Files and links (1)
CC BY V4.0, Open Access
Thesis
DETECTING CYBER ATTACKS WITH PACKET LOSS RESILIENCE FORPOWER SYSTEMS
Washington State University
Master of Science (MS), Washington State University
01/2021
DOI:
https://doi.org/10.7273/000005400
Handle:
https://hdl.handle.net/2376/119190
Abstract
It's important to the continued operation of the power grid that power system managers have access to trustworthy and accurate data. Unfortunately, due to the possibility of spoof attacks on the Phasor Measurement Units (PMUs) that generate said data, the collected data may not match the true state of the grid, causing lasting damage to said grid if the falsified data is acted upon. To prevent this, spoof detection methods were developed using Machine Learning (ML) models that analyze PMU data streams to detect spoofed signals in a timely manner.Unfortunately, as with all data sent through a network, the data generated by the PMUs is subject to varying amounts of packet loss when in transit from the PMU to the Phasor Data Concentrator (PDC) for processing. Because of this, the data passed to the spoof detection methods in practice might contain variance that the ML model was not trained to account for, resulting in degraded performance or outright crashes from the spoof detection model when passed data that contains said packet loss.
In this thesis, the exact granular effects of packet loss on spoof detection models is quantified and examined. Several mitigation strategies are considered and recommended when dealing with packet loss in the data stream. Finally, a Dynamic Window Size Algorithm (DWSA) is developed to minimize the amount of packet loss the models are passed for each data point. The positive and negative effects of using DWSA to mitigate the effects of packet loss are also explored.
Metrics
29 File views/ downloads
30 Record Views
Details
- Title
- DETECTING CYBER ATTACKS WITH PACKET LOSS RESILIENCE FORPOWER SYSTEMS
- Creators
- Jonathan Reed Cavitt
- Contributors
- Xinghui Zhao (Advisor)Scott Wallace (Committee Member)Ben McCamish (Committee Member)
- Awarding Institution
- Washington State University
- Academic Unit
- School of Electrical Engineering and Computer Science
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University
- Number of pages
- 128
- Identifiers
- 99900592362901842
- Language
- English
- Resource Type
- Thesis