Theft Detection Research Articles

Predictive Data Analytics for Electricity Fraud Detection Using Tuned CNN Ensembler in Smart Grid

In the smart grid (SG), user consumption data are increasing very rapidly. Some users consume electricity legally, while others steal it. Electricity theft causes significant damage to power grids, affects power supply efficiency, and reduces utility revenues. This study helps utilities reduce the problems of electricity theft, inefficient electricity monitoring, and abnormal electricity consumption in smart grids. To this end, an electricity theft dataset from the state grid corporation of China (SGCC) is employed and this study develops a novel model, a mixture of convolutional neural network and gated recurrent unit (CNN-GRU), for automatic power theft detection. Moreover, the hyperparameters of the proposed model are tuned using a meta-heuristic method, the cuckoo search (CS) algorithm. The class imbalance problem is solved using the synthetic minority oversampling technique (SMOTE). The clean data are trained and then tested with the proposed classification. Extensive simulations are performed based on real energy consumption data. The simulated results show that the proposed theft detection model (CNN-GRU-CS) solved the theft classification problem better than other approaches in terms of effectiveness and accuracy by 10% on average. The calculated accuracy of the proposed method is 92% and the precision is 94%.

Vehicle theft detection by generative adversarial networks on driving behavior

Human driving behavior can be a unique fingerprint to identify individual drivers and can be used for vehicle theft detection. Prior research often uses supervised learning to classify drivers’ behaviors. However, that method is not suitable for vehicle theft detection because it is not possible to derive a training dataset which comprehends all possible thieves. A few studies have instead leveraged unsupervised learning, such as k-means, but such approaches cannot achieve acceptable accuracy or provide a method of tolerating the false outcomes from classifying individual data points. Moreover, the influence of environment and road conditions on the driver classification was not included further limiting its usability. In this work, we propose a redesigned Generative Adversarial Network (GAN) model, Convolutional Long short-term GAN (CLGAN), which comprises long short-term memory (LSTM) and a convolutional neural network (CNN). This model ensures the ability of feature extraction from the convolutional layer and feature preservation from the LSTM layer, while simultaneously minimizing overfitting. It is instructive to analyze and benchmark CLGAN with the various GAN models, such as DCGAN, RNN-GAN, and AAE. Applying a public dataset which was generated by an electronic control unit (ECU) and collected through in-vehicle Controller Area Network (CAN) bus, our model achieves high accuracy of 98.5%, and is more robust against various driving conditions on multiple types of roads. In addition, we leverage threshold random walk to ensure the reliability of detection as well as adopting Principal Component Analysis (PCA) on feature pre-processing to improve the accuracy by approximately 20%. This work sheds light on a feasible and practical way of implementing vehicle theft detection.

Electricity-theft detection for smart grid security using smart meter data: A deep-CNN based approach

Electricity theft has a considerable negative effect on energy suppliers and power infrastructure, leading to non-technical losses and business losses. Power quality deteriorates and overall profitability falls as a result of energy theft. By fusing information and energy flow, smart grids may assist solve the issue of power theft. The examination of smart grid data aids in the detection of power theft. However, the earlier techniques were not very good in detecting energy theft. In this work, we suggested an electricity theft detection approach using smart meter consumption data in order to handle the aforementioned issues and assist and assess energy supply businesses to lower the obstacles of limited energy, unexpected power usage, and bad power management. In specifically, the Deep CNN model effectively completes two tasks: it differentiates between energy that is not periodic and that is, while keeping the general features of data on power consumption. The trial’s results show that the deep CNN model outperforms prior ones and has the best level of accuracy for detecting energy theft.

Effectiveness of learning algorithms with attack and defense mechanisms for power systems

Machine learning and artificial intelligence have created a myriad of opportunities for power systems. For example, learning techniques have been widely used for forecasting, data-driven frequency and voltage control, clustering of demand profiles, state estimation, theft detection, etc. Despite their satisfactory performances, these methods can face challenges associated with adversarial attacks that may result in system failure. In this paper, we systematically compare the effects of a set of attacks using different learning algorithms for a set of power systems problems (classification, forecasting, and control). We first show that most of the machine learning models proposed for power system applications are vulnerable to adversarial attacks. Then we adopt a series of common defense algorithms to improve performance under the different attacks. We identify GAN as the most effective defense algorithm across all power system applications tested, among all attacks and attack levels. It is of interest to notice that for the three power system problems different application datasets can be much more vulnerable. As the first systematic study of attack and defense mechanisms for a variety of power systems applications we hope to motivate the power systems and machine learning communities to continue studying how to increase the robustness of learning models against attacks. • We study the effects of attacks using different learning algorithms for power systems. • We test which defense algorithms are effective based on the attack and case study. • GAN is the most effective defense algorithm for all power system applications tested. • The power systems applications we study are classification, forecasting, and control. • Attack vulnerability varies widely based on the dataset studied in the control case.

Electricity Theft Detection in AMI With Low False Positive Rate Based on Deep Learning and Evolutionary Algorithm

Due to the diversity of power consumption patterns, the false positive rate (FPR) of data-driven electricity theft detection (ETD) methods is too high to meet practical needs, which severely restricts the engineering application of data-based methods. To reduce FPR of ETD methods based on advanced metering infrastructure (AMI), a deep neural network with low FPR (LFPR-DNN) is proposed in this paper. First, a deep model is constructed based on one-dimensional convolution and residual network, which can automatically extract features from consumption data. Then, a two-stage training scheme is used to train the network. In the first stage, the conventional gradient descent algorithm is used to update the network weights. To minimize the impact of data imbalance on detection performance, focal loss is used. Besides, grid search is used to optimize the hyper-parameters of the model. In the second stage, with FPR as the optimization objective, the particle swarm optimization (PSO) algorithm is used to train the network. Finally, the proposed LFPR-DNN is verified by using the open Irish data set. Compared to other state-of-the-art classifiers, LFPR-DNN has the lowest FPR with 0.29% and the highest AUC with 99.42%. The FPR is reduced by an order of magnitude, which verifies the effectiveness of the proposed method.

Electricity Theft Detection in Smart Grids Using a Hybrid BiGRU-BiLSTM Model with Feature Engineering-Based Preprocessing.

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.

A novel approach to detect electricity theft based on conv-attentional Transformer Neural Network

With the establishment of advanced metering infrastructure (AMI), more and more deep learning (DL) methods are being used for electricity theft detection. However, there are still problems such as the construction of a DL model that better fits the theft detection task, sample imbalance in the data set and overfitting of the model which limit the potential of DL models. Therefore, a novel end-to-end solution based on DL to solve these problems for electricity theft detection is proposed in this paper. First, we construct a model based on Transformer Neural Network (TNN), which extracts global features of consumption data by calculating the self-attention between each segment obtained by dividing the whole load sequence, and calculates the relative relationship between features for customer classification. Then, we refine the model to further improve its performance. Conv-attentional module is used to embed the input data and capture the local features in each segment. And we minimize the effect of sample imbalance by choosing a suitable loss function, and address the problem of model overfitting by adding normalization layers, dropout regularization and L2 regularization. In addition, grid search is used to determine the optimal values of the model hyper-parameters. Finally, the performance of the proposed model is verified by experiments using the Irish data set. The results show that our method is able to extract features more efficiently and thus has a higher true positive rate (TPR) with a lower false positive rate (FPR) than other state-of-the-art detectors, and it has strong robustness.

An Efficient Method Combined Data-Driven for Detecting Electricity Theft with Stacking Structure Based on Grey Relation Analysis

Nowadays, electricity theft has been a major problem worldwide. Although many single-classification algorithms or an ensemble of single learners (i.e., homogeneous ensemble learning) have proven able to automatically identify suspicious customers in recent years, after the accuracy of these methods reaches a certain level, it still cannot be improved even if it continues to be optimized. To break through this bottleneck, a heterogeneous ensemble learning method with stacking integrated structure of different strong individual learners for detection of electricity theft is presented in this paper. Firstly, we use the grey relation analysis (GRA) method to select the heterogeneous strong classifier combination of LG + LSTM + KNN as the base model layer of stacking structure based on the principle of the highest comprehensive evaluation index value. Secondly, the support vector machine (SVM) model with relatively good results of the stacking overall structure experiment is selected as the model of the meta-model layer. In this way, a heterogeneous integrated learning model for electricity theft detection of the stacking structure is constructed. Finally, the experiments of this model are conducted on electricity consumption data from State Grid Corporation of China, and the results show that the detection performance of the proposed method is better than that of the existing state-of-the-art detection method (where the area under receiver operating characteristic curve (AUC) value is 0.98675).

The detection of non-technical losses and electricity theft by smart meter data and Artificial Intelligence in the context of electric distribution utilities: A comprehensive review

The detection of non-technical losses and electricity theft by smart meter data and Artificial Intelligence in the context of electric distribution utilities: A comprehensive review

Synthetic data generation for machine learning model training for energy theft scenarios using cosimulation

AbstractTechnical and non‐technical losses in distribution circuits result in significant economic costs to power utilities. One type of non‐technical loss is energy theft by various means including illegal tapping of feeders, bypassing the meter, and billing fraud. These losses are usually hard to detect, and can remain undetected for long periods of time. Machine learning models have been proven effective in detecting these conditions, but rely on the availability of large, good‐quality training data sets. The problem is exacerbated by the imbalanced nature of data related to these conditions—energy theft, though costly, is very rare. The available data sets generally have very few samples of theft with most of the data pertaining to normal operation. Such data sets are generally not suitable to train machine learning models. In this paper, an overview of energy theft detection techniques, the challenges with their data needs, and the limitations of current techniques to bridge such data limitations is presented. A co‐simulation framework is proposed to generate reliable training data for machine learning algorithms for theft detection. An example scenario is presented and a machine learning model is built to detect certain kinds of energy theft.

INTELLIGENT VIDEO SURVEILLANCE USING DEEP LEARNING

Video surveillance, also known as CCTV (closed-circuit television), is a rapidly growing industry that has been around for more than 30 years and has seen its fair share of technological advancements. In today's world, video surveillance has become an essential component for ensuring public safety. Security can be defined in a variety of ways depending on the context, such as theft detection, violence detection, explosion risk, and so on. The term "security" in crowded public places refers to almost any type of abnormal event.Intelligent video surveillance delivers cutting-edge smart security by recording unexpected activities in homes, offices, and public locations based on the preferences of the user. In the event of an abnormal incident, the video surveillance system will actively respond to detect actions in advance through real-time monitoring and promptly communicate data. The primary focus is on the use of deep learning techniques to provide tracking of a moving target, high-definition picture quality, and night vision technology triggered by motion sensors, which means the system isn't running when nothing is happening at your location, automatic audio and visual detection, video recording initiation, and detection of suspicious activities that can trigger and alert the systems in all climate conditions.Deep learning technology will be used in the data processing model design to visualise data for abnormal activities, and this design also proposes an intelligent surveillance system to quickly and effectively detect activities by sending a video image and an alert message to the web via real-time processing. Recent improvements in computer vision, particularly deep learning approaches, have opened up new possibilities for these systems, enhancing their capabilities and launching new research areas in this field.

Electricity theft detection in unbalanced sample distribution: a novel approach including a mechanism of sample augmentation

Electricity theft detection in unbalanced sample distribution: a novel approach including a mechanism of sample augmentation

FedDP: A Privacy-Protecting Theft Detection Scheme in Smart Grids Using Federated Learning

In smart grids (SGs), the systematic utilization of consumer energy data while maintaining its privacy is of paramount importance. This research addresses this problem by energy theft detection while preserving the privacy of client data. In particular, this research identifies centralized models as more accurate in predicting energy theft in SGs but with no or significantly less data protection. Current research proposes a novel federated learning (FL) framework, namely FedDP, to tackle this issue. The proposed framework enables various clients to benefit from on-device prediction with very little communication overhead and to learn from the experience of other clients with the help of a central server (CS). Furthermore, for the accurate identification of energy theft, the use of a novel federated voting classifier (FVC) is proposed. FVC uses the majority voting-based consensus of traditional machine learning (ML) classifiers namely, random forests (RF), k-nearest neighbors (KNN), and bagging classifiers (BG). To the best of our knowledge, conventional ML classifiers have never been used in a federated manner for energy theft detection in SGs. Finally, substantial experiments are performed on the real-world energy consumption dataset. Results illustrate that the proposed model can accurately and efficiently detect energy theft in SGs while guaranteeing the security of client data.

Electricity Theft Detection Based on ReliefF Feature Selection Algorithm and BP Neural Network

As China’s distributed energy is still in the development stage, energy transmission loss will inevitably occur in the transmission process from the source end to the load end. To reduce transmission energy loss, we should also beware of electricity theft. The principle of common electricity theft methods is analyzed to improve the accuracy of established electricity theft characteristics and electricity theft detection. The ReliefF multivariate characteristics selection algorithm optimizes the electricity theft characteristics. The back propagation (BP) neural network-based electricity theft detection model is built, and the optimized characteristics are selected as the model’s input. The experiment results show that the detection model has better electricity theft identification accuracy using the optimized characteristics for electricity theft detection.

On the effect of sampling frequency on the electricity theft detection performance

Electricity theft is a common problem in many countries and affects the revenue of the electricity industry significantly. Recently, machine and deep learning techniques are being used widely to detect thieves by analysing the consumption patterns. While the prediction accuracy of these methods depends on the number and quality of the existing samples used for training models, the majority of previous research work focussed on data with high sampling frequencies, for example, data from smart grids. However, based on technological and operational limitations, the rate of metre reading is too low in many countries, which can affect detection performance. To investigate the effect of sampling frequency on the performance of detection methods, we designed a processing framework to evaluate different classification algorithms on versions of a challenging dataset obtained by down-sampling the original data at various rates. We used different features from time, frequency and time-frequency domains and their combinations in our investigations. Experimental results show that the performance of the models decreases with a small slope up to the sampling frequency of one data per week. The performance degradation rate is significant for data with lower sampling frequencies. We also proposed a bagging network that could improve the overall detection performance at different sampling frequencies.

Electricity theft Detection with Borderline-SMOTE and WDCBL in the Smart Grid

The non-technical loss caused by electricity theft on the user side not only increases the operationcost of the smart grid but also causes some harm to the electricity system. At present, the existingelectricity theft detection model ignores the time-series correlation of user power consumption data,and the distribution of positive and negative samples in the relevant data sets is uneven. Aiming atthe existing problems, we propose an electricity theft detection model based on Borderline-SMOTEand WDCBL(wide and deep CBL) networks. The WDCBL model consists of wide componentsand deep CBL components. The wide part uses a fully connected layer to extract one-dimensionalfeatures in user electricity consumption data. The model introduces the hybrid network model ofa one-dimensional convolutional neural network(CNN) and bidirectional long-term and short-termmemory network(BiLSTM) into the deep part, which can learn both spatial and temporal features inuser electricity consumption data. Finally, we conducted a comparative experiment on the user electricityconsumption data published by SGCC. The results show that our model is superior to othersin the comprehensive performance.

Pattern-based and context-aware electricity theft detection in smart grid

The smart grid offers numerous potential benefits for energy management by two-way information transmission. However, the incorporation of smart infrastructure such as smart meters into the grid systems made it vulnerable to various communication attacks. The electricity consumption data coming from the smart meters can be acquired and analyzed to detect malicious behavior, tampering, and data manipulation. In this paper, a pattern-based and context-aware approach for electricity theft detection (PCETD) is proposed to mitigate the challenges of theft-based Non-Technical Losses (NTLs). The proposed approach considers the relevant calendar context and features of daily electricity demand for a given day to compute the probability of customers being malicious. In this process, a combination of dynamic time warping (DTW) and k-nearest neighbors (k-NN) is proposed, where DTW is utilized to capture the relationship between two consumption patterns correctly, and k-NN is employed to rank the anomalousness of the given day. This research introduces several forms of theft attacks and assesses the effectiveness of the proposed approach. The results exhibited the overall F1-score for the proposed approach to be 94%, the True-Positive Rate (TPR) as 93%, and the False-Positive Rate (FPR) as 1.1%, which substantiates the efficiency of the model in detecting electricity theft. These findings further advocate that the approach outperforms the prior contributions in terms of high detection rate and low false-positive rate. Electric utilities can be provided with anomaly scores and plan on-site inspections to catch fraudulent customers.

A Supermarket Anti-Theft Scanner : digiSCAN

Supermarket shopping is an essential part of the livelihood of most people around the world. Consumers can acquire items essential for their daily activities. However, in an ever-evolving world with an increasing population and increasing crime rates, supermarket theft is becoming a prevalent problem with supermarket owners spending large sums of money on hiring security often with little effect. Organized Retail Crime (ORC) costs the retail industry approximately $30 billion each year, with 71.3% of retailers reporting an increase in ORC year-over-year. With the current global economic conditions, high labor costs are longer feasible. Consumers also face the issue of paying for items they did not select. Advanced camera systems, for some, may be an escape however, this approach is not feasible for all aspects of shopping and in underdeveloped countries that have technical constraints. The advent of digitization has helped improve the livelihood of consumers in Ghana. Currently, many large-scale retailers are oblivious to some of these advancements. The oblivion of the management of such retail services results in the loss of products, customer dissatisfaction, and the mismanagement of untracked products by employees. To reduce theft and the mismanagement of products by employees, a smart antitheft system should be deployed in supermarkets; at the till and before the exit of supermarkets to ensure all products leaving the store are paid for and accounted for. The system consists of a deactivation and theft detection system. The product is deactivated by the store attendant at the till when the customer pays for the product. However, if a customer crosses the initial warning zone without paying, a warning sound is triggered and after the customer crosses the final warning zone, the alarm is triggered indicating an attempted theft by the customer. A log of products is also kept ensuring employees are not stealing products. This paper presents a smart way of detecting theft during supermarket shopping using Radio Frequency Identification (RFID) readers and tags, a microcontroller-based control system, a database server, and an Integromat.

A Supermarket Anti-Theft RFID Scanner : digiSCAN

Supermarket shopping is an essential part of the livelihood of most people around the world. Consumers can acquire items essential for their daily activities. However, in an ever-evolving world with an increasing population and increasing crime rates, supermarket theft is becoming a prevalent problem with supermarket owners spending large sums of money on hiring security often with little effect. Organized Retail Crime (ORC) costs the retail industry approximately $30 billion each year, with 71.3% of retailers reporting an increase in ORC year-over-year. With the current global economic conditions, high labor costs are longer feasible. Consumers also face the issue of paying for items they did not select. Advanced camera systems, for some, may be an escape however, this approach is not feasible for all aspects of shopping and in underdeveloped countries that have technical constraints. The advent of digitization has helped improve the livelihood of consumers in Ghana. Currently, many large-scale retailers are oblivious to some of these advancements. The oblivion of the management of such retail services results in the loss of products, customer dissatisfaction and the mismanagement of untracked products by employees. To reduce theft and the mismanagement of products by employees, a smart antitheft system should be deployed in supermarkets; at the till and before the exit of supermarkets to ensure all products leaving the store are paid for and accounted for. The system consists of a deactivation and theft detection system. The product is deactivated by the store attendant at the till when the customer pays for the product. However, if a customer crosses the initial warning zone without paying, a warning sound is triggered and after the customer crosses the final warning zone, the alarm is triggered indicating an attempted theft by the customer. A log of products is also kept ensuring employees are not stealing products. This paper presents a smart way of detecting theft during supermarket shopping using Radio Frequency Identification (RFID) readers and tags, microcontroller-based control system, a database server and an Integromat

Edge Computing Based Electricity-Theft Detection of Low-Voltage Users

Electricity theft of low voltage (LV) users could result not only in the escalation of power loss but also in dangerous electric shock. Since LV users are served by distribution transformers, electricity theft of an LV user will cause line loss escalation of the associated distribution serving zone (DTSZ). Therefore, it seems promising to identify anomaly users of electricity theft with a Granger causality test to find out the user causing an escalation of line loss in DTSZ with time series of users’ usage and line loss. However, meters of LV users in severe environments occasionally suffer from communication failure to upload metering data to the head end of advanced metering infrastructure (AMI), which could distort the daily electricity usage of the associate user. Consequently, it could cause false alarms unavoidably once we detect electricity theft with these distorted data. Since the distribution transformer unit (DTU) collects metering data of LV users within associate DTSZ without distortion, an edge computing–based electricity theft detection approach is proposed in this article. The correlation between line loss of a DTSZ and electricity usage of anomaly users of electricity theft is first analyzed. Thereafter, the Granger causality test is used to identify anomaly users with authentic usage data with edge computing in DTU. Finally, the abnormal data and the data repaired by different missing data filling algorithms are used on the main station to detect electricity theft. Numerical simulation suggests that although missing data completion could recover information in missing data partially, it could result in notable false positive alarms in electricity theft, while the proposed method based on edge computing can completely eliminate the data distortion caused by communication failure.