Electricity Theft Research Articles

Boruta-XGBoost Electricity Theft Detection Based on Features of Electric Energy Parameters

Electricity theft detection is critical for the safe and effective development of the electric power system. The existing methods that are used to detect electricity theft rely on historical load data and are considered to have poor timeliness. Their detection results have limited reference to power supply enterprises’ investigation on electricity theft. Therefore, this paper proposes the Boruta-XGBoost power theft detection model based on multiple features of electric energy parameters. The model converts electricity theft detection problem into a multiclass classification problem. First, the features of various electric energy parameters that are collected by the electric energy metering device are used to construct the original dataset. Then, the Boruta algorithm is used to select features and reconstruct the dataset based on the selection results. Finally, the reconstructed dataset is used to train an XGBoost model that can detect the type of electricity theft based on the features of real-time electric energy parameters. In order to verify the effectiveness of the model, a comparative experiment is conducted in this paper. The reconstructed dataset is used to train the following algorithms: LightGBM, CART, SVM, and logistic regression models. The test results show that the Boruta-XGBoost model in this paper has the best effect on electricity theft detection.

Artificial intelligence for energy fraud detection: a review

Energy fraud in the distribution sector of electric utility includes electricity theft, meter tampering, or billing error. This fraud causing non-technical loss has led to an economic loss of the company. In order to detect and minimize fraud, different technologies have been used. From conventional methods to development in the field of artificial intelligence (AI), effective and reliable fraud detection methods have been proposed. This paper first provides an overview of different proposed methods for non-technical loss detection and evaluate the advantage and limitation of using those methods. Furthermore, several supervised and unsupervised machine learning methods for detecting electricity theft are discussed in summary along with their metrics and attributes used. Finally, these methods are classified based on the overall operation and the parameters used. This paper provides comparisons of several fraud detection methods using AI along with their weak and strong points and this information is very useful for the researchers who are working in the field of AI method for detecting fraud.

Data-Driven Detection of Electricity Theft Cyberattacks in PV Generation

Most of the existing research focuses on electricity theft cyberattacks in the consumption domain. On the contrary, a high penetration level of distributed generators (DGs) may result in increased electricity theft cyberattacks in the distributed generation domain, which is the focus of this article. In these attacks, malicious customers can hack into the smart meters monitoring their DG units, which are usually photovoltaic, and manipulate their readings to report higher injected energy to the grid and claim more profit under feed-in tariff programs. This article proposes a data-driven approach based on machine learning to detect such thefts. We adopt an anomaly detection approach where a theft detection unit (TDU) based on a regression tree model is designed to detect suspicious data. Historical records of solar irradiance, temperature, and smart meter readings are utilized in the training stage of the detector. The probability density function of the error between the actual readings from DG meters and the predicted generation by the regression model is utilized as a metric to detect suspicious data. Several theft scenarios are used to assess the performance of the TDU. Furthermore, a comparison study with other detectors is presented to demonstrate the superiority of the proposed TDU.

Non-technical Losses in Brazil: Overview, Challenges, and Directions for Identification and Mitigation

Non-technical losses directly affect the electricity distribution system's quality and create significant economic problems in developing countries. There has been an advance in Brazil's regulations to combat this kind of loss in the last 15 years. However, the electricity consumed and not billed is still high, impacting the electricity tariff and distributors' investment capacity and creating difficulties in developing public policies to mitigate the problem. Thus, this article seeks to present the panorama of non-technical losses in Brazil and propose legislative, regulatory, business, and academic directions. For this, 28 semi-structured interviews were carried out with specialists, resulting in identifying the main challenges for identifying and mitigating non-technical losses in Brazil and the factors that help overcome this problem. The results demonstrate that coordinated strategic actions among all stakeholders need to be developed to combat non-technical losses. The cultural change in acceptance of electricity theft needs to be one of the country's main focuses. The main contribution is to disseminate information to regulatory and legislative authorities, government, concessionaires, and researchers to develop practical actions for mitigating non-technical losses in Brazil.

Prevalence of electricity theft among households in Lagos State, Nigeria

Power outages and blackouts have continued to characterize household electricity supply despite the desire of Nigerians to have improved quality of electricity supply. Nigeria has an installed electric power capacity of 12,500MW but power sent out daily as at the end of June 2019 was 3,419MW. This is 200kWh per capita, which is a fraction of 4,229kWh per capita for South Africa. Worst still, Nigerians have only 59.3% access to electricity and those connected to the grid face extensive power interruptions. Attainment of stable and reliable electricity supply requires three basic dimensions: technicalities, organisational structures and reduction of Electricity Theft (ET) to the barest minimum. Previous studies have focussed more on the technical and organisational requirements than on issues bothering on ET and its resultant effects on stable electricity supply. Therefore, this study investigated the prevalence of ET among households in Lagos State, Nigeria. A self-constructed structured questionnaire focusing on demographic characteristics and prevalence of ET was purposively administered to 580 households (area of franchise under Ikeja Electric Plc. = 330, under Eko Electricity Distribution Company = 250), using the statistical sample size determination formula. Descriptive and inferential statistics was used to identify and analyse prevalence of ET among households. The extensive Electricity theft among households in Lagos State, Nigeria, was exacerbated by weak enforcement of anti-electricity theft laws with severe consequences on the entire electric power value chain. Strengthening institutions for enforcement and application of anti-electricity theft laws is recommended to mitigate the problem.

Two-Step Electricity Theft Detection Strategy Considering Economic Return Based on Convolutional Autoencoder and Improved Regression Algorithm

Electricity theft behaviors have caused great harm to the economic benefits of power companies and the secure operation of power systems, thus electricity theft detection is paid much attention in the actual power supply management. In this work, a two-step electricity theft detection strategy is proposed to identify electricity theft users and predict potentially stolen electricity (PSE) for maximizing economic return. In the first step, a neural network model called convolutional autoencoder (CAE) is proposed for electricity theft identification, and the convolutional layer is adopted in CAE to extract and identify the abnormalities of electricity theft users against the uniformity and periodicity of normal power consumption features. In the second step, the PSE of each identified electricity theft user is predicted by the improved regression algorithm named Tr-XGBoost, which combines the extreme gradient boosting (XGBoost) algorithm and transfer adaptive boosting (TrAdaBoost) training strategy. The propsoed Tr-XGBoost could learn the relationship between the extracted electricity features and the PSE of each electricity theft user, and then the predicted PSE can be used to determine the list of electricity theft users to be inspected for maximizing economic return. Case studies on both the IEEE 33-bus test system and a low-voltage distribution system of a province in China show that the proposed two-step electricity theft detection strategy can improve the accuracy of electricity theft identification, and obtain a larger economic return because of a more accurate result of PSE prediction than other state-of-the-art algorithms.

A Control-Chart-Based Detector for Small-Amount Electricity Theft (SET) Attack in Smart Grids

For achieving the goal of two-way communication and power flows, smart grids are integrated with much state-of-the-art hardware and software. However, these newly added components also introduce a lot of vulnerabilities into the power systems, which results in that malicious users can launch various cyber-physical attacks to steal electricity. Existing electricity theft detection techniques suffer from an implicit assumption that malicious users tamper with smart meter readings to values much less than their actual electricity consumptions. These are called Large-amount Electricity Theft (LET) attacks. Nevertheless, in the real world, some malicious users may be cautious enough to deliberately launch Small-amount Electricity Theft (SET) attacks where smart meter readings are manipulated to numbers slightly lower than actual values, mainly to escape detection. To address this limitation, we propose a detector able to deal with both LET and SET attacks effectively. This detector applies a cumulative sum (CUSUM) control chart and a Shewhart control chart together to analyze users’ reported readings and measurements of a central observer meter. It consists of an electricity theft detection phase which aims to detect the existence of LET/SET attacks timely and a malicious user identification phase which aims to identify malicious users exactly. Extensive experiments are conducted to evaluate the proposed detector, and the results show that it has good performance in terms of several metrics.

Power Theft Detection using GSM

Electrical energy is very important for everyday life and spine for the industry. Electricity power is indiscipline to our daily life with increasing need of electricity, the energy robbery is also growing, electricity theft is a hassle that keeps to plague electricity region across the country, the goal of this paper is to design one of these gadget with a purpose to try and reduce the illegal use of power and also lessen the probabilities of theft. In this research we have focused on the most common practice of stealing power which is tapping or tampering the meter. The system has been designed to detect the theft and also inform to the nearest substation and to the consumer. This model try to achieve theft control.

Electricity theft detection using big data and genetic algorithm in electric power systems

Non-technical losses (NTLs) are one of the major causes of revenue losses for electric utilities. In the literature, various machine learning (ML)/deep learning (DL) approaches are employed to detect NTLs. The existing studies are mostly concerned with tuning the hyperparameters of ML/DL methods for efficient detection of NTL, i.e., electricity theft detection. Some of them focus on the selection of prominent features from data to improve the performance of electricity theft detection. However, the curse of dimensionality affects the generalization ability of ML/DL classifiers and leads to computational, storage, and overfitting problems. Therefore, to deal with the above-mentioned issues, this study proposes a system based on metaheuristic techniques (artificial bee colony and genetic algorithm) and denoising autoencoder for electricity theft detection using big data in electric power systems. The former (metaheuristics) are used to select prominent features, while the latter is utilized to extract high variance features from electricity consumption data. Firstly, 11 new features are synthesized using statistical and electrical parameters from the user’s consumption history. Then, the synthesized features are used as input to metaheuristic techniques to find a subset of optimal features. Finally, the optimal features are fed as input to the denoising autoencoder to extract features with high variance. The ability of both metaheuristic and autoencoder techniques to select and extract features is measured using a support vector machine. The proposed system reduces the overfitting, storage, and computational overhead of ML classifiers. Moreover, we perform several experiments to verify the effectiveness of our proposed system and results reveal that the proposed system has better performance than its counterparts.

Synthetic Theft Attacks and Long Short Term Memory-Based Preprocessing for Electricity Theft Detection Using Gated Recurrent Unit

Electricity theft is one of the challenging problems in smart grids. The power utilities around the globe face huge economic loss due to ET. The traditional electricity theft detection (ETD) models confront several challenges, such as highly imbalance distribution of electricity consumption data, curse of dimensionality and inevitable effects of non-malicious factors. To cope with the aforementioned concerns, this paper presents a novel ETD strategy for smart grids based on theft attacks, long short-term memory (LSTM) and gated recurrent unit (GRU) called TLGRU. It includes three subunits: (1) synthetic theft attacks based data balancing, (2) LSTM based feature extraction, and (3) GRU based theft classification. GRU is used for drift identification. It stores and extracts the long-term dependency in the power consumption data. It is beneficial for drift identification. In this way, a minimum false positive rate (FPR) is obtained. Moreover, dropout regularization and Adam optimizer are added in GRU for tackling overfitting and trapping model in the local minima, respectively. The proposed TLGRU model uses the realistic EC profiles of the Chinese power utility state grid corporation of China for analysis and to solve the ETD problem. From the simulation results, it is exhibited that 1% FPR, 97.96% precision, 91.56% accuracy, and 91.68% area under curve for ETD are obtained by the proposed model. The proposed model outperforms the existing models in terms of ETD.

Timing shift-based bi-residual network model for the detection of electricity stealing

With the increasing number of electricity stealing users, the interests of countries are jeopardized and it brings economic burden to the government. However, due to the small-scale stealing and its random time coherence, it is difficult to find electricity stealing users. To solve this issue, we first generate the hybrid dataset composed of real electricity data and specific electricity stealing data. Then, we put forward the timing shift-based bi-residual network (TS-BiResNet) model. It learns the features of electricity consumption data on two aspects, i.e., shallow features and deep features, and meanwhile takes time factor into consideration. The simulation results show that TS-BiResNet model can detect electricity stealing behaviors that are small scaled and randomly coherent with time. Besides, its detection accuracy is superior to the benchmark schemes, i.e., long short-term memory (LSTM), gated recurrent unit (GRU), combined convolutional neural network and LSTM (CNN-LSTM) and Bi-ResNet.

Electric Power System Monitoring and Theft Detection using Power Line Communication

Electric power theft is a serious concern in the world irrespective of being major revenue losses and developing a nation. More than one-third part of the electricity generated power is lost due to electric theft, power loss, and inefficiencies in the distribution system. Interdicted or illegal utilization of electricity has not only affected economically but also obstructs the design and modeling phases of the power system. Due to electric theft, providing wrong data input values for power system analysis and difficult to load forecasting. In this paper, an inventive Simulink model is designed to detect and monitoring of electric power theft in power system distribution networks through Power Line Communication (PLC). Electric power theft was detected with variance amendment in the amplitude of carrier signal with a narrow band. PLC technique is utilized for data communication over the power line. A narrow band power line carrier signal which has high frequency transferred in power line alongside with power frequency signal. The deviation in the amplitude of the transmitted carrier signal is monitored at the regular time- intervals and the stealing of electricity can be distinguished by the computing of distinction change within the amplitude of the carrier signal. In a normal case, the signal present fixes pattern and waveform, but in the case of power theft, the signal shows some variation and disturbance in a within waveform pattern. A pattern recognition and monitoring approach is used for direct power theft in the PLC model. The Simulink model is performed on MATLAB software to analyze the performance and efficient results that satisfy the proposed Simulink model.

Energy Theft Detection in Smart Grids: Taxonomy, Comparative Analysis, Challenges, and Future Research Directions

Electricity theft is one of the major issues in developing countries which is affecting their economy badly. Especially with the introduction of emerging technologies, this issue became more complicated. Though many new energy theft detection (ETD) techniques have been proposed by utilising different data mining (DM) techniques, state & network (S&N) based techniques, and game theory (GT) techniques. Here, a detailed survey is presented where many state-of-the-art ETD techniques are studied and analysed for their strengths and limitations. Three levels of taxonomy are presented to classify state-of-the-art ETD techniques. Different types and ways of energy theft and their consequences are studied and summarised and different parameters to benchmark the performance of proposed techniques are extracted from literature. The challenges of different ETD techniques and their mitigation are suggested for future work. It is observed that the literature on ETD lacks knowledge management techniques that can be more effective, not only for ETD but also for theft tracking. This can help in the prevention of energy theft, in the future, as well as for ETD.

Electrical Palestine: Capital and Technology from Empire to Nation by Fredrik Meiton

Reviewed by: Electrical Palestine: Capital and Technology from Empire to Nation by Fredrik Meiton Xiaoyue Li (bio) Electrical Palestine: Capital and Technology from Empire to Nation By Fredrik Meiton. Oakland: University of California Press, 2019. Pp. 312. Whereas Thomas Hughes's seminal Networks of Power (1983) sets the tone for studying electricity in Western societies, Electrical Palestine offers new insight into this infrastructure in a non-Western and colonial context. Fredrik Meiton excellently demonstrates that the physical materials for electrification both embodied and enacted modern political power. Meiton thus pushes STS scholarship to rethink the critical role of infrastructure in ethnic conflict and nation-building. Although electricity networks were not the only infrastructure under-girding Israel, Electrical Palestine eloquently convinces readers that electricity was the foundational technology in two major ways. Meiton persuasively argues that electricity contributed significantly to the Jewish sector's rapid industrialization and exponential economic growth in the interwar period, while the Arab sector, unlit due to deliberate electric grid arrangements that bypassed it, remained unindustrialized and underdeveloped (p. 5). In addition, electrification functioned as an integral substrate for other heterogeneous infrastructure systems, such as electrified railways and Jewish settlements (p. 62, 71). Therefore, electrification was the infrastructure of all infrastructures and substrate of the modern Jewish economy and political power. In what is his major contribution to technology studies—also constituting his central arguments—Meiton positions his delicate and powerful explanation of the electricity infrastructure as a trinity of material technology, capital, and politics. He vigorously highlights Zionist engineer Pinhas Rutenberg's state-building agenda embedded within the apolitical and developmentalist languages of his technical proposals, strategies that Meiton [End Page 563] calls "politics of the non-politics" (p. 89, chs. 1–4). By skillfully using British and Zionist archives, as well as electricity company records, Electrical Palestine highlights how the material infrastructure of power plants and electric grids concretized and inscribed the Zionist movement's ideal nation-building ambitions. It thus reveals from a material perspective the founding myth of modern Israel. In the classic STS literature by Bruno Latour, Susan Leigh Star, and James Griesemer, "boundary work" seeks mutually recognizable objects, standards, or rules, laying the foundation for scientific collaboration (Star and Griesemer, Social Studies of Science, 1989; Latour, Reassembling the Social, 2005). Meiton showcases that "boundary work," in a colonial context, can be at once inclusive and exclusive. Rutenberg's apolitical and developmentalist outlook enabled him to forge an alliance with British officials, European capital, and Jewish settlers. In contrast with this inclusiveness, the next set of chapters demonstrate that Rutenberg excluded the Arab population in Palestine from enjoying equal access to electricity, resulting in widespread disillusionment among Arab communities and the subsequent mass revolt between 1936 and 1939 (chs. 5–7). Through the lens of Rutenberg's boundary work, the author diagnoses a root cause of the Arab-Israeli conflict from an infrastructural perspective. Unlike an earlier monograph on this topic—Ronen Shamir's Current Flow (2013)—Electrical Palestine includes "Palestinian perspectives on electrification" (p. 10). Of note, the asymmetrical structure of political power is also fully reflected in the historical sources. Hebrew, English, and other European-language materials produced in Britain and Israel are used far more frequently in Shamir's work. In this respect, Meiton's meticulously researched project impressively excavates the Arabic municipal archives in Nablus, Tel Aviv-Jaffa, and Haifa, revealing new perspectives of Palestinian elites that Shamir does not access. These uncovered Arabic sources shed light on the Palestinian elites' aborted attempts to restructure Zionist infrastructure. The municipalities of Jaffa, for instance, never opposed Rutenberg's electrification plan, and even sought to invest in and operate local electric grids (p. 97). Future research could adopt a non-elite perspective, investigating if historians can view illicit acts such as sabotage and electricity theft as "political leverage" of Palestinian nationalist leaders or as spontaneous, grassroots activities countering unfavorable conditions (p. 82, 93). In the Jewish and Arab communities' increasingly heroic nationalist narratives, how can histories account for the everyday experiences of non-elites, the segment who suffer directly from ever-rigid ethno-religious segregation and opposition? Anthropologist Nikhil Anand argues that the "banality of infrastructure" often makes people ignore...

Smart Energy Meter

India uses electromechanical electricity meters, but considers the drawbacks of electricity theft, meter reading errors, billing, and consumers hesitating to pay utility bills on time. Therefore, such systems are being replaced by more sophisticated and accurate digital and electronic gauges. This paper proposes a new methodology for implementing a control-based global system for mobile communication networks (GSMs) to integrate prepaid metering system setup and remote load control. This provides a secure smart card solution for new types of prepaid power systems. It aims to reduce the number of utility bill obstacles using smart card technology. The LCD display is used to show the amount of energy consumed. Users can replenish the counter as needed by sending an SMS to the server. Users must make the first replenishment to address the issue of unpaid invoices and human error in invoices. This ultimately guarantees a legitimate return.

Customer Attitudes Towards the Role of Socio-Economic Factors in Electricity Theft

Electricity theft has become a matter of trouble for both customers and electricity distribution companies. Due to electricity theft, distribution companies are facing lots of T&D losses every year. Despite of several technical measures adopted, there is no significant reduction in losses due to electricity theft. This fact diverts the attention towards non-technical measures which include formulation and enforcement of stringent rules and regulations. As the policies need to be enforced on electricity customers, therefore, policies should be designed in accordance with the customers’ attitude towards electricity theft. Therefore, this work has analyzed their attitude towards role of certain socio-economic factors which strongly impact the practice of electricity theft. This study has surveyed the electricity customers of two distribution companies, UHBVN and DHBVN in State Haryana. The findings of this work may help the electricity distribution companies to chalk out better and more effective plans to put check upon the practice of electricity theft in the society.

Online electricity theft detection framework for large-scale smart grid data

Smart grid gives more control and information to the utility companies. However, it can be leveraged for data manipulation, which can lead to new techniques in electricity theft. This paper presents an electricity theft detection framework, designed for handling real-time large-scale smart grid data to address these new emerging threats. It uses a hybrid approach, combining the information inferred by analyzing the reported data from distribution transformer meters with machine learning algorithms to discover fraudulent activity. We added an additional form of attack to the six previously known patterns and generated malicious variants of consumption data to solve the problem of imbalanced dataset classes, resulting in more accurate classifiers. The framework also allows for a trade-off between the detection rate and triggered false alarms by using a sliding window in the decision-making process. In the end, the proposed framework is evaluated using well-known clustering and classification methods in a practical scenario, resulting in outcomes superior or equal to the previously achieved scores while having the advantages of online and distributed processing.

A Stacked Machine and Deep Learning-Based Approach for Analysing Electricity Theft in Smart Grids

The role of electricity theft detection (ETD) is critical to maintain cost-efficiency in smart grids. However, existing methods for theft detection can struggle to handle large electricity consumption datasets because of missing values, data variance and nonlinear data relationship problems, and there is a lack of integrated infrastructure for coordinating electricity load data analysis procedures. To help address these problems, a simple yet effective ETD model is developed. Three modules are combined into the proposed model. The first module deploys a combination of data imputation, outlier handling, normalization and class balancing algorithms, to enhance the time series characteristics and generate better quality data for improved training and learning by the classifiers. Three different machine learning (ML) methods, which are uncorrelated and skillful on the problem in different ways, are employed as the base learning model. Finally, a recently developed deep learning approach, namely a temporal convolutional network (TCN), is used to ensemble the outputs of the ML algorithms for improved classification accuracy. Experimental results confirm that the proposed framework yields a highly-accurate, robust classification performance, in comparison to other well-established machine and deep learning models and thus can be a practical tool for electricity theft detection in industrial applications.

Research on monitoring technology of power stealing behavior in bitcoin mining based on analyzing electric energy data

As we all know, the behavior of stealing electric energy governance is always the difficulty and key point in the management of electric power enterprises. In recent years, as bitcoin’s value continued to climb, the theft of electricity by bitcoin mining user began to appear. In order to solve the power theft problem of bitcoin mining users, we conducted an in-depth study on the power consumption behavior of such users based on the power data analysis technology. This paper analyzes the power consumption characteristics of bitcoin mining users and uses electric data acquire system to monitor power consumption behavior. The paper makes comparative analysis on the massive data such as voltage and power of the electric energy acquisition system, analyzes and calculates the Pearson correlation coefficient between the electricity consumption of each customer and the line loss statistics of the power station by using Pearson correlation algorithm combined with the power loss of the power station, and analyzes the suspected users of stealing electric energy by taking an actual example. Through our research, we found a total of 16 bitcoin miners suspected of stealing electricity. After on-site investigation and evidence collection, we found that 10 of the users did have abnormal power consumption, and the accuracy rate reached 62.50%. Therefore, the economic benefits of this research are very significant.

Research on comprehensive diagnosis model of anti-stealing electricity based on big data technology

For a long time, power supply enterprises have been plagued by the problem of electricity theft and default. Although power supply enterprises have strengthened anti-theft measures from various aspects, the huge benefits brought by electricity theft and default have driven the development trend of electricity theft methods to be more complicated and concealed, which has brought great challenges to the anti-theft work. In order to quickly and accurately locate the suspected users of ”defaulting on electricity consumption and stealing electricity”, based on the massive data of marketing business application system and electricity consumption information collection system, this paper analyzes and studies the existing common means of stealing electricity, and establishes an anti-stealing diagnostic analysis model by combining the correlation analysis algorithm, extracts the abnormal data related to stealing electricity and its prevention and investigation, and accurately locks the suspected users. The aim is to improve the efficiency and accuracy of preventing and investigating electricity theft, so as to effectively curb the occurrence of electricity theft, reduce the line loss rate, ensure the safety of the power grid and improve the efficiency of power supply enterprises.