Based on the Fractal Technology of Bad Data Detection Method in Power System

2012 ◽  
Vol 490-495 ◽  
pp. 1358-1361
Author(s):  
Yan Hong Li
Keyword(s):  
Power System ◽  
Search Space ◽  
Detection Algorithm ◽  
Fractal Model ◽  
Detection Methods ◽  
Data Detection ◽  
Data Set ◽  
Bad Data Detection ◽  
Time Space ◽  
Bad Data

detection and identification of bad data is an important part of state estimation in power system. To solute the problem generates a variety of detection methods and means in academic and industrial circles, commonly used methods include objective function detection, weighted residual detection, measurement suddenly-change detection and the comprehensive application of above methods. In order to detection the bad data from large amounts of data over the multiple sliding windows, bad data detection algorithm is proposed based on fractal technology building monotonic search space. Firstly, it gives the data set on the piecewise fractal model, and then based on this model to design a detection algorithm. The algorithm can reduce detection processing time greatly. The subsection fractal model can accurately model on the data self similarity and compress data. Theoretical analysis and experimental results show that, the algorithm has higher precision and lower time / space complexity, more suitable for bad data detection.

scholarly journals PSO Supported Ensemble Algorithm for Bad Data Detection Against Intelligent Hacking Algorithm

2021 ◽  
Vol 9 ◽  
Author(s):  
Levent Yavuz ◽  
Ahmet Soran ◽  
Ahmet Onen ◽  
SM Muyeen
Keyword(s):  
Machine Learning ◽  
Power System ◽  
Detection Algorithm ◽  
Cyber Attacks ◽  
Data Detection ◽  
Particle Swarm Optimizer ◽  
Bad Data Detection ◽  
Detection Mechanisms ◽  
Bad Data ◽  
Advanced Computer

Power system cybersecurity has recently become important due to cyber-attacks. Due to advanced computer science and machine learning (ML) applications being used by malicious attackers, cybersecurity is becoming crucial to creating sustainable, reliable, efficient, and well-protected cyber-systems. Power system operators are needed to develop sophisticated detection mechanisms. In this study, a novel machine-learning-based detection algorithm that combines the five most popular ML algorithms with Particle Swarm Optimizer (PSO) is developed and tested by using an intelligent hacking algorithm that is specially developed to measure the effectiveness of this study. The hacking algorithm provides three different types of injections: random, continuous random, and slow injections by adaptive manner. This would make detection harder. Results shows that recall values with the proposed algorithm for each different type of attack have been increased.

Bad data detection in power system state estimation based on generalized likelihood ratio test

2016 ◽  
Vol 04 (04) ◽  
pp. 1650016 ◽  
Author(s):  
Zahid Khan ◽  
Radzuan B. Razali ◽  
Hanita Daud ◽  
Nursyarizal Mohd Nor ◽  
Mahmud Fotuhi-Firuzabad ◽  
...  
Keyword(s):  
Power System ◽  
State Estimation ◽  
Likelihood Ratio Test ◽  
Generalized Likelihood Ratio Test ◽  
Data Detection ◽  
Ratio Test ◽  
System State ◽  
Power System State Estimation ◽  
Bad Data Detection ◽  
Bad Data

scholarly journals Denoising and Bad Data Detection in Distribution Phasor Measurements using Filtering, Clustering and Koopman Mode Analysis

2021 ◽  
Author(s):  
Amirkhosro Vosughi ◽  
Amir Gholami ◽  
Anurag K. Srivastava
Keyword(s):  
Data Processing ◽  
Test System ◽  
Mode Analysis ◽  
Data Detection ◽  
Complex Data ◽  
Data Set ◽  
Power Distribution System ◽  
Bad Data Detection ◽  
Processing Window ◽  
Bad Data

Distribution-level phasor measurement units (D-PMU) data are prone to different types of anomalies given complex data flow and processing infrastructure in an active power distribution system with enhanced digital automation. It is essential to pre-process the data before being used by critical applications for situational awareness and control. In this work, two approaches for detection of data anomalies are introduced for offline (larger data processing window) and online (shorter data processing window) applications. A margin-based maximum likelihood estimator (MB-MLE) method is developed to detect anomalies by integrating the results of different base detectors including Hampel filter, Quartile detector and DBSCAN. A smoothing wavelet denoising method is used to remove high-frequency noises. The processed data with offline analysis is used to fit a model to the underlying dynamics of synchrophasor data using Koopman Mode Analysis, which is subsequently employed for online denoising and bad data detection (BDD) using Kalman Filter (KF). The parameters of the KF are adjusted adaptively based on similarity to the training data set for model fitting purposes. Developed techniques have been validated for the modified IEEE test system with multiple D-PMUs, modeled and simulated in real-time for different case scenarios using the OPAL-RT Hardware-In-the-Loop (HIL) Simulator.

Sign in / Sign up

Export Citation Format

Share Document