Search

Theft of electricity is an increasingly common problem that has a detrimental effect on utility providers as well as power consumers. It affects consumers’ high energy costs, creates electric risks, and affects the electric utility industry’s capacity to grow economically. The biggest issue facing smart grids is the theft of electricity. In order to monitor loads and regulate energy usage, smart meters (SMs) are installed at the end of customers’ residences and are used to periodically transmit fine-grained power consumption measurements to the supplier. Due to nonlinear correlations and missing values, existing theft detection techniques have difficulty processing large electrical usage information. An integrated system for coordinating the examination of electrical demand data is also absent. To address these limitations in this research we propose a new electricity theft detection framework to further enhance the system reliability and fault tolerance. Initially, we utilize the quantum key distribution (QKD) with the rolling optimization strategy (ROS) to reduce the computational overhead and efficiently minimize the fluctuations. After that extreme gradient boosting (EGB) and coati optimization algorithm (COA) are employed for classification. Finally, we proposed privacy functionality trade-off strategies for smart meters to improve the consumer trust and confidence in the smart grid system. Thus, the proposed new electricity theft detection framework to further enhance the system reliability and fault tolerance method’s simulation in Matlab-R2023a\Simulink demonstrates superior performance compared to existing techniques. The approaches in this study to overcome the issues faced in previous technologies are tested using different metrics of authentication rate at 98(%), accuracy at 99 (%), detection rate at 98.6 (%), precision at (97%), recall at (98.6%), at F1-score (95.15%), and AUC at (0.3123). [ABSTRACT FROM AUTHOR]

The theft of electricity is regarded as a global problem which creates negative impacts for both electricity users and utility companies. The economic development of utility companies gets destabilized which further leads to electric hazards, thereby increasing the energy cost. Numerous methods are utilized for substantial detection of electricity theft, but these approaches consume more time and are inefficient and expensive. Electricity theft detection also uses artificial intelligence techniques like deep learning and machine learning. Despite innovative and remarkable characteristics of these approaches, their performance is unsatisfactory. Taking these aforementioned issues into consideration, a cascaded region-based convolutional neural network with a cascade of specialized regressors is proposed in this work for efficient detection of electricity theft. The proposed classifier determines the close false positives for adjacent stage training enabling the generation of high quality detection of electricity theft. Initially, pre-processing which combines data interpolation and data normalization is carried out for the process of recovering missing values. An adaptive synthetic technique is utilized to address class imbalance issue owing to unbalanced data. In order to extract relevant features, a hybrid whale optimized chicken swarm algorithm is used which selects the accurate features thus performing the effective modelling of obtained electrical parameters. In comparison with existing approaches, the proposed work generates optimized results for performance metrics values with an accuracy of 94.3%, F1-Score of 94.58%, and precision of 94%. [ABSTRACT FROM AUTHOR]

Electricity theft is a major challenge for PT PLN (Persero), particularly in managing 27 million postpaid customers, most of whom still use traditional meters. Detecting and addressing electricity theft has become increasingly complex, requiring more efficient approaches. Unlike smart meters, traditional meters lack communication capabilities, making detection reliant on manual processes. This research develops a machine learning model to optimize the Target Operation (TO) process. TO is a list of customers targeted for on-site verification due to suspected electricity theft. This study focuses on optimizing the formation of TO by analyzing monthly electricity usage, particularly in the 450 VA household segment receiving government subsidies. The model aims to reduce reliance on subjective manual observations while ensuring proper subsidy allocation. Various classification models, including Decision Tree, Naive Bayes, Random Forest, K-Nearest Neighbors, Logistic Regression, and Deep Neural Network, were evaluated, with Random Forest achieving the best performance across simulations. A sequential evaluation method is introduced to enhance accuracy through layered filtering, where detection results from the three-theft model are further filtered using the two-theft and one-theft models, resulting in a more precise TO. The combination of Random Forest and K-Nearest Neighbors achieved the highest performance, with an accuracy of 0.89, precision of 0.83, recall of 0.98, F1-Score of 0.90, and AUC of 0.89. These findings demonstrate the model’s effectiveness in delivering reliable TO recommendations, supporting PLN’s operational strategies, and offering practical benefits through a more objective, standardized TO process that minimizes human error and improves efficiency.

To accurately locate electricity theft and reduce the economic losses caused by electricity theft to the power system, a multi-classification electricity theft detection model based on the entropy weight method Stacking E_Stacking(stacking based entropy) ensemble learning was proposed. First, based on the collinear characteristics of electricity consumption information, the VIF(variance inflation factor)was used as a standard to reduce the dimensionality of the data to reduce data complexity. Then k-fold cross-validation was embedded during model training to effectively prevent model overfitting. This model contained two layers of learners, a primary learner, and a meta-learner, it could fully combine the advantages of the two-layer learner and combine the learned complementary features and discriminative features to further improve detection performance. Finally, the Irish dataset and a portion of UCI(University of California Irvine)datasets were used to verify the model, and the results were better than several common methods at present, which demonstrates that the model has certain effectiveness and robustness. [ABSTRACT FROM AUTHOR]

One of the crucial issues for power grids in strengthening the urbanization around the world is imbalance between supply and demand, which leads the users to consume electricity in an anomalous manner without paying for it. Electricity theft plays a pivotal role in cutting down on the electricity bills. The existing data-oriented approaches for electricity theft detection (ETD) in the smart cities have limited ability to handle noisy high-dimensional data and features' associations. These limitations raise the misclassification rate, which makes some of the approaches unacceptable for electric utilities. A new twofold end-to-end methodology is proposed for ETD. In the first fold, it groups the similar electricity consumption (EC) cases through grey wolf optimization (GWO)-based clustering mechanism; clustering by fast search and find of density peaks (CFSFDP), we named it GC. In the second fold, a new relational stacked denoising autoencoder (RSDAE)-based semi-supervised generative adversarial network (GAN), termed as RGAN, is used for ETD. The combined methodology is named as GC-RGAN. In the methodology, RSDAE acts as both feature extraction technique and generator sub-model of the proposed RGAN. The proposed methodology utilizes the advantages of clustering, adversarial learning and semi-supervised EC data. Besides, to validate the effectiveness of the proposed solution, extensive simulations are performed using smart meter data. Simulation results validate the excellent ETD performance of the proposed GC-RGAN against existing ETD schemes, such as random forest and semi-supervised support vector machine. In comparison, GC-RGAN covers the ETD score of 98% that shows its suitability for real-world scenarios. The proposed solution has extraordinary performance for ETD as compared to traditional solutions, which shows its superiority and usefulness for real-world applications. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Electricity theft comes with various disadvantages for power utilities, governments, businesses, and the general public. This continues despite the various solutions employed to detect and prevent it. Some of the disadvantages of electricity theft include revenue loss and load shedding, leading to a disruption in business operations. This study aimed to conduct a systematic literature review to identify what technology solutions have been offered to solve electricity theft and the effectiveness of those solutions by considering peer-reviewed empirical studies. The systematic literature review was undertaken following the guidelines for conducting a literature review in computer science to assess potential bias. A total of 11 journal articles published from 2012 to 2022 in SCOPUS, Science Direct, and Web of Science were analysed to reveal solutions, the type of theft addressed, and the success and limitations of the solutions. The findings show that the focus in research is channelled towards solving electricity theft in Smart Grids (SGs) and Advanced Metering Infrastructure (AMI); moreover, there is a neglect in the recent literature on finding solutions that can prevent electricity theft in countries that do not have SG and AMI installed. Although the results reported in this study are confined to the analysed research papers, the leading limitation in the selected studies, lack of real-life data for dishonest users. This study’s contribution is to show what technology solutions are prevalent in solving electricity theft in recent years and the effectiveness of such solutions.

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. [ABSTRACT FROM AUTHOR]

Electricity theft comes with various disadvantages for power utilities, governments, businesses, and the general public. This continues despite the various solutions employed to detect and prevent it. Some of the disadvantages of electricity theft include revenue loss and load shedding, leading to a disruption in business operations. This study aimed to conduct a systematic literature review to identify what technology solutions have been offered to solve electricity theft and the effectiveness of those solutions by considering peer-reviewed empirical studies. The systematic literature review was undertaken following the guidelines for conducting a literature review in computer science to assess potential bias. A total of 11 journal articles published from 2012 to 2022 in SCOPUS, Science Direct, and Web of Science were analysed to reveal solutions, the type of theft addressed, and the success and limitations of the solutions. The findings show that the focus in research is channelled towards solving electricity theft in Smart Grids (SGs) and Advanced Metering Infrastructure (AMI); moreover, there is a neglect in the recent literature on finding solutions that can prevent electricity theft in countries that do not have SG and AMI installed. Although the results reported in this study are confined to the analysed research papers, the leading limitation in the selected studies, lack of real-life data for dishonest users. This study's contribution is to show what technology solutions are prevalent in solving electricity theft in recent years and the effectiveness of such solutions. [ABSTRACT FROM AUTHOR]

Copyright of Integrated Intelligent Energy is the property of Editorial Department of Integrated Intelligent Energy and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Nowadays, electricity theft is a major issue in many countries and poses a significant financial loss for global power utilities. Conventional Electricity Theft Detection (ETD) models face challenges such as the curse of dimensionality and highly imbalanced electricity consumption data distribution. To overcome these problems, a hybrid system Multi-Layer Perceptron (MLP) approach with Gated Recurrent Units (GRU) is proposed in this work. The proposed hybrid system is applied to analyze and solve electricity theft using data from the Chinese National Grid Corporation (CNGC). In the proposed hybrid system, first, preprocess the data; second, balance the data using the k-means Synthetic Minority Oversampling Technique (SMOTE) technique; third, apply the GTU model to the extracted purified data; fourth, apply the MLP model to the extracted purified data; and finally, evaluate the performance of the proposed system using different performance measures such as graphical analysis and a statistical test. To verify the consistency of our proposed hybrid system, we use three different ratios for training and testing the dataset. The outcomes show that the proposed hybrid system for ETD is highly accurate and efficient compared to the other models like Alexnet, GRU, Bidirectional Gated Recurrent Unit (BGRU) and Recurrent Neural Network (RNN). [ABSTRACT FROM AUTHOR]

Copyright of Gazi Üniversitesi Fen Bilimleri Dergisi Part C: Tasarım ve Teknoloji is the property of Gazi University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the energy sector, electricity theft presents serious financial and security risks. By fusing supervised learning models (Random Forest) with unsupervised learning algorithms (Isolation Forest, One-Class Support Vector Machine (SVM), Local Outlier Factor (LOF), and Density-Based Spatial Clustering of Applications with Noise(DBSCAN)), this study presents a unique hybrid technique for identifying power theft. The models are developed and tested by the study using data from the State Grid Corporation of China (SGCC). Data on power use is examined by unsupervised algorithms to find abnormalities, which are then further examined by the Random Forest classifier for increased precision. The hybrid models work well in identifying anomalous consumption patterns that point to theft without requiring large amounts of labeled data. To improve grid sustainability and lower non-technical losses, this study offers power providers a scalable and effective option. The study advances the discipline by providing an original model detection and demonstrating its potential application in practical scenarios.

With the development of advanced metering infrastructure (AMI), large amounts of electricity consumption data can be collected for electricity theft detection. However, the imbalance of electricity consumption data is violent, which makes the training of detection model challenging. In this case, this paper proposes an electricity theft detection method based on ensemble learning and prototype learning, which has great performance on imbalanced dataset and abnormal data with different abnormal level. In this paper, convolutional neural network (CNN) and long short-term memory (LSTM) are employed to obtain abstract feature from electricity consumption data. After calculating the means of the abstract feature, the prototype per class is obtained, which is used to predict the labels of unknown samples. In the meanwhile, through training the network by different balanced subsets of training set, the prototype is representative. Compared with some mainstream methods including CNN, random forest (RF) and so on, the proposed method has been proved to effectively deal with the electricity theft detection when abnormal data only account for 2.5% and 1.25% of normal data. The results show that the proposed method outperforms other state-of-the-art methods.

Electricity theft is a pervasive issue with economic implications that necessitate innovative approaches for its detection, given the critical challenge of limited labeled data. However, connecting smart home devices introduces numerous vectors for electricity theft. Therefore, this study introduces an innovative approach to detecting electricity theft in smart homes, leveraging knowledge-based, fine-grained, time-series appliance benign and anomalous consumption patterns. We simulated five attack classes and extended our model’s detection capabilities to unknown anomalies across residential settings by segmenting the anonymized data into three different home categories. We validated our experiment using simulated and real building attack data. Extreme Gradient Boost (XGB), Random Forest, and Multilayer Perceptron (MLP) outperform the legacy unsupervised model (LUM), which included MLP-Autoencoder (AE), 1D-CONV-AE, and Isolation Forest (RF). XGB had the highest average AUC scores of 98.69% and 98.74% for simulated and real attack detection, respectively, followed by RF at 96.76% and 97.07%, respectively, across all homes, indicating the robustness of our model in detecting benign and anomalous appliance consumption patterns. This study contributes to the academic discourse in the field and offers practical solutions to energy providers and stakeholders in the smart home industry.

Illegal electricity users pose a significant threat to the economic and security aspects of the power system by illicitly accessing or manipulating electrical resources. With the widespread adoption of Advanced Metering Infrastructure (AMI), researchers have turned to leveraging smart meter data for electricity theft detection. However, existing models rely on methods that model a single electricity load curve and cannot capture the temporal dependencies, periodicity, and underlying features between electricity consumption cycles. This study introduces a novel electricity theft detection method based on dynamic residual graph networks. Innovatively, it proposes a dynamic topological graph construction technique that allows for the real-time updating of adjacency matrices during the training process, thereby effectively capturing the complex relationships in electricity usage patterns. Utilizing the MixHop graph convolutional network, it delves into the temporal sequence dependencies, periodicity, and hidden characteristics within user electricity consumption data. Additionally, to address the issue of model instability caused by scarce theft data, we employ the SMOTE (Synthetic Minority Over-sampling Technique) oversampling technique and enhance overall classification performance by modifying class weights in the loss function. We trained this network architecture on the real SGCC (State Grid Corporation of China) dataset, and the results demonstrate its superiority over other mainstream existing models.

Electricity theft is a prevalent global issue that has detrimental effects on both utility providers and electricity consumers. This phenomenon undermines the economic stability of utility companies, worsens power hazards, and influences electricity costs for consumers. The advancements in Smart Grid technology play an essential role in Electricity Theft Detection (ETD), as they generate large amounts of data that can be effectively utilized for ETD through the application of Machine Learning (ML) and Deep Learning (DL) methodologies. The present study presents a novel approach for ETD by combining Omni-Scale CNN (OS-CNN) and AutoXGB. Firstly, the Piecewise Cubic Hermite Interpolating Polynomial (PCHIP) is employed as the data interpolation technique to address the limitations and missing data in the dataset. Additionally, a combination of the Synthetic Minority Over-Sampling Technique (SMOTE) and the Edited Nearest Neighbors (ENN), known as SMOTEENN, is utilized for data resampling to tackle the issue of class imbalance in the dataset. Secondly, the multi-layer Omni-Scale block stack is employed to effectively cover the receptive fields of diverse time series scales based on a straightforward rule. This enables the One-dimensional Convolutional Neural Network (1D-CNN) to acquire enhanced learning capabilities for both irregular electricity consumption data anomalies and periodic normal electricity consumption patterns in smart grid datasets, facilitating superior extraction of essential data features. The AutoXGB classifier is then utilized to classify the extracted features. AutoXGB possesses the capability of automatically optimizing the hyperparameters required by the model, ensuring that the classification model maintains optimal accuracy and settings. Finally, the method exhibits superior competitiveness compared to other methods on the same dataset. The experimental results demonstrate that the proposed model achieves an accuracy rate of 99.2%, a precision rate of 97.5%, and an area under the ROC curve of 98.4%. These results establish its significant superiority over alternative models.

Given the low accuracy of the traditional electricity theft detection method based on one-dimensional electricity consumption data mining and analysis， a detection method for electricity theft by distribution network users based on a hybrid neural network is proposed. Firstly， to enhance the characteristic difference between the electricity consumption of normal users and that of power theft users， the Markov transition field （MTF） is used to transform one-dimensional electricity consumption data into two-dimensional graphs. Moreover， to improve the accuracy and generalization of the model， profile data of users' electricity consumption is introduced. Then， the hybrid neural network is used to extract and fuse the feature quantities of the preprocessed two-dimensional electricity consumption graphs and profile data respectively to detect electricity theft by distribution network users. Finally， the effectiveness and accuracy of the proposed method are verified through two sets of comparison experiments. The experimental results show that the method based on a hybrid neural network is superior to other models in detection accuracy of electricity theft， recall rate， and AUROC （area under the receiver operating characteristics）， and has higher detection performance.

Abstract The rapid increase in nontechnical loss (NTL) has become a principal concern for distribution system operators (DSOs) over the years. Electricity theft makes up a major part of NTL. It causes losses for the DSOs and also deteriorates the quality of electricity. The introduction of advanced metering infrastructure along with the upgradation of the traditional grids to the smart grids (SGs) has helped the electric utilities to collect the electricity consumption (EC) readings of consumers, which further empowers the machine learning (ML) algorithms to be exploited for efficient electricity theft detection (ETD). However, there are still some shortcomings, such as class imbalance, curse of dimensionality, and bypassing the automated tuning of hyperparameters in the existing ML‐based theft classification schemes that limit their performances. Therefore, it is essential to develop a novel approach to deal with these problems and efficiently detect electricity theft in SGs. Using the salp swarm algorithm (SSA), gate convolutional autoencoder (GCAE), and cost‐sensitive learning and long short‐term memory (CSLSTM), an effective ETD model named SSA–GCAE–CSLSTM is proposed in this work. Furthermore, a hybrid GCAE model is developed via the combination of gated recurrent unit and convolutional autoencoder. The proposed model comprises five submodules: (1) data preparation, (2) data balancing, (3) dimensionality reduction, (4) hyperparameters' optimization, and (5) electricity theft classification. The real‐time EC data provided by the state grid corporation of China are used for performance evaluations via extensive simulations. The proposed model is compared with two basic models, CSLSTM and GCAE–CSLSTM, along with seven benchmarks, support vector machine, decision tree, extra trees, random forest, adaptive boosting, extreme gradient boosting, and convolutional neural network. The results exhibit that SSA–GCAE–CSLSTM yields 99.45% precision, 95.93% F1 score, 92.25% accuracy, and 71.13% area under the receiver operating characteristic curve score, and surpasses the other models in terms of ETD.

Nowadays, electricity theft is a major issue in many countries and poses a significant financial loss for global power utilities. Conventional Electricity Theft Detection (ETD) models face challenges such as the curse of dimensionality and highly imbalanced electricity consumption data distribution. To overcome these problems, a hybrid system Multi-Layer Perceptron (MLP) approach with Gated Recurrent Units (GRU) is proposed in this work. The proposed hybrid system is applied to analyze and solve electricity theft using data from the Chinese National Grid Corporation (CNGC). In the proposed hybrid system, first, preprocess the data; second, balance the data using the k-means Synthetic Minority Oversampling Technique (SMOTE) technique; third, apply the GTU model to the extracted purified data; fourth, apply the MLP model to the extracted purified data; and finally, evaluate the performance of the proposed system using different performance measures such as graphical analysis and a statistical test. To verify the consistency of our proposed hybrid system, we use three different ratios for training and testing the dataset. The outcomes show that the proposed hybrid system for ETD is highly accurate and efficient compared to the other models like Alexnet, GRU, Bidirectional Gated Recurrent Unit (BGRU) and Recurrent Neural Network (RNN).

The successful implementation of Smart Grids heavily relies on energy efficiency, particularly through the Advanced Metering Infrastructure (AMI) and Smart Electricity Meters (SEM). However, cyber-attacks pose a threat to SEM, with electricity theft being a primary motivation. Despite the valuable data provided by SEM for analytical purposes, existing methods to identify theft involve cumbersome and costly on-site inspections. This research proposes an electricity theft detection model using the Long Short-Term Memory (LSTM) network. The model employs a collective anomaly approach, defining prediction errors through a threshold and forecast horizon. Suspicious consumption profiles are analysed, and a fuzzy inference system (FIS) implemented in MATLAB 2021b is used to model security risks based on these profiles. The study utilizes energy consumption data from four diverse consumer profiles (consumers 1, 2, 3, and 4) to develop consumer-specific LSTM models for detection and an FIS model for confirmation. Tampered consumer data is identified and confirmed based on selected AMI parameters. While all consumers exhibit suspicious profiles at times, only consumers 2 and 3 are confirmed as engaging in electricity theft. This research provides a robust approach to detecting and verifying fraudulent consumption profiles within the context of AMI, offering a more reliable dimension to theft detection and confirmation.

To enhance the accuracy of theft detection for electricity consumers, this paper introduces a novel strategy based on the fusion of the dual-time feature and deep learning methods. Initially, considering electricity-consumption features at dual temporal scales, the paper employs temporal convolutional networks (TCN) with a long short-term memory (LSTM) multi-level feature extraction module (LSTM-TCN) and deep convolutional neural network (DCNN) to parallelly extract features at these scales. Subsequently, the extracted features are coupled and input into a fully connected (FC) layer for classification, enabling the precise detection of theft users. To validate the method's effectiveness, real electricity-consumption data from the State Grid Corporation of China (SGCC) is used for testing. The experimental results demonstrate that the proposed method achieves a remarkable detection accuracy of up to 94.7% during testing, showcasing excellent performance across various evaluation metrics. Specifically, it attained values of 0.932, 0.964, 0.948, and 0.986 for precision, recall, F1 score, and AUC, respectively. Additionally, the paper conducts a comparative analysis with mainstream theft identification approaches. In the comparison of training processes, the proposed method exhibits significant advantages in terms of identification accuracy and fitting degree. Moreover, with adjustments to the training set proportions, the proposed method shows minimal impact, indicating robustness. [ABSTRACT FROM AUTHOR]

Copyright of Zhejiang Electric Power is the property of Zhejiang Electric Power Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Electricity theft represents a pressing problem that has brought enormous financial losses to electric utility companies worldwide. In the United States alone, $6 billion worth of electricity is stolen annually. Traditionally, electricity theft is committed in the consumption domain via physical attacks that includes line tapping or meter tampering. Therefore, this project evaluating performance of various deep learning algorithms such as deep feed forward neural network (DNN), recurrent neural network with gated recurrent unit (RNN-GRU) and convolutional neural network (CNN) for electricity cyber-attack detection. Now-a-days in advance countries solar plates are used to generate electricity and these users can sale excess energy to other needy users and they will be maintained two different meters which will record consumption and production details. While producing some malicious users may tamper smart meter to get more bill which can be collected from electricity renewable distributed energy. This attack may cause huge losses to agencies. To detect such attack, this project is employing deep learning models which can detect all possible alterations to predict theft. [ABSTRACT FROM AUTHOR]

Abstract As an important edge device of power grid, smart meters enable the detection of illegal behaviors such as electricity theft by analyzing large-scale electricity consumption data. Electricity theft poses a major threat to the economy and the security of society. Electricity theft detection (ETD) methods can effectively reduce losses and suppress illegal behaviors. On electricity consumption data from smart meters, ETD methods always train deep learning models. However, these methods are limited to extract different electricity consumption characteristics between independent users, and the pattern differences between users cannot be actively learned. Such difficulty prevents ETD further performance improvement. Therefore, a novel ETD method is proposed, which is the first attempt to apply supervised contrastive learning for electricity theft detection. On the one hand, our method allows the detection model to improve its detection performance by actively comparing users’ representation vectors. On the other hand, in order to obtain high-quality augmented views, largest triangle three buckets time series downsampling is adopted innovatively to improve model stability through data augment. Experiments on real-world datasets show that our model outperforms state-of-the-art models.

Abstract To solve the problem of low accuracy of the previous electricity theft detection methods, the authors propose a multi‐domain feature (MDF) fusion electricity theft detection method based on improved tensor fusion (ITF). Firstly, the original electricity consumption series is transformed by gram angle field (GAF) to obtain the time‐domain matrix. The original electricity consumption series is converted into frequency‐domain by Maximal Overlap Discrete Wavelet Transform (MODWT) to obtain the frequency‐domain matrix. Then, the convolutional neural networks (CNN) are used to extract features of the time‐domain matrix and frequency‐domain matrix, respectively. Next, in order to fuse single‐domain feature information and MDF interaction information while reducing redundant information, the authors propose an ITF method to obtain a multi‐domain fusion tensor. Finally, the multi‐domain fusion tensor is input into the electricity theft inference module to judge whether the user implements electricity theft behaviour. The authors simulate six electricity theft types and evaluate the method's performance separately for each electricity theft type. The results show that the proposed method outperforms other methods.

Illicitly obtaining electricity, commonly referred to as electricity theft, is a prominent contributor to power loss. In recent years, there has been growing recognition of the significance of neural network models in electrical theft detection (ETD). Nevertheless, the existing approaches have a restricted capacity to acquire profound characteristics, posing a persistent challenge in reliably and effectively detecting anomalies in power consumption data. Hence, the present study puts forth a hybrid model that amalgamates a convolutional neural network (CNN) and a transformer network as a means to tackle this concern. The CNN model with a dual-scale dual-branch (DSDB) structure incorporates inter- and intra-periodic convolutional blocks to conduct shallow feature extraction of sequences from varying dimensions. This enables the model to capture multi-scale features in a local-to-global fashion. The transformer module with Gaussian weighting (GWT) effectively captures the overall temporal dependencies present in the electricity consumption data, enabling the extraction of sequence features at a deep level. Numerous studies have demonstrated that the proposed method exhibits enhanced efficiency in feature extraction, yielding high F1 scores and AUC values, while also exhibiting notable robustness. [ABSTRACT FROM AUTHOR]

Due to the illegal use of electricity, non-technical losses are exponentially increasing in electricity distribution systems day by day. With the debut of smart meters in the smart grid, new electricity theft attacks are welcomed. The investigation of abnormal electricity consumption patterns helps in detecting electricity thieves. Moreover, existing methods have poor electricity theft detection (ETD) accuracy due to imbalanced datasets provided by the utilities. They have also failed to capture both periodicity and non-periodicity of 1-D daily electricity usage data. We primarily propose a novel sampling technique to balance the dataset, named as random oversampling using both classes (ROBC). This technique performs oversampling using both the theft and normal classes. With this technique, the problem of low accuracy has been resolved. We also propose a unique ETD model using densenet-fully convolutional network (DenseNet-FCN) and gated recurrent unit (GRU) with a light gradient boosting machine (LightGBM), known as DenseNet-GRU-LightGBM, to address the above mentioned concerns. DenseNet-FCN module extracts periodic and non-periodic patterns from 2-D electricity consumption data in a precise way. Whereas, GRU module captures as well as memorizes features from 1-D consumption data. Afterwards, LightGBM module is used as an ensemble classifier to give final ETD results. As a result, the proposed model has excellent ETD results. Comprehensive simulations indicate that the proposed scheme outperforms other existing methods regarding ETD.

This paper proposes a novel convolution–non-convolution parallel deep network (CNCP)-based method for electricity theft detection. First, the load time series of normal residents and electricity thieves were analyzed and it was found that, compared with the load time series of electricity thieves, the normal residents' load time series present more obvious periodicity in different time scales, e.g., weeks and years; second, the load times series were converted into 2D images according to the periodicity, and then electricity theft detection was considered as an image classification issue; third, a novel CNCP-based method was proposed in which two heterogeneous deep neural networks were used to capture the features of the load time series in different time scales, and the outputs were fused to obtain the detection result. Extensive experiments show that, compared with some state-of-the-art methods, the proposed method can greatly improve the performance of electricity theft detection. [ABSTRACT FROM AUTHOR]

As an important edge device of power grid, smart meters enable the detection of illegal behaviors such as electricity theft by analyzing large-scale electricity consumption data. Electricity theft poses a major threat to the economy and the security of society. Electricity theft detection (ETD) methods can effectively reduce losses and suppress illegal behaviors. On electricity consumption data from smart meters, ETD methods always train deep learning models. However, these methods are limited to extract different electricity consumption characteristics between independent users, and the pattern differences between users cannot be actively learned. Such difficulty prevents ETD further performance improvement. Therefore, a novel ETD method is proposed, which is the first attempt to apply supervised contrastive learning for electricity theft detection. On the one hand, our method allows the detection model to improve its detection performance by actively comparing users' representation vectors. On the other hand, in order to obtain high-quality augmented views, largest triangle three buckets time series downsampling is adopted innovatively to improve model stability through data augment. Experiments on real-world datasets show that our model outperforms state-of-the-art models. [ABSTRACT FROM AUTHOR]

Aiming at the limitation of traditional detection model for electricity stealing detection only by a single method and the class imbalance in electricity consumption data, an electricity theft detection model based on the entropy weight method fusing heterogeneous classifiers from the perspective of ensemble learning was proposed. Firstly, the problem of imbalance in electricity consumption data was handled by synthetic minority oversampling technique (SMOTE). Secondly, the diversity of individual classifiers and their respective detection performance and training mechanism were considered to optimize the base classifier. Finally, the concept of information entropy was introduced to calculate the weight share of each base classifier based on the dispersion of its classification results, and the output of each base classifier was integrated with this weight share. The experimental results show that compared with the traditional electricity stealing detection model, the model proposed in this paper performs better in multiple evaluation indicators and has good detection performance. [ABSTRACT FROM AUTHOR]

Electricity theft is a major cause of non-technical loss (NTL) in smart grids. However, existing research on electricity theft detection (ETD) lacks a generalized analysis of the characteristics of theft behaviors and fails to effectively address the problem of unbalanced sample distribution; the electricity theft features they recognize are also singular. To address these problems, a novel approach consisting of a sample augmentation mechanism based on convolutional transformer-Wasserstein generative adversarial networks (CT-WGANs) and an electricity theft detection scheme using bridged multiscale convolutional neural network-bidirectional gate recurrent units (MCNN-BiGRUs) is proposed in this paper. First, the generalized characteristics of electricity theft behavior in multiple time dimensions are analyzed, and the data slices are constructed. Then, with the aim of reducing the influence of unbalanced sample distribution, CT-WGAN, which focuses on the generalized characteristics of electricity theft in various time dimensions, is designed and has better sample generation capability. Finally, a bridged MCNN-BiGRU is proposed to recognize the temporal, transition, and persistence characteristics of electricity theft to improve the efficiency of ETD. Experimental results on the State Grid Corporation of China (SGCC) and Irish Smart Energy Trial (ISET) datasets show that the proposed approach outperforms traditional schemes in terms of the area under curve (AUC), precision, recall, f1-score, and accuracy. [ABSTRACT FROM AUTHOR]

Despite the widespread use of artificial intelligence-based methods in detecting electricity theft by smart grid customers, current methods suffer from two main flaws: a limited amount of data on electricity theft customers compared to that on normal customers and an imbalanced dataset that can significantly affect the accuracy of the detection method. Additionally, most existing methods for detecting electricity theft rely solely on one-dimensional electricity consumption data, which fails to capture the periodicity of consumption and overlooks the temporal correlation of customers' electricity consumption based on their weekly, monthly, or other time scales. To address the mentioned issues, this paper proposes a novel approach that first employed a time series generative adversarial network to balance the dataset by generating synthetic data for electricity theft customers. Then, a hybrid multi-time-scale neural network-based model was utilized to extract customers' features and a CatBoost classifier was applied to achieve classification. Experiments were conducted on a real-world smart meter dataset obtained from the State Grid Corporation of China. The results demonstrated that the proposed method could detect electricity theft by customers with a precision rate of 96.64%, a recall rate of 96.87%, and a significantly reduced false detection rate of 3.77%. [ABSTRACT FROM AUTHOR]

To solve the problem of low accuracy of the previous electricity theft detection methods, the authors propose a multi‐domain feature (MDF) fusion electricity theft detection method based on improved tensor fusion (ITF). Firstly, the original electricity consumption series is transformed by gram angle field (GAF) to obtain the time‐domain matrix. The original electricity consumption series is converted into frequency‐domain by Maximal Overlap Discrete Wavelet Transform (MODWT) to obtain the frequency‐domain matrix. Then, the convolutional neural networks (CNN) are used to extract features of the time‐domain matrix and frequency‐domain matrix, respectively. Next, in order to fuse single‐domain feature information and MDF interaction information while reducing redundant information, the authors propose an ITF method to obtain a multi‐domain fusion tensor. Finally, the multi‐domain fusion tensor is input into the electricity theft inference module to judge whether the user implements electricity theft behaviour. The authors simulate six electricity theft types and evaluate the method's performance separately for each electricity theft type. The results show that the proposed method outperforms other methods. [ABSTRACT FROM AUTHOR]

Electricity theft is the largest type of non-technical losses faced by power utilities around the globe. It not only raises revenue losses to the utilities but also leads to lethal fires and electric shocks at distribution side. In the past, field operation groups were sent by the utilities to conduct inspections of suspicions electric equipments stated by the public. Advanced metering infrastructure based recent development in the smart grids makes it easy to detect electricity thefts. However, the conventional supervised learning techniques have low theft detection performance mainly due to imbalance datasets available for training. Therefore, in this paper, we develop a novel theft detection model with twofold contribution. A unique hybrid sampling technique named as hybrid oversampling and undersampling using both classes (HOUBC) is proposed to balance the dataset. HOUBC first performs undersampling and then oversampling using both the majority (normal) and minority (theft) classes. A new deep learning method, fractal network is applied with light gradient boosting method to extract and learn important characteristics from electricity consumption profiles for identifying electricity thieves. The proposed model relies on smart meter's data for theft detection and hence, a rapid and widespread adaption of this model is feasible, which shows its main advantage. The performance of the model is evaluated with real-world smart meter's data, i.e., state grid corporation of China. Comprehensive simulation results describe the effectiveness of the proposed model against conventional schemes in terms of electricity theft detection.

Electricity ranks among the world’s most plundered commodities. The fraudulent act of acquiring electrical power without paying for it is termed electricity theft. Electricity theft is captured in power distribution systems as non-technical losses (NTL), representing a major loss in revenue for power utility companies. Electricity theft has far-reaching financial consequences owing to unrealised revenue, and this has a knock-on effect on both developed and developing countries because electricity represents a major part of a country’s GDP and facilitates other industries. AMI-based smart energy meters (SM) gather large amounts of electricity consumption (EC) data that power utilities can utilise to monitor and detect fraudulent customers. This EC data is fed to a machine learning (ML) based electricity theft detection model to learn the behaviour of fraudulent customers. However, existing ML-based electricity theft detection (ETD) models do not produce the best outcomes because of; consecutive missing values in EC datasets, data class imbalance problems, inappropriate hyperparameter tuning of ML models, etc. This research introduces an ETD model using an extremely randomised trees classifier to detect electricity theft in smart grids efficiently. SMOTE Tomek sampling is used to deal with the data class imbalance, and the grid search optimisation technique is employed to optimise the hyperparameters of the proposed model. The proposed model shows its capacity to detect electricity theft by obtaining 98%, 95.06%, 98%, 97%, 98%, and 99.65% accuracy, Matthew’s correlation coefficient, detection rate, Precision, F1-score, and area under the curve receiver operating characteristic, respectively.

Electricity theft is a critical issue in smart grids, leading to significant financial losses for utilities and compromising the stability and reliability of the power system. Existing centralized methods for electricity theft detection raise privacy and security concerns due to the need for sharing sensitive customer data. To address these challenges, we propose HeteroFL, a novel heterogeneous federated learning framework for privacy-preserving electricity theft detection in smart grids. HeteroFL enables retailers to collaboratively train a global model without sharing their private data, while accounting for the class imbalance problem prevalent in electricity theft datasets. We introduce a data partitioning and aggregation scheme that assigns different weights to classes, ensuring a balanced contribution and representation of each class in the global model. In addition, our framework leverages the CKKS homomorphic encryption scheme to perform secure computations on encrypted parameters and employs a CNN-LSTM model to capture the spatial and temporal dependencies in electricity consumption patterns. We evaluate HeteroFL using a real-world smart grid dataset and demonstrate its effectiveness and efficiency in detecting energy theft. Furthermore, we analyze the robustness and perform ablation studies to validate the framework's stability and identify the contributions of its key components. Although the impact of approximation errors introduced by the CKKS scheme on the CNN-LSTM model's performance requires further investigation, our framework presents a promising solution for privacy-preserving and accurate electricity theft detection in smart grids using heterogeneous federated learning. • HeteroFL detects electricity theft without sharing raw customer data, ensuring privacy. • Novel techniques in HeteroFL ensure accurate theft detection even with imbalanced datasets. • Secure aggregation with CKKS encryption protects model updates in HeteroFL from attacks. • HeteroFL's hybrid CNN-LSTM model effectively captures consumption patterns for accurate theft detection. • The HeteroFL framework is validated on a smart grid dataset, outperforming baseline methods. [ABSTRACT FROM AUTHOR]

With the application of the advanced measurement infrastructure in power grids, data driven electricity theft detection methods become the primary stream for pinpointing electricity thieves. However, owing to anomaly submergence, which shows that the usage patterns of electricity thieves may not always deviate from those of normal users, the performance of the existing usage-pattern-based method could be affected. In addition, the detection results of some unsupervised learning algorithm models are abnormal degrees rather than “0-1” to ascertain whether electricity theft has occurred. The detection with fixed threshold value may lead to deviation and would not be sufficiently flexible to handle the detection for different scenes and users. To address these issues, this study proposes a new electricity theft detection method based on load shape dictionary of users. A corresponding strategy for tunable threshold is proposed to optimize the detection effect of electricity theft, and the efficacy and applicability of the proposed adaptive electricity theft detection method were verified from numerical experiments.

Today, electricity theft is one of the main challenges for energy distribution and transmission companies around the world. Early detection of abnormal consumers can prevent security and financial losses. Extensive research studies have been done to detect electricity theft by analyzing customer consumption patterns. Today, one of the most widely used methods is convolutional neural networks (CNNs). These networks contain a large number of hyper-parameters. The accuracy of these networks is low in most studies due to the lack of attention to the adjustment of these hyperparameters. Network accuracy and achieving a robust learning model are influenced by the optimal adjusting of these hyper-parameters, which requires exploring a complex and large search space. Meta-heuristic-based search methods are suitable for solving these problems. Therefore, the main contribution of this paper is to use the high ability of the cheetah optimization algorithm (CHOA) to optimally extract CNN hyper-parameters. In this paper, in order to balance the dataset, abnormal samples are created using artificial attacks and added to the dataset. Also, in order to increase the accuracy of the network, abnormal data are clustered using the CHOA algorithm. ISSDA dataset is used to test and evaluate the results. Based on the results obtained and comparing them with the other works, it was proved that the proposed framework with high accuracy identifies abnormal consumers. [ABSTRACT FROM AUTHOR]

Owing to the contagiousness of theft behaviors among customers, collaborative energy theft, such as village fraud, has become particularly common. In this study, a bunch of electricity thieves that steal energy at a constant ratio were considered. Conventional correlation-sorting-based methods may have some trouble handling these electricity thieves when they exist in the same area. To overcome such limitation, we firstly establish the mathematical model of non-technical loss (NTL) and the load data of fixed ratio electricity thieves (FRETs). Subsequently, an interesting correlation trend, which can be exploited to locate FRETs, was observed and analyzed. Based on this trend, we propose a correlation analysis-based detection method. It adopts a standardized covariance to measure the correlation between the NTL and user data. The detection of FRETs is realized by solving a combinatorial optimization problem. A corresponding framework in practice was also designed. Finally, numerical experiments based on a realistic dataset and an electricity theft dataset from an electricity theft emulator (ETE) are conducted to validate the effectiveness and superiority of the proposed method in terms of accuracy, stability, and scalability.

Electricity theft (ET) is an utmost problem for power utilities because it threatens public safety, disturbs the normal working of grid infrastructure and increases revenue losses. In the literature, many machine learning (ML), deep learning (DL) and statistical based models are introduced to detect ET. However, these models do not give optimal results due to the following reasons: curse of dimensionality, class imbalance problem, inappropriate hyper-parameter tuning of ML and DL models, etc. Keeping the aforementioned concerns in view, we introduce a hybrid DL model for the efficient detection of electricity thieves in smart grids. AlexNet is utilized to handle the curse of dimensionality issue while the final classification of energy thieves and normal consumers is performed through adaptive boosting (AdaBoost). Moreover, class imbalance problem is resolved using an undersampling technique, named as near miss. Furthermore, hyper-parameters of AdaBoost and AlexNet are tuned using artificial bee colony optimization algorithm. The real smart meters’ dataset is used to assess the efficacy of the hybrid model. The substantial amount of simulations proves that the hybrid model obtains the highest classification results as compared to its counterparts. Our proposed model obtains 88%, 86%, 84%, 85%, 78% and 91% accuracy, precision, recall, F1-score, Matthew correlation coefficient and area under the curve receiver operating characteristics, respectively.

In this paper, we present a hybrid deep learning model that is based on a two-dimensional convolutional neural network (2D-CNN) and a bidirectional long short-term memory network (Bi-LSTM)to detect non-technical losses (NTLs) in smart meters. NTLs occur due to the fraudulent use of electricity. The global integration of smart meters has proven to be beneficial for the storage of historical electricity consumption (EC) data. The proposed methodology learns the deep insights from the historical EC data and informs power utilities about the presence of NTLs. However, the effective detection of NTLs faces the problem of class imbalance that occurs due to the rare availability of fraudulent electricity consumers. To solve this issue, an evolutionary bidirectional Wasserstein generative adversarial network (Bi-WGAN) is employed. Bi-WGAN synthesizes the most plausible fraudulent EC samples by integrating an auxiliary encoder module. Besides, the inevitable curse of high dimensional data reduces the generalization ability of classifiers. The proposed hybrid model efficiently handles the highly dynamic data by utilizing its potent feature extracting capabilities. The one-dimensional daily EC data is passed to Bi-LSTM model for capturing the non-malicious changes from consumers’ profiles. Meanwhile, 2D-CNN takes 2D weekly EC data as input to extract the potential features by applying different convolutions and pooling operations. Extensive experiments are conducted on a realistic smart meters dataset to prove the effectiveness of the proposed model. The results show that the proposed model outperforms the state-of-the-art models by achieving area under the curve receiver operating characteristics of 0.97 and precision-recall area under the curve of 0.98, which make it suitable for real-world scenarios.

Electricity theft causes significant damage to social and economic development.How to detect malicious electricity theft based on power big data has been widely concerned by academia and industry.Aiming at the problems of traditional methods relying on manual features,insufficient behavior sequence representation,poor detection accuracy,etc.,this paper proposes an electricity theft detection model based on multi-head attention mechanism (ETD-MHA).The bidirectional gated recurrent unit is used to fully capture the time features of the electricity consumption behavior sequence,and the distinction of key features is gradually enhanced in the multi-head attention mechanism,and finally,the learning effect is improved by deepening the networks.Extended experiments are conducted on the smart meter datasets of Ireland and China State Grid.The results show that the proposed method achieves better performance compared with the linear regression (LR),support vector machine (SVM),random forest (RF),and other traditional algorithms.For example,the AUC value of the proposed model is improved by up to 34.6%compared to the LR algorithm.

Electricity theft is considered one of the most significant reasons of the non technical losses (NTL). It negatively influences the utilities in terms of the power supply quality, grid’s safety, and economic loss. Therefore, it is necessary to effectively deal with the electricity theft problem. For detecting electricity theft in smart grids (SGs), an efficient and state-of-the-art approach is designed in the underlying work based on autoencoder and bidirectional gated recurrent unit (AE-BiGRU). The proposed approach consists of six components: (1) data collection, (2) data preparation, (3) data balancing, (4) feature extraction, (5) classification and (6) performance evaluation. Moreover, bidirectional gated recurrent unit (BiGRU) is used for the identification of the anomalies in electricity consumption (EC) patterns caused due to factors like family formation changes, holidays, parties, and so on, which are referred as non-theft factors. The proposed autoencoder-bidirectional gated recurrent unit (AE-BiGRU) model employs the EC data acquired from state grid corporation of China (SGCC) for simulations. Furthermore, it is visualized from the simulation results that 90.1% accuracy and 10.2% false positive rate (FPR) are obtained by the proposed model. The results are better than different existing classifiers, i.e., logistic regression (LR), decision tree (DT), extreme gradient boosting (XGBoost), gated recurrent unit (GRU), etc.

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.

Non-technical loss is a serious issue around the globe. Consumers manipulate their smart meter (SM) data to under-report their readings for financial benefit. Various manipulation techniques are used. This paper highlights novel false data injection (FDIs) techniques, which are used to manipulate the smart meter data. These techniques are introduced in comparison to six theft cases. Furthermore, various features are engineered to analyze the variance, complexity, and distribution of the manipulated data. The variance and complexity are created in data distribution when FDIs and theft cases are used to poison SM data, which is investigated through skewness and kurtosis analysis. Furthermore, to tackle the data imbalance issue, the proximity weighted synthetic oversampling (ProWsyn) technique is used. Moreover, a hybrid attentionLSTMInception is introduced, which is an integration of attention layers, LSTM, and inception blocks to tackle data dimensionality, misclassification, and high false positive rate issues. The proposed hybrid model outperforms the traditional theft detectors and achieves an accuracy of 0.95%, precision 0.97%, recall 0.94%, F1 score 0.96%, and area under-the-curve (AUC) score 0.98%.

In this paper, a defused decision boundary which renders misclassification issues due to the presence of cross-pairs is investigated. Cross-pairs retain cumulative attributes of both classes and misguide the classifier due to the defused data samples' nature. To tackle the problem of the defused data, a Tomek Links technique targets the cross-pair majority class and is removed, which results in an affine-segregated decision boundary. In order to cope with a Theft Case scenario, theft data is ascertained and synthesized randomly by using six theft data variants. Theft data variants are benign class appertaining data samples which are modified and manipulated to synthesize malicious samples. Furthermore, a K-means minority oversampling technique is used to tackle the class imbalance issue. In addition, to enhance the detection of the classifier, abstract features are engineered using a stochastic feature engineering mechanism. Moreover, to carry out affine training of the model, balanced data are inputted in order to mitigate class imbalance issues. An integrated hybrid model consisting of Bi-Directional Gated Recurrent Units and Bi-Directional Long-Term Short-Term Memory classifies the consumers, efficiently. Afterwards, robustness performance of the model is verified using an attack vector which is subjected to intervene in the model's efficiency and integrity. However, the proposed model performs efficiently on such unseen attack vectors. [ABSTRACT FROM AUTHOR]