Non-technical Losses Research Articles

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.

Technical loss estimation approach in power distribution systems using load model in frequency domain

Electricity losses have been a focus of attention for Distribution System Operators (DSOs) and regulatory bodies. To define non-technical loss reduction policies is necessary to determine their amount. The strategy adopted is to calculate the technical losses to obtain the non-technical losses through the total losses difference. This paper presents an approach to estimate electric technical losses in distribution systems, showing that the load model in the frequency domain calculation is robust. Our analyses examine a model for calculating the loss coefficient in distribution systems due to dynamic energy consumption characteristics. We decomposed the load profile by Discrete Fourier Transform (DFT) and applied it to a model adapted to compute the losses spectral analysis, using the Parseval Identity. This paper examines how to estimate the coefficient up to the Nyquist Limit, considering the losses contributions to high frequencies. We evaluate this impact using a practical calculation in the load frequency domain. In this context, it would be interesting to reduce the computational cost and increase the accuracy estimate. Load flow simulations show that the model in the frequency domain presents an error of 0.1514% when compared with the model in the time domain. We obtained an error of 1.8718% using a correlation model between the loss simulations with the low-frequency components and the resolution limit. The model in the frequency domain has greater predictability, considering the load harmonic components' exponential decay characteristic. The intended purpose of this paper is defining regulatory losses in distribution systems.

Identification of Typical and Anomalous Patterns in Electricity Consumption

Nontechnical losses in electricity distribution networks are often associated with a countries’ socioeconomic situation. Although the amount of global losses is usually known, the separation between technical and commercial (nontechnical) losses will remain one of the main challenges for DSO until smart grids become fully implemented and operational. The most common origins of commercial losses are energy theft and deliberate or accidental failures of energy measuring equipment. In any case, the consequences can be regarded as consumption anomalies. The work described in this paper aims to answer a request from a DSO, for the development of tools to detect consumption anomalies at end-customer facilities (HV, MV and LV), invoking two types of assessment. The first consists of the identification of typical patterns in the set of consumption profiles of a given group or zone and the detection of atypical consumers (outliers) within it. The second assessment involves the exploration of the load diagram evolution of each specific consumer to detect changes in the consumption pattern that could represent situations of probable irregularities. After a representative period, typically 12 months, these assessments are repeated, and the results are compared to the initial ones. The eventual changes in the typical classes or consumption scales are used to build a classifier indicating the risk of anomaly.

Non-Technical Electricity Losses

Non-technical loss of electricity (comprising theft, fraud, non-payment and billing irregularities) is a significant issue, particularly in developing countries, and represents a large financial burden on utility companies, governments and society as a whole. This paper takes a wholistic and global view of the challenge and provides a broad perspective of the interrelated issues. Media reports and public perception of non-technical losses tend to focus on residential consumers, particularly those with limited financial resources, whereas review of more robust literature indicates that the largest proportion of non-technical losses is often due to industry, state-owned enterprises and relatively well-off residential consumers. Measures to reduce non-technical losses focusing on average residential consumers, such as pre-paid metering, therefore have limited effect on overall losses. Strengthening of legal and regulatory frameworks, particularly with regard to those larger users, and installing high security tamper-resistant metering systems for commercial consumers may have more effect. The reasons for non-technical losses, especially theft, are complex, but the customer–utility relationship is a key determinant. Improvement of this relationship through local participation in development of renewable energy schemes, such as rooftop solar photovoltaics, could bring benefit if challenges such as financing, design of the distribution system, utility company codes and standards and competence in post installation maintenance can be overcome.

Maximizing the Financial Return of Non-Technical Loss Management in Power Distribution Systems

Despite many studies have been published on non-technical loss management, there is a lack of solutions focused in the financial return of utilities’ actions. This paper aims to contribute to fill up this gap, presenting a new approach that maximizes the financial return of utilities when selecting consumers for field inspections. The predicted return of an inspection is calculated considering its operational cost versus the potential of energy recovery and the tariff value. The potential of energy recovery, in turn, is calculated considering the probability of non-technical loss existence and the forecast of unmeasured energy. The Rotation Forest algorithm is utilized to indicate the non-technical loss existence, while the eXtreme Gradient Boosting algorithm is utilized for energy recovery forecast. The proposed approach was applied in a real database of 261,489 consumers from a Brazilian utility. Then, 338 new field inspections were performed on unlabeled consumers in order to corroborate results in a real application. Achieved results showed an increase of up to 11.5 times in the financial return of field inspections when applying the proposed approach. Results could also be used to determine the optimal number of inspections in the utility, for which the financial return is maximum.

Non-Technical Loss Detection Using Deep Reinforcement Learning for Feature Cost Efficiency and Imbalanced Dataset

One of the problems of the electricity grid system is electricity loss due to energy theft, which is known as non-technical loss (NTL). The sustainability and stability of the grid system are threatened by the unexpected electricity losses. Energy theft detection based on data analysis is one of the solutions to alleviate the drawbacks of NTL. The main problem of data-based NTL detection is that collected electricity usage dataset is imbalanced. In this paper, we approach the NTL detection problem using deep reinforcement learning (DRL) to solve the data imbalanced problem of NTL. The advantage of the proposed method is that the classification method is adopted to use the partial input features without pre-processing method for input feature selection. Moreover, extra pre-processing steps to balance the dataset are unnecessary to detect NTL compared to the conventional NTL detection algorithms. From the simulation results, the proposed method provides better performances compared to the conventional algorithms under various simulation environments.

Data Augmentation Using BiWGAN, Feature Extraction and Classification by Hybrid 2DCNN and BiLSTM to Detect Non-Technical Losses in Smart Grids

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.

A Detection Method for Group Fixed Ratio Electricity Thieves Based on Correlation Analysis of Non-Technical Loss

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.

Non-Technical Losses Detection Using Autoencoder and Bidirectional Gated Recurrent Unit to Secure Smart Grids

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.

Electricity Theft Detection using Machine Learning

This research work dealt with the indiscriminate theft of electric power, reported as a non-technical loss, affecting electric distribution companies and customers, triggering serious consequences including fires and blackouts. The research focused on recommending the best prediction model using Machine Learning in electrical energy theft. The source of the information on the electricity consumption of 42372 consumers was a dataset published in the State Grid Corporation of China. The method used was data imputation, data balancing (oversampling and under sampling), and feature extraction to improve energy theft detection. Five Machine Learning models were tested. As a result, the accuracy indicator of the SVM model was 81%, K-Nearest Neighbors 79%, Random Forest 80%, Logistic Regression 69%, and Naive Bayes 68%. It is concluded that the best performance, with an accuracy of 81%, is obtained by using the SVM model.

Non-technical losses detection in power system

The digitization of distribution networks enables the collection of big data from which it is necessary to draw conclusions and detect anomalies among electricity consumers. This paper explains methodologies to detect non-technical losses, commercial losses, and electricity theft. Based on monthly electricity consumption measurements, possible and prevalent cases of anomalies and theft among consumers are identified. Indicators that can detect anomalies have been proposed for such types of load diagrams. The sensitivity of the indicators to different types of consumers was analyzed. The applicability of this methodology was examined for a set of real measurements, and its advantages were pointed out. This concept represents a good recommendation, as it is possible to observe and detect irregularities in electricity consumption.

Managing System Losses to Improve Energy Efficiency within the Electricity Company of Ghana (ECG) Limited

The inability to achieve the target of universal access to electricity is influenced by several factors including funding limitations, the use of obsolete equipment, power theft, and system losses confronting the electricity distribution services of the Electricity Company of Ghana Limited (ECG). The study assessed the components of system losses within the ECG by determining and computing the percentage of system losses within ECG, examining the causes of both commercial and technical losses in ECG, and determining ways to improve energy efficiency by reducing system losses in the most cost-efficient manner. The study adopted deductive reasoning and a quantitative approach to guide data collection and analysis of the research output. A sample of 345 technical and non-technical staff of ECG in the Greater Accra Metropolis was selected from a population of 2500. Purposive, simple random, and cluster sampling techniques were used in identifying and accessing respondents for the study. Descriptive statistics were applied to measure central tendency and degrees of dispersion and the Relative Importance Index (RII) to predict criterion and predictor variables. The impact of low voltage network losses can adversely contribute to technical losses (20%) and reduce energy efficiency in power or electricity distribution companies. Non-technical losses are mainly caused by illegal connections, meter problems, and billing problems. Each of the non-technical losses contributes a maximum of 10% to system losses. Contributors to system losses at ECG are ranked first for power theft and least for lack of incentives. System losses at ECG include metering inaccuracies, bad workmanship, unmetered supply, and lengthy distribution lines, each recording a mean value of above 3.5. Measures to improve monitoring of the networks and systems at ECG and discourage power theft should include an extensive quantification, patrolling, and inspection of the entire network to assess the extent of the network and conditions relevant for the placement of systematically planned maintenance programmes.

Non-Technical Losses Detection Employing Adversarial Domain Adaptation

Non-Technical Losses Detection Employing Adversarial Domain Adaptation

Adaptive Data Balancing Method Using Stacking Ensemble Model and Its Application to Non-Technical Loss Detection in Smart Grids

Adaptive Data Balancing Method Using Stacking Ensemble Model and Its Application to Non-Technical Loss Detection in Smart Grids

Nontechnical Loss Detection With Duffing–Holmes Self-Synchronization Dynamic Errors and 1D CNN-Based Multilayer Classifier in a Smart Grid

The combined Duffing–Holmes (D–H)–based quantizer and one-dimensional (1D) convolutional neural network (CNN)-based multilayer classifier were applied to perform the nontechnical loss (NTL’s) (electricity fraud) feature quantification, feature extraction, and classification tasks to analyze electricity consumption data and to identify either normal or abnormal consumption patterns for NTL detection. The metering data is gathered every 15 minutes and a 3-hour screening window is used to distinguish between the normal conditions and likely NTL events or power outage events. The D–H-based quantizer in the feature quantification layer may quantify the different levels among three events for preliminary screening differences using D–H self-synchronization dynamic errors. In the feature extraction layer, two 1D convolutional-pooling processes are used to extract 1D key feature signals to enhance the distinguished levels for further classification applications. The gray relational analysis (GRA)-based multilayer network is trained as a classifier. In the classification layer, to identify electricity fraud events. The proposed method is verified and validated using simulation data and the electricity fraud attack model. The correlation coefficient and unitary averaged changed intensity index are applied in correlation analysis to discover apparent abnormality between historical consumption and metering consumption patterns within the short-time monitoring. The D-H-based quantizer and 1D CNN-based classifier then work together to accomplish classification tasks on the time-series metering data. The experimental results show that the suggested classifier model demonstrates promising performance and efficiency compared to the traditional multilayer classifier in feature extraction, training, and recall processing, and accurate classification.

IoT Based Non–Technical Loss Detection and Mitigation System for Power Distribution Networks

Electrical Energy crisis is a major problem faced in the world today and it’s increasingly significant in this part of Africa. A perfect solution seems not to be feasible as several solutions have been proposed in the past by various authors with little impact on the power sector. In this work, we present a method of Non-Technical Loss (NTL) detection consisting of a microcontroller interfaced with a current sensor that measures the current on the power line. A sensor node is placed at the supply end of the pole while two or more others sensor nodes are connected to the output of the pole depending on the number of consumers. The measured value of current is sent via the microcontroller to a web cloud that is accessible by the consumers and the utility company from any part of the world by simply logging on to the website; www.electricity-theft.herokuapp.com. The design uses the principle of Kirchhoff Current Law (KCL) to achieve this aim. The consumers can therefore monitor their power consumption from any location in the world and prevent theft on the network. The results obtained from the installation of the sensor nodes were analyzed using correlation and regression analysis. A correlation analysis of the data results gave us a correlation coefficient of 0.9802, while a regression analysis provided us with a linear relationship between the dependent and independent variable expressed mathematically thus Y = 0.916x + 0.254. A regression graph is also plotted. Furthermore, a T-Test and F-Test was conducted to statistically test the sensor nodes. A NodeMCU Wi-Fi microcontroller and a self-powered Phidget current sensor is used for the sensor node design. Communication between the sensor nodes is via Wi-Fi while a 4G router was used to provide internet services.

IoT Based Non–Technical Loss Detection and Mitigation System for Power Distribution Networks

Electrical Energy crisis is a major problem faced in the world today and it’s increasingly significant in this part of Africa. A perfect solution seems not to be feasible as several solutions have been proposed in the past by various authors with little impact on the power sector. In this work, we present a method of Non-Technical Loss (NTL) detection consisting of a microcontroller interfaced with a current sensor that measures the current on the power line. A sensor node is placed at the supply end of the pole while two or more others sensor nodes are connected to the output of the pole depending on the number of consumers. The measured value of current is sent via the microcontroller to a web cloud that is accessible by the consumers and the utility company from any part of the world by simply logging on to the website; www.electricity-theft.herokuapp.com. The design uses the principle of Kirchhoff Current Law (KCL) to achieve this aim. The consumers can therefore monitor their power consumption from any location in the world and prevent theft on the network. The results obtained from the installation of the sensor nodes were analyzed using correlation and regression analysis. A correlation analysis of the data results gave us a correlation coefficient of 0.9802, while a regression analysis provided us with a linear relationship between the dependent and independent variable expressed mathematically thus Y = 0.916x + 0.254. A regression graph is also plotted. Furthermore, a T-Test and F-Test was conducted to statistically test the sensor nodes. A NodeMCU Wi-Fi microcontroller and a self-powered Phidget current sensor is used for the sensor node design. Communication between the sensor nodes is via Wi-Fi while a 4G router was used to provide internet services.

Determining the causes of electricity losses and the role of management in curbing them: A case study of City of Tshwane Metropolitan Municipality, South Africa

The problem of energy losses, both nationally and internationally, is a leading cause for the financial collapse of most utilities. A quantitative research approach was adopted for this study where a questionnaire was used to collect information from the participants. A total of 113 City of Tshwane (CoT) employees within the electricity division participated in the study. Descriptive statistics and inferential statistical methods were used to analyse the outcome of the survey. The study found that technical and non-technical losses are the major cause of revenue loss. Non-technical losses are caused either by inefficiencies in managing losses or by end-users being unwilling to pay for electricity. The study found that power theft through meter tampering, incorrect billing by employees, and cable theft were also major causes of energy losses. Illegal connections were found to be the major cause of energy losses, along with power theft and lack of resources. Deficiencies in infrastructure maintenance were found to be the main cause of technical losses. The study found that management of CoT is committed to managing energy losses, being aware of their impact on the financial well-being of the municipality. There is an established policy of managing energy losses and there is a plan to replace ageing infrastructure. Employees are continuously trained in accurate billing and metering as part of efforts to curb energy losses. The municipality is also engaged in efforts to put educational programmes in place to inform communities about electricity theft.

Non-technical losses in an electrical distribution system. Energy efficiency as a continuous process

This work analyzes the problem of non-technical losses in a low-voltage electrical power distribution system with an artificial intelligence model. The problem focuses on the use of a backpropagation multilayer perceptron neural network, which will quantitatively determine these losses from the manipulation of the current profile and the voltage drop expressed as percentages of their nominal values. These two magnitudes considered, will allow obtaining from the identification of patterns with large variations a technical assessment or quantification to approach the analysis from a different perspective, differing in the methodological determination of non-technical losses currently considered as a percentage of total losses. The results obtained will allow to form a basis for the correct determination of the non-supplied energy, its influence on distribution costs and energy efficiency for the future insertion of distributed generation.

Application of Machine Learning Algorithm in Managing Deviant Consumer Behaviors and Enhancing Public Service.

Consumer-deviant behavior costs global utility firms USD 96 billion yearly, attributable to Non-Technical Losses (NTLs). NTLs affect the operations of power systems by overloading lines and transformers, resulting in voltage imbalances and, thereby, impacting services. They also impact the electricity price paid by the honest customers. Traditional meters constitute 98 % of the total electricity meters in India. This paper argues that while traditional meters have their limitation in checking consumer-deviant behavior, this issue can be resolved with ML-based algorithms. These algorithms can predict suspected cases of theft with reasonable certainty, thereby enabling distribution companies to save money and provide consistent and dependable services to honest customers at reasonable costs. The key learning from this paper is that even if data is noisy, it is possible to create a Machine Learning Model to detect NTL with 80 percentage plus accuracy.