Thesis
Defending against adversarial attacks in electric power systems: a machine learning approach
Washington State University
Master of Science (MS), Washington State University
2019
Handle:
https://hdl.handle.net/2376/107160
Abstract
Phasor measurement units (PMUs) provide high-fidelity situational awareness of electric power grid operations. PMU data are used in real-time to inform wide area state estimation, monitor area control error, and event detection. As PMU data becomes more reliable, these devices are finding roles within control systems such as demand response programs and early fault detection systems. As with other cyber physical systems, maintaining data integrity and security are significant challenges for power system operators. In this thesis, we present a comprehensive study of multiple machine learning techniques for detecting malicious data injection within PMU data streams. Our results show that both SVM and ANN are generally effective in detecting spoofed data using signal correlations, and TensorFlow, the open source machine learning library, demonstrates potential for distributing the training workload and achieving higher performance. We also developed a competent second-wise LSTM model based on raw signals which increases the detection granularity to seconds. We expect these results to shed light on future work of adopting machine learning and data analytics techniques in the electric power industry.
Metrics
23 File views/ downloads
18 Record Views
Details
- Title
- Defending against adversarial attacks in electric power systems
- Creators
- Jun Jiang
- Contributors
- Xinghui Zhao (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525002001842
- Language
- English
- Resource Type
- Thesis