idea of Backpropagation, and updates the weights of each sample in the clusters to reflect the different importance of different samples, thus reducing the influence of outlier samples. A new activation function, Odd, is proposed to enhance the ability of the proposed method to solve linearly indistinguishable problems. A self-decision dropout mechanism is proposed which evolves the mechanism of randomly stopping the work of samples in clusters into a targeted and self-decision mechanism that stops the work of redundant or non-active samples as well as improves the contribution of outlier samples with positive effects. In this paper, the proposed method is tested by the electricity consumption data provided by the State Grid Corporation of China (SGCC) and the Smart* Data Set for Sustainability (SDSS) provided by the UMass Trace Repository, and the experimental results show that the proposed method effectively solves the above problems with higher detection accuracy, it has certain advantages over other current studies.

A multiscale electricity theft detection model based on feature engineering

With the widespread adoption of smart meters and the growing availability of data mining and machine learning algorithms, there is a pressing demand for methods that are both accurate and explicable in identifying electricity theft patterns among end-users. To address this need, this study proposes a multi-scale anomaly detection model based on feature engineering.Specifically, tsfresh is utilized in feature engineering to extract electricity consumption features from the raw data, and XGBoost is employed to select features that are highly correlated with anomalous behavior, which have clear physical interpretations. Multi-scale convolutional neural networks are then used to analyze and process the data at different temporal and frequency scales. Attention mechanisms are applied to assign weights to different feature channels, and all of the extracted information is fused for anomaly detection. The combination of feature engineering and multi-scale convolutional neural networks not only enhances the interpretability of the model but also improves its performance, as demonstrated by the experimental results, which show that the proposed method outperforms traditional anomaly detection approaches across multiple evaluation metrics.

Integrated encoder-decoder-based wide and deep convolution neural networks strategy for electricity theft arbitration

Integrating energy systems with information systems in smart grids offers a promising avenue for combating electricity theft by leveraging real-time data insights. Suspicious activity indicative of theft can be identified through anomalous consumption patterns observed in smart networks. However, a smart model is required for capturing and analysing the data intelligently to accurately detect electricity theft. In the paper, electricity theft has been detected using an encoder-decoder-based classifier that integrates two models of convolutional neural networks (CNN). The aim is to scan the strength of the data and built a smart model that analysed the connections in complex data and determine the pattern of theft. The model comprises three compartments: the auto-encoder, the wide convolutional neural network (1-D CNN model), and the deep convolutional neural network (2-D CNN model). The auto-encoder has been trained on the complex and in-depth linkage between the theft data and the normal data as it removes noise and unnecessary information. The 1-D CNN model gathers relevant connections and general features, while the 2-D CNN model determines the rate at which energy theft occurs and differentiates between the energy-stealing consumers and normal consumers. The efficacy of the approach is underscored by its superiority over traditional deep learning and machine learning techniques. This paper elucidates the distinct advantages and applications of the proposed model in combating electricity theft within smart grid environments.

Research on FCM-LR cross electricity theft detection based on big data user profile

Research on FCM-LR cross electricity theft detection based on big data user profile

Machine learning-based electricity theft detection using support vector machines

Electricity theft is a serious issue that many nations face, especially in developing areas where non-technical losses can make up a significant percentage of the overall losses sustained by utilities. Electricity theft detection (ETD) is a very challenging task because it frequently introduces irregularities in customer electricity consumption patterns. In recent times, machine learning (ML) techniques have been investigated as a potential solution for ETD. In this research, author propose electricity theft detection based on four kernel functions of support vector machines (SVM). The proposed method analyzes the electricity consumption patterns and then predicts the category of the user. The kernel functions utilized includes polynomial, sigmoid, radial basis function (RBF) and linear kernel function. For experimentation and model training, a dataset of Pakistani utility company is used, which contains the electricity consumption information. The results highlight SVM method works well for accurate ETD. The detection accuracy of the various kernel functions of SVM is 83%, 79%, 80%, and 76% for RBF, polynomial, sigmoid, and linear kernel functions, respectively, demonstrating the effectiveness of the proposed SVM-based method for theft detection. By leveraging these ML-based methods, utility companies can strengthen their ability to detect and prevent electricity theft, leading to improved revenue management and dependability of services.