What is it about?
Identify false data injection attacks from PMU packet data streams Features are extracted from the PMU buffer to train multiple deep machine learning models This paper is concerned with a class of false data injection attacks (FDIA) which aim to modify PMU measurements resulting in incorrect state estimation solutions. We extract multi-variate time-series signals from PMU data packets aggregated in phasor data concentrators (PDC) corresponding to different events such as line faults and trips, generation and load fluctuations, shunt disconnections and FDIA prior to every cycle of state estimation (SE). A Convolutional Neural Network (CNN) data filter with Nesterov Adam gradient descent and categorical cross entropy loss is proposed to validate the PMU data. This filter extracts inter time-series relationships to classify different power system events by comparing the temporal structure of PMU packet data. The performance of the filter is then compared with (a) deep learning algorithms such as Recurrent Neural Networks (RNN) and Long Short Term Memory (LSTM) and (b) traditional classifiers such as SVM and ensemble methods. It is seen that the proposed CNN-based filter results in higher classification accuracies among all classifiers. This makes the CNN classifier suitable to serve as an independent data filter to identify falsified data streams targeted to alter SE. In order to verify the accuracy of the proposed filter, a hybrid state estimator (HSE) has been used in this study which obtains measurements from both PMU and traditional meters.
Photo by sterlinglanier Lanier on Unsplash
Why is it important?
Serve as an independent data filter to identify falsified data streams prior to each cycle of State Estimation Early warning system
Read the Original
This page is a summary of: Packet-data anomaly detection in PMU-based state estimator using convolutional neural network, International Journal of Electrical Power & Energy Systems, May 2019, Elsevier, DOI: 10.1016/j.ijepes.2018.11.013.
You can read the full text:
A PMU-Based Data-Driven Approach for Classifying Power System Events Considering Cyberattacks
Transient event identification is essential for power system operation and situational awareness. The increased penetration of the high sampling frequency phasor measurement units (PMUs) enables using PMU data to analyze power system events, and thus enhances power system visualization, monitoring and control. At the same time, the risks associated with cyberattacks on power systems increase. A malicious cyberattack on PMUs, aiming at generating fake transient data, may lead to incorrect actions that jeopardize system reliability. Therefore, it is critical to distinguish between fake data and real data when analyzing transient events. Utilizing PMU measurements, this article develops a data-driven approach, based on text-mining methodologies, for classifying transient events and identifying fake events caused by false data attacks. The developed methodology provides credible information regarding the cause of various events, and facilitates postevent decision-making to prevent potential cascading failures. Case studies, performed on the IEEE 30-bus and IEEE 118-bus systems, show that the developed approach is efficient in classifying false data and identifying different transient events regardless of the system topology, loading conditions, or the placement of PMUs.
The following have contributed to this page