Detecting and Locating Non-Technical Losses in Modern Distribution Networks

Leite, Jônatas Boás; Mantovani, José Roberto Sanches

doi:10.1109/tsg.2016.2574714

Cited by 115 publications

(54 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pulz et al [10] used the social indicators extracted from the census data to analyse the correlation between losses and socio-economic indices for energy theft detection. Apart from using machine learning approaches, Leite and Mantovani [11] devised a non-technical loss detection mechanism by monitoring the variance of various regional values using multivariate control chart. Xiao and Ai [12] proposed an energy theft detection method on the basis of random matrix theory model to identify the correlations between power consumption and system operation under various scenarios of electricity usage.…”

Section: B Aggregate Energy Consumption Profilingmentioning

confidence: 99%

Tackling Energy Theft in Smart Grids through Data-driven Analysis

Jindal

Schaeffer-Filho

Marnerides

et al. 2020

2020 International Conference on Computing, Networking and Communications (ICNC)

View full text Add to dashboard Cite

The increasing use of information and communication technology (ICT) in electricity grid infrastructures facilitates improved energy generation, transmission, and distribution. However, smart grids are still in their infancy with a disparate regional role out. Due to the involved costs utility providers are only embedding ICT in selected parts of the grid, thereby creating only partial smart grid infrastructures. We argue that using the data provided by these partial smart grid deployments can still be beneficial in solving various issues such as energy theft detection. In this paper, we focus on various data-driven techniques to detect energy theft in power networks. These datadriven detection techniques (at the smart meter as well as the aggregated level) can indicate various forms of energy theft (e.g. through clandestine connections or meter tampering). This paper also presents two case studies to show the effectiveness of these approaches.

show abstract

Section: B Aggregate Energy Consumption Profilingmentioning

confidence: 99%

Tackling Energy Theft in Smart Grids through Data-driven Analysis

Jindal

Schaeffer-Filho

Marnerides

et al. 2020

2020 International Conference on Computing, Networking and Communications (ICNC)

View full text Add to dashboard Cite

show abstract

“…The implementation of advance metering infrastructure (AMI) has benefits in the detection of fraudulent users who have billing such as flexibility and adaptability in any electrical system, monitoring data in real time with reduction of electricity costs due to more precise consumption and more accurate location of non-technical losses. This result is achieved through the use of intelligent electronics devices, measures taken through an automated process and advanced measurement systems (Jiang et al, 2014;Leite & Mantovani, 2016;Lo, Huang, & Lu, 2012;Su, Lee, & Wen, 2016). The importance of this technology is due to the increase of efficiency of estimation algorithms and classification of users, such as distribution state estimation (DSE), A-Star algorithm and semi-definite relaxation (SDR).…”

Section: Uparela Gonzalez Jimenez and Quinteromentioning

confidence: 99%

Intelligent system for non-technical losses management in residential users of the electricity sector

Cantillo¹,

González²,

Mares³

et al. 2018

Ing. Inv.

View full text Add to dashboard Cite

The identification of irregular users is an important assignment in the recovery of energy in the distribution sector. This analysis requires low error levels to minimize non-technical electrical losses in power grid. However, the detection of fraudulent users who have billing does not present a generalized methodology. This issue is complex and varies according to the case study. This paper presents a novel methodology to identify residential fraudulent users by using intelligent systems. The proposed intelligent system consists of three fundamental modules. The first module performs the classification of users with similar power consumption curves using self-organizing maps and genetic algorithms. The second module allows carrying out the monthly electricity demand forecasting through of recursive adjustment of ARIMA models. The third module performs the detection of fraudulent users through an artificial neural network for pattern recognition. For the design and validation of the proposed intelligent system, several tests were performed in each developed module. The database used for the design and evaluation of the modules was constructed with data supplied by the energy distribution company of the Colombian Caribbean Region. The results obtained by the proposed intelligent system show a better performance versus the detection rates obtained by the company. RESUMENLa identificación de usuarios con consumo fraudulento es una actividad importante en la recuperación de energía en el sector de la distribución. Este análisis requiere bajos niveles de error para minimizar las pérdidas eléctricas no técnicas en la red de distribución. Sin embargo, la detección de usuarios fraudulentos con facturación no tiene una metodología generalizada. Este es un problema complejo y varía de acuerdo con cada caso de estudio. Este artículo presenta una nueva metodología para la identificación inteligente de usuarios fraudulentos residenciales basada en sistemas inteligentes. El sistema inteligente propuesto consiste en tres módulos fundamentales. El primer módulo clasifica a los usuarios con curvas de consumo similares a través de mapas auto-organizativos y algoritmo genéticos. El segundo módulo realiza la predicción de consumos mensuales mediante ajustes recursivos de modelos ARIMA. El tercer módulo es el responsable de llevar a cabo la detección de usuarios irregulares por medio de una red neuronal para reconocimiento de patrones. Para el diseño y validación del sistema inteligente propuesto se realizaron pruebas en cada módulo que lo integra para diferentes tipos de clientes del mercado. La base de datos utilizada para el diseño y evaluación de los módulos fue construida a partir de los datos suministrados por la empresa de distribución de energía de la Costa Caribe Colombiana. Los resultados obtenidos por el sistema inteligente propuesto muestran un mejor desempeño frente a los índices de detección obtenidos por la empresa.Palabras clave: pérdidas no técnicas, consumo irregular de electricidad, detección de fraudes, sistemas i...

show abstract

“…e key idea of state-based detection [9][10][11] is based on special devices such as wireless sensors and distribution transformers [12].…”

Section: Introductionmentioning

confidence: 99%

Electricity Theft Detection in Power Grids with Deep Learning and Random Forests

Shuan

Han

Yao

et al. 2019

Journal of Electrical and Computer Engineering

137

View full text Add to dashboard Cite

As one of the major factors of the nontechnical losses (NTLs) in distribution networks, the electricity theft causes significant harm to power grids, which influences power supply quality and reduces operating profits. In order to help utility companies solve the problems of inefficient electricity inspection and irregular power consumption, a novel hybrid convolutional neural network-random forest (CNN-RF) model for automatic electricity theft detection is presented in this paper. In this model, a convolutional neural network (CNN) firstly is designed to learn the features between different hours of the day and different days from massive and varying smart meter data by the operations of convolution and downsampling. In addition, a dropout layer is added to retard the risk of overfitting, and the backpropagation algorithm is applied to update network parameters in the training phase. And then, the random forest (RF) is trained based on the obtained features to detect whether the consumer steals electricity. To build the RF in the hybrid model, the grid search algorithm is adopted to determine optimal parameters. Finally, experiments are conducted based on real energy consumption data, and the results show that the proposed detection model outperforms other methods in terms of accuracy and efficiency.

show abstract

Detecting and Locating Non-Technical Losses in Modern Distribution Networks

Cited by 115 publications

References 28 publications

Tackling Energy Theft in Smart Grids through Data-driven Analysis

Tackling Energy Theft in Smart Grids through Data-driven Analysis

Intelligent system for non-technical losses management in residential users of the electricity sector

Electricity Theft Detection in Power Grids with Deep Learning and Random Forests

Contact Info

Product

Resources

About