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

Cui, Xueyuan; Liu, Shengyuan; Liu, Shengyuan; Ma, Jien; Wen, Fushuan; Ding, Yi; Yang, Li; Guo, Wenchong; Feng, Xiaofeng

doi:10.1109/tpwrs.2021.3114307

Cited by 42 publications

(9 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5 Terminal fault diagnosis process When analyzing the fault of electric energy measuring equipment, the output fault information inevitably contains the mutation quantity and mutation quantity, and also contains some unsteady state noise. In order to accurately analyze this type of signal, it is necessary to process it accordingly, remove the noise in it, and retain useful information [9]. In terms of denoising, the conventional Fourier transform can not achieve the ideal denoising effect, because all steps of Fourier decomposition are carried out in the time domain, so it can not reflect the sudden change of the signal in real time, and when the signal changes at a certain time, it will cause serious damage to the whole image.…”

Section: Development Of Intelligent Fault Detection Systemmentioning

confidence: 99%

Application of SSA-KNN Algorithm in Fault Analysis of Power Metering Automation System

Yan Liu, Chaoran Bi, Yaoyu Wang

2024

jes

View full text Add to dashboard Cite

In view of the great pressure of operation and maintenance of power energy data collection terminal after putting into operation, an intelligent fault diagnosis system for power equipment terminal based on computer was developed. This paper proposes an Agent based on autonomy, promotility, cooperation and interactivity. It also provides a flexible interactive communication interface and load balancing optimization method. It can meet a variety of data transmission specifications and a large number of data service transmission requirements. The SA-KNN algorithm is used to analyze the power quality. Methods The operation data of maintenance electricity were collected. Learning and cluster analysis are carried out by using relevant data, and the calculation model of automatic check device failure is established. At the same time, the outlier points in the collected data are used to accurately locate the fault points of the power grid. This method can realize the comprehensive fault diagnosis of the power grid by using the interaction between the power grid and each component.

show abstract

Section: Development Of Intelligent Fault Detection Systemmentioning

confidence: 99%

Application of SSA-KNN Algorithm in Fault Analysis of Power Metering Automation System

Yan Liu, Chaoran Bi, Yaoyu Wang

2024

jes

View full text Add to dashboard Cite

show abstract

“…The fluctuation index (FI) is used to describe the discrete degree of load data during a time period, which is calculated by Equation (8).…”

Section: Fluctuation Indexmentioning

confidence: 99%

“…To address these issues, the power utilities usually send technical staffs to check ammeters termly, which is extremely time-consuming, expensive, and inefficient and can only detect the electricity theft behaviour of destroying ammeters [5][6][7]. With the application of smart meters and advanced metering infrastructure (AMI) [8], other electricity theft behaviours including bypassing and non-invasive interference ammeters can be effectively prevented. However, fraudulent users can tamper with the records of smart meters by using digital tools or cyber-attacks [9,10], and these misbehaviours are difficult to be detected using conventional electricity theft detection methods.…”

Section: Introductionmentioning

confidence: 99%

A combined unsupervised learning approach for electricity theft detection and loss estimation

Shao

Chen

2023

IET Energy Syst Integration

View full text Add to dashboard Cite

Electricity theft is a great trouble for power companies. As the means of tampering with smart meters continue to increase, the electricity theft behaviours become more diversified and covert, which are difficult to be identified using the existing electricity theft detection method. In addition, the existing methods usually cannot estimate the economic losses caused by electricity theft. To address these issues, a combined unsupervised learning approach for electricity theft detection and loss estimation is proposed in this study. First, three anomaly measurement indexes including the mean index, fluctuation index, and trend index are proposed to capture different anomalies respectively. Then, based on historical electricity consumption data, we develop two unsupervised learning techniques including the sample-to-subsamples decomposition algorithm and clustering algorithm to obtain the typical ranges of index values, and the load samples whose index values are not in the typical ranges will be considered fraudulent. Furthermore, three anomaly measurement indexes are combined to judge whether the load sample is fraudulent, and the user whose most load samples are judged fraudulent will be considered as an electricity thief. Finally, an economic loss estimation method is proposed, which quantifies the losses of electricity theft. Numerical experiments are carried out based on the Irish smart meter dataset, and the results demonstrate the effectiveness and the superior performance of the proposed method compared with a series of electricity theft detection methods.

show abstract

“…Smart meters are used to monitor the electricity usage of customers and the power consumption of various appliances, providing real-time client electricity consumption data to power grid operators so that operators can detect and solve abnormal electricity usage situations timely, reduce resource consumption, and ensure safe operation of the power grid [3]. A series of abnormal electricity usage behaviours, such as illegal power connection [4], theft [5], overload [6], and illegal power transfer [7], seriously affect the safety of load electricity usage in the power system, with electricity theft being the most prominent [8]. Therefore, the detection and analysis of abnormal electricity usage have attracted the attention of many scholars [9][10][11].…”

Section: Introductionmentioning

confidence: 99%

Analysis of safe electricity consumption on load side based on attack and defence game model

Wang,

Gong,

Chen

et al. 2024

The Journal of Engineering

View full text Add to dashboard Cite

With the improvement of digitalization and intelligence in the power system, the safe operation of the power system is facing enormous challenges. The safe use of electricity on the load side is the key to achieving safe and reliable power system operation. The detection party needs amounts of human and material resources when the power network is attacked. In response to the current difficulties of low detection ability and high detection costs, this paper proposes an attack and defence game model that considers the differences between different nodes, ensuring the safety and economy of electricity consumption while reducing energy waste. At first, the structure of smart meters and the attack characteristics of intruders are summarized, and a basic attack and defence game model is constructed. The Nash equilibrium is then solved, and the optimal strategy for the game between the defender and the intruder is given to balance the relation between detection performance and energy consumption. In response to the differences generated by each node, strategies for attackers to launch attacks on different nodes and the setting of optimal thresholds for other nodes in the defence system are explored. Finally, case studies verify that the proposed model could reduce the cost of intruder detection while ensuring a specific detection rate.

show abstract

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

Cited by 42 publications

References 36 publications

Application of SSA-KNN Algorithm in Fault Analysis of Power Metering Automation System

Application of SSA-KNN Algorithm in Fault Analysis of Power Metering Automation System

A combined unsupervised learning approach for electricity theft detection and loss estimation

Analysis of safe electricity consumption on load side based on attack and defence game model

Contact Info

Product

Resources

About