A machine learning-based detection framework against intermittent electricity theft attack

Fang, Hongliang; Xiao, Jiang‐Wen; Wang, Yan‐Wu

doi:10.1016/j.ijepes.2023.109075

Cited by 11 publications

(3 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LightGBM : The light gradient boosting method (LightGBM), a boosting framework, leverages tree-based learning algorithms and is designed to be efficient and scalable for large datasets [ 115 ]. It adopts gradient-based one-sided sampling and exclusive feature bundling to expedite training and diminish memory usage.…”

Section: Methodsmentioning

confidence: 99%

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Klaar,

Seman,

Mariani

et al. 2024

Sensors

View full text Add to dashboard Cite

The electrical energy supply relies on the satisfactory operation of insulators. The ultrasound recorded from insulators in different conditions has a time series output, which can be used to classify faulty insulators. The random convolutional kernel transform (Rocket) algorithms use convolutional filters to extract various features from the time series data. This paper proposes a combination of Rocket algorithms, machine learning classifiers, and empirical mode decomposition (EMD) methods, such as complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN), empirical wavelet transform (EWT), and variational mode decomposition (VMD). The results show that the EMD methods, combined with MiniRocket, significantly improve the accuracy of logistic regression in insulator fault diagnosis. The proposed strategy achieves an accuracy of 0.992 using CEEMDAN, 0.995 with EWT, and 0.980 with VMD. These results highlight the potential of incorporating EMD methods in insulator failure detection models to enhance the safety and dependability of power systems.

show abstract

Section: Methodsmentioning

confidence: 99%

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Klaar,

Seman,

Mariani

et al. 2024

Sensors

View full text Add to dashboard Cite

show abstract

“…Robust data mining and ML techniques are employed for the training and testing of the classifier before being deployed to detect fraudulent cases. Some artificial intelligence techniques such as support vector machine, decision tree, random forest, and gradient boosting have been implemented for electricity theft detection to detect nontechnical losses (Ahmad et al, 2018;Depuru et al, 2011;Nagi et al, 2008;Tehrani et al, 2020;Toma et al, 2019). However, a fundamental issue related to ML classifiers as applicable to electricity theft detection is imbalance in the data resulting from the difference in normal and abnormal samples.…”

Section: Related Studiesmentioning

confidence: 99%

“…Moreover, the conventional power systems are being upgraded worldwide to deliver the advantages AMI offered through SG implementations. These include effective power consumption monitoring, reduced grid losses, enhanced grid operations and effective energy management (Calderaro et al, 2011;Clastres, 2011;El-Hawary, 2014;Moretti et al, 2017). AMI enables a two-way communication between the consumers and utilities via smart electricity meters (SEM) at both ends (Fatemieh et al, 2010;Jiang et al, 2014;Jokar, 2015;Shuaib et al, 2015).…”

Section: Introductionmentioning

confidence: 99%

Detection and confirmation of electricity thefts in Advanced Metering Infrastructure by Long Short-Term Memory and fuzzy inference system models

Otuoze,

Mustafa,

Sultana

et al. 2024

Nig. J. Technol. Dev.

View full text Add to dashboard Cite

The successful implementation of Smart Grids heavily relies on energy efficiency, particularly through the Advanced Metering Infrastructure (AMI) and Smart Electricity Meters (SEM). However, cyber-attacks pose a threat to SEM, with electricity theft being a primary motivation. Despite the valuable data provided by SEM for analytical purposes, existing methods to identify theft involve cumbersome and costly on-site inspections. This research proposes an electricity theft detection model using the Long Short-Term Memory (LSTM) network. The model employs a collective anomaly approach, defining prediction errors through a threshold and forecast horizon. Suspicious consumption profiles are analysed, and a fuzzy inference system (FIS) implemented in MATLAB 2021b is used to model security risks based on these profiles. The study utilizes energy consumption data from four diverse consumer profiles (consumers 1, 2, 3, and 4) to develop consumer-specific LSTM models for detection and an FIS model for confirmation. Tampered consumer data is identified and confirmed based on selected AMI parameters. While all consumers exhibit suspicious profiles at times, only consumers 2 and 3 are confirmed as engaging in electricity theft. This research provides a robust approach to detecting and verifying fraudulent consumption profiles within the context of AMI, offering a more reliable dimension to theft detection and confirmation.

show abstract

Ensemble LOF-based detection of false data injection in smart grid demand response system

Tirulo,

Chauhan,

Issac

2024

Computers and Electrical Engineering

View full text Add to dashboard Cite

A machine learning-based detection framework against intermittent electricity theft attack

Cited by 11 publications

References 38 publications

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Random Convolutional Kernel Transform with Empirical Mode Decomposition for Classification of Insulators from Power Grid

Detection and confirmation of electricity thefts in Advanced Metering Infrastructure by Long Short-Term Memory and fuzzy inference system models

Ensemble LOF-based detection of false data injection in smart grid demand response system

Contact Info

Product

Resources

About