A SVM-based detection method for electricity stealing behavior of charging pile

Hong, Huawei; Su, Yuquan; Zheng, Peng; Cheng, Nuo; Zhang, Jinbo

doi:10.1016/j.procs.2021.02.062

Cited by 10 publications

(4 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After getting the hybrid dataset composed of real electricity data and specific electricity stealing data, various detection models can be adopted [9][10][11][12][13][14][15][16][17][18][19]. However, due to two features of S , i.e., small scale of electricity stealing and random coherence with time, the performance of these models is not optimal and deep features are needed.…”

Section: Method: Bi-resnet Modelmentioning

confidence: 99%

“…Subsequently, various studies concern more about the features of electricity data rather than LLR. Specifically, paper [14,15] utilizes support vector machines (SVM) to seek for the hyperplanes which can distinguish ordinary users and electricity stealing users. Paper [16,17] adopts long and short-term memory (LSTM) network to study the time characteristics of electricity data and achieves anti-electricity theft load.…”

mentioning

confidence: 99%

See 1 more Smart Citation

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

Feng

et al. 2022

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

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.

show abstract

Section: Method: Bi-resnet Modelmentioning

confidence: 99%

mentioning

confidence: 99%

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

Feng

et al. 2022

EURASIP J. Adv. Signal Process.

View full text Add to dashboard Cite

show abstract

“…At present, some scholars have also carried out research on charging piles. Hong et al (2021) detected electricity stealing behavior of charging piles based on support vector machine. By constructing a recognition model of the electricity stealing behavior of a charging pile, the purpose of anti-stealing electricity from a charging pile is achieved.…”

Section: Literature Reviewmentioning

confidence: 99%

Research on Restrictive Factors and Planning of Charging Piles for Electric Vehicles in the Park Based on the Interpretative Structural Model

Zhang

Zhao

et al. 2022

Front. Energy Res.

View full text Add to dashboard Cite

At present, the world is vigorously promoting the innovative development concept of “green development, park first,” prompting the park to vigorously promote the construction of electric vehicle charging stations and charging pile projects. However, the development of the construction is not satisfactory due to a series of restrictive factors. Under this background, this article studies the constraints of EV charging stations in the park and further studies the impact on park planning. First, this article outlines the constraints of charging piles in the park based on the field research. Then, interpretive structural modeling (ISM) is adopted in this article for in-depth analysis of the restrictive factors. Finally, the impact on the industrial park’s planning is analyzed as a case study. The improved countermeasures provide a basis for the scientific planning and design of electric vehicle charging stations in industrial parks.

show abstract

“…With the popularity of electric vehicles, more and more charging stations are appearing in cities [1][2][3]. Since the wiring in charging piles is in a dense and small space, the multi-sensors in charging piles must meet the characteristics of small size, AC-DC simultaneous measurement, large dynamic range, low power consumption and fast response [4][5]. In electric vehicles, the charging and discharging activities of the battery will show the reaction of internal chemicals, which are related to the charging energy efficiency of the electric vehicle and the service life of the battery, requiring the staff to scientifically monitor the charging pile in terms of current, voltage, and temperature [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Research on multi-sensor-based online inspection technology for electric vehicle charging pile transfer type equipment

Chen,

Zhao,

Zhang

et al. 2023

Applied Mathematics and Nonlinear Sciences

View full text Add to dashboard Cite

This paper performs data fusion based on a multi-sensor fusion algorithm, which measures the sensors and calculates the distance between the data to obtain the measurement weights when participating in the fusion. The sensor observation model is created using an extended Kalman filter, and the nonlinear state transition function is linearized using the covariance matrix. Accurately estimating sensor inter-cluster data is necessary to achieve the scalability of online detection technology for charging piles. The results show that the disconnection time of the contactor of the charging pile transfer type equipment is 1.153s after the simulated charging pile output over-voltage in the disconnection time detection. The online detection efficiency can be improved by using multiple sensors, the method analysis can be intuitive, and the charging service capability of the electric vehicle charging pile can be effectively improved.

show abstract

A SVM-based detection method for electricity stealing behavior of charging pile

Cited by 10 publications

References 1 publication

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

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

Research on Restrictive Factors and Planning of Charging Piles for Electric Vehicles in the Park Based on the Interpretative Structural Model

Research on multi-sensor-based online inspection technology for electric vehicle charging pile transfer type equipment

Contact Info

Product

Resources

About