Packet-data anomaly detection in PMU-based state estimator using convolutional neural network

Basumallik, Sagnik; Ma, Rui; Eftekharnejad, Sara

doi:10.1016/j.ijepes.2018.11.013

Cited by 117 publications

(49 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Contrary to SVMs, deep learning methodologies require large amounts of training data and their detection efficiency is heavily affected by the dimension of the training dataset. Multiple works report detection rates between 90 and 99% when abundance of training data is available for the deep learning detectors [98, 99, 103–107]. Despite the impressive results that deep learning algorithms exhibit, their training process requires an excessive amount of time, has high‐computational costs and demands specialised equipment, in addition to big datasets.…”

Section: Discussion On the Detection Performance Of Machine Learning mentioning

confidence: 99%

Survey of machine learning methods for detecting false data injection attacks in power systems

Hu²,

et al. 2020

View full text Add to dashboard Cite

Section: Discussion On the Detection Performance Of Machine Learning mentioning

confidence: 99%

Survey of machine learning methods for detecting false data injection attacks in power systems

Hu²,

et al. 2020

View full text Add to dashboard Cite

“…Basumallik et al [71] performed an average case analysis of the generalization dynamics of large neural networks trained using gradient descent. Especially, the author studied the practically-relevant "high-dimensional" to use random matrix theory and exact solutions in linear models.…”

Section: Mathematical Methodsmentioning

confidence: 99%

“…Basumallik et al [71] The dataset matrix helps user to detect the abnormal electricity consumption in a short time.…”

Section: Reference Benefits Weaknessesmentioning

confidence: 99%

Anomaly detection for electricity consumption in cloud computing: framework, methods, applications, and challenges

Feng

Zhang

et al. 2020

J Wireless Com Network

View full text Add to dashboard Cite

Driven by industrial development and the rising population, the upward trend of electricity consumption is not going to curb. While the electricity suppliers make every endeavor to satisfy the needs of consumers, they are facing the plight of indirect losses caused by technical or non-technical factors. Technical losses are usually induced by short circuits, power outage, or grid failures. The non-technical losses result from humans’ improper behaviors, e.g., electricity burglars. Due to the restrictions of the detection methods, the detection rate in the traditional power grid is lousy. To provide better electricity service for the customers and minimize the losses for the providers, a leap in the power grid is occurring, which is referred to as the smart grid. The smart grid is envisioned to increase the detection accuracy to an acceptable level by utilizing modern technologies, such as cloud computing. With the aim of obtaining achievements of anomaly detection for electricity consumption with cloud computing, we firstly introduce the basic definition of anomaly detection for electricity consumption. Next, we conduct the surveys on the proposed framework of anomaly detection for electricity consumption and propose a new framework with cloud computing. This is followed by centralized and decentralized detection methods. Then, the applications of centralized and decentralized detection methods for the anomaly electricity consumption are listed. Finally, the open challenges of the accuracy of detection and anomaly detection for electricity consumption with edge computing are discussed.

show abstract

“…A k ‐NN classification method is applied while the features for the training are determined from the instantaneous correlation matrix corresponding to the states. Instead of taking each pixel of instantaneous correlation matrix image as features similar to [10], we extracted features to train the k ‐NN method for classification which is computationally efficient.…”

Section: Related Workmentioning

confidence: 99%

Detecting and locating cyber and physical stresses in smart grids using the k‐nearest neighbour analysis of instantaneous correlation of states

Hasnat

Rahnamay-Naeini

2021

IET Smart Grid

View full text Add to dashboard Cite

Monitoring the state of smart grids and detecting abnormalities are challenging tasks due to their large size, distributed nature, and complex and stochastic dynamics. Large deployment of sensors and monitoring devices, such as Phasor Measurement Units, provides a large volume of data about the state of the system, which presents both new opportunities and challenges in monitoring these systems. Different types of cyber-attacks have targeted the important function of monitoring smart grids and the integrity of the collected data. The multivariate time series of the state of components are analysed through their instantaneous correlation. The effects of multiple cyber-attacks and single line failures in the system on the instantaneous correlations are discussed. Moreover, a machine learning method is proposed to use the features selected from instantaneous correlations in a k-Nearest Neighbour classification for real-time detection and locating of stresses. The presented method shows a promising performance, which has been evaluated under a large number of simulated scenarios. This is an open access article under the terms of the Creative Commons Attribution-NonCommercial-NoDerivs License, which permits use and distribution in any medium, provided the original work is properly cited, the use is non-commercial and no modifications or adaptations are made.

show abstract

Packet-data anomaly detection in PMU-based state estimator using convolutional neural network

Cited by 117 publications

References 32 publications

Survey of machine learning methods for detecting false data injection attacks in power systems

Survey of machine learning methods for detecting false data injection attacks in power systems

Anomaly detection for electricity consumption in cloud computing: framework, methods, applications, and challenges

Detecting and locating cyber and physical stresses in smart grids using the k‐nearest neighbour analysis of instantaneous correlation of states

Contact Info

Product

Resources

About