2018
DOI: 10.1016/j.ijepes.2018.01.036
|View full text |Cite
|
Sign up to set email alerts
|

Detection of illegal consumers using pattern classification approach combined with Levenberg-Marquardt method in smart grid

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
31
0

Year Published

2019
2019
2023
2023

Publication Types

Select...
6
2
1

Relationship

0
9

Authors

Journals

citations
Cited by 45 publications
(31 citation statements)
references
References 22 publications
0
31
0
Order By: Relevance
“…In ETD literature, the proposed methods are categorized into two major groups: ETD through technical methods and ETD through nontechnical methods. Nontechnical methods cover: the auditing and inspection of illegal electricity consumers, giving awareness to the electricity consumers about electricity theft as a crime and punishment, installing the smart meters that can not be easily tampered with by consumers and reducing electricity theft through the psychosocial methods, such as social support [26]. Technical methods are also broadly classified into three types: state-based solutions (also known as hardware-based solutions), game-theory-based solutions and data-driven solutions (also known as machine learning-based solutions) [12].…”
Section: Introductionmentioning
confidence: 99%
See 1 more Smart Citation
“…In ETD literature, the proposed methods are categorized into two major groups: ETD through technical methods and ETD through nontechnical methods. Nontechnical methods cover: the auditing and inspection of illegal electricity consumers, giving awareness to the electricity consumers about electricity theft as a crime and punishment, installing the smart meters that can not be easily tampered with by consumers and reducing electricity theft through the psychosocial methods, such as social support [26]. Technical methods are also broadly classified into three types: state-based solutions (also known as hardware-based solutions), game-theory-based solutions and data-driven solutions (also known as machine learning-based solutions) [12].…”
Section: Introductionmentioning
confidence: 99%
“…Maamar et al [32] offered a hybrid model that utilizes the k-means clustering procedure and deep neural networks (DNN) for ETD in the AMI system, where k-means is utilized to gather consumers having the same electricity consumption behaviors, and DNN is used to detect anomalies in the electricity consumption behaviors of the consumers. Ghasemi et al [26] proposed a solution comprising of a probabilistic neural network and mathematical model, named the PNN-Levenberg-Marquardt, for the identification of two types of illegal consumers using the observer's meters. PNN is applied to detect the suspicious consumers, and the Levenberg-Marquardt is practiced for classifying the fraud consumers.…”
Section: Introductionmentioning
confidence: 99%
“…The dimensionality of data and the operation cost of outlier factor algorithm were reduced by grid technology. In [26], electricity theft detection method based on probabilistic neural network was employed to detect two types of illegal consumption.…”
Section: Introductionmentioning
confidence: 99%
“…For example, improved exponential smoothing grey model [10], self-adaptive evolutionary fuzzy model [11], and, artificial neural network (ANN) [12] have been employed into solve the STLF. Furthermore, random forest has been applied into day-ahead load forecasting [13]; deep neural networks (DNNs) have been employed into building energy load forecasting [14]; Levenberg-Marquardt method has been applied into the detection of illegal consumers [15]; the ANN-based conjugate gradient with Powell/Beale restarts has been modeled for fault detection of partial shaded photo-voltaic modules [16]; rule-based autoregressive moving average method has been proposed for forecasting load on a special France days [17] and complex nonlinear systems [18].…”
Section: Introductionmentioning
confidence: 99%