A Tunable Fraud Detection System for Advanced Metering Infrastructure Using Short-Lived Patterns

Zanetti, Marcelo Serrano; Jamhour, Edgard; Pellenz, Marcelo Eduardo; Penna, Manoel Camillo; Zambenedetti, Voldi Costa; Chueiri, Ivan

doi:10.1109/tsg.2017.2753738

Cited by 121 publications

(75 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, the realistic NTL samples of which in-field inspected are rare indeed, supervised learning methods are an easier lead to overfitting. On the other hand, the artificial samples as a possible solution are adopted by some approaches [10,11]. Even though they provide lots of labeled samples to support training models, the effectiveness of such attack models is not verified by realistic cases.…”

Section: How To Obtain Satisfactory Performance Based On Limited Labementioning

confidence: 99%

“…However, it is difficult to collect enough realistic normal and abnormal cases, which makes the labeled samples are very scarce. To avoid insufficient realistic NTL samples, [10,11,13] attempt to model NTL and produce artificial NTL samples. Same as the necessary requirement of massive labeled samples, features are equally important to classifiers.…”

Section: Related Workmentioning

confidence: 99%

“…Furthermore, it might be existed from the beginning, such as phase disorder. In contrast to the SMART attack defined in [11] or FDI5 defined in [10], the realistic NTL does not run in fixed artificial model and is more random and complicated. Consequently, the domain knowledge based features are very important for classifier to detect NTL.…”

Section: Phase Disordermentioning

confidence: 99%

“…They can hardly represent all scenarios of NTL because consumption behaviour is random and unpredictable, especially for industrial customers. For example, when changes in consumption pattern due to change in household residents or usage of electrical devices might make it looks like electricity theft [10]. This situation would destroy linear separability of traditional features.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Knowledge Embedded Semi-Supervised Deep Learning for Detecting Non-Technical Losses in the Smart Grid

Zhou

Wang

et al. 2019

Energies

View full text Add to dashboard Cite

Non-technical losses (NTL) caused by fault or electricity theft is greatly harmful to the power grid. Industrial customers consume most of the power energy, and it is important to reduce this part of NTL. Currently, most work concentrates on analyzing characteristic of electricity consumption to detect NTL among residential customers. However, the related feature models cannot be adapted to industrial customers because they do not have a fixed electricity consumption pattern. Therefore, this paper starts from the principle of electricity measurement, and proposes a deep learning-based method to extract advanced features from massive smart meter data rather than artificial features. Firstly, we organize electricity magnitudes as one-dimensional sample data and embed the knowledge of electricity measurement in channels. Then, this paper proposes a semi-supervised deep learning model which uses a large number of unlabeled data and adversarial module to avoid overfitting. The experiment results show that our approach can achieve satisfactory performance even when trained by very small samples. Compared with the state-of-the-art methods, our method has achieved obvious improvement in all metrics.

show abstract

Section: How To Obtain Satisfactory Performance Based On Limited Labementioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Phase Disordermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Knowledge Embedded Semi-Supervised Deep Learning for Detecting Non-Technical Losses in the Smart Grid

Zhou

Wang

et al. 2019

Energies

View full text Add to dashboard Cite

show abstract

“…In [305], information leakage from a smart meter is studied using a RES and battery to partially hide customer details, and it is concluded that larger batteries can help to enhance privacy by exploiting the available energy. To determine malicious meters, a fraud detection system (FDS) is developed in [306] while detectors in both centralised and distributed settings for the online detection of false data injection (FDI) and denial of service (DoS) attacks are proposed in [307] using a CUSUM algorithm. As exposure to radio frequencies from smart meters during wireless communication is another concern, various countries have taken action to limit its bad effects [308].…”

Section: Challenges Of Microgridsmentioning

confidence: 99%

Evolution of Microgrids with Converter-Interfaced Generations: Challenges and Opportunities

Hossain¹,

Pota²,

Hossain³

et al. 2018

Preprint

View full text Add to dashboard Cite

Although microgrids facilitate the increased penetration of distributed generations (DGs) and improve the security of power supplies, they have some issues that need to be better understood and addressed before realising the full potential of microgrids. This paper presents a comprehensive list of challenges and opportunities supported by a literature review on the evolution of converter-based microgrids. The discussion in this paper presented with a view to establishing microgrids as distinct from the existing distribution systems. This is accomplished by, firstly, describing the challenges and benefits of using DG units in a distribution network and then those of microgrid ones. Also, the definitions, classifications and characteristics of microgrids are revised according to their specific roles to provide a sound basis for novice researchers to undertake ongoing research on microgrids.

show abstract

False Data Injection Attacks in Power Systems

Ameli¹,

Hamed²

2023

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Power networks are among the most critical infrastructures of any society, since other infrastructures are dependent on power and energy systems. Recently, there has been a trend toward harnessing Information Technology (IT) in power networks to enhance their performance and improve their consumer centricity. This movement, however, has exposed power systems to cyberattacks. Among various types of cyber intrusions, False Data Injection Attack (FDIA) is the most important one, since it stealthily intercepts the legitimate traffic and/or injects malicious data into the system, thus resulting in severe physical and economic damages. There has been a substantial increase in the number of reported FDIAs in recent years, which indicates the necessity of extensive research on vulnerabilities of power systems to FDIAs, probable attack models, impacts of such intrusions, and the possible preventive and detective measures. On this basis, this article presents a comprehensive review of FDIAs in power networks, with a particular focus on attack targets and adversarial methods. Additionally, it elaborates on various types of FDIAs, their implementation steps and strategies, and the vulnerabilities of various components and schemes to this type of attack. Finally, the it briefly discusses FDIA detection techniques in power grids.

show abstract

A Tunable Fraud Detection System for Advanced Metering Infrastructure Using Short-Lived Patterns

Cited by 121 publications

References 35 publications

Knowledge Embedded Semi-Supervised Deep Learning for Detecting Non-Technical Losses in the Smart Grid

Knowledge Embedded Semi-Supervised Deep Learning for Detecting Non-Technical Losses in the Smart Grid

Evolution of Microgrids with Converter-Interfaced Generations: Challenges and Opportunities

False Data Injection Attacks in Power Systems

Contact Info

Product

Resources

About