Machine Learning-based Cybersecurity Defence of Wide-area Monitoring Systems
Paper
Paper/Presentation Title | Machine Learning-based Cybersecurity Defence of Wide-area Monitoring Systems |
---|---|
Presentation Type | Paper |
Authors | He, Qian, Bai, Feifei, Cui, Yi and Zillmann, Matthew |
Journal or Proceedings Title | Proceedings of 2022 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) |
Number of Pages | 6 |
Year | 2022 |
Publisher | IEEE (Institute of Electrical and Electronics Engineers) |
Place of Publication | China |
Digital Object Identifier (DOI) | https://doi.org/10.1109/ICPSAsia55496.2022.9949686 |
Web Address (URL) of Paper | https://ieeexplore.ieee.org/abstract/document/9949686?casa_token=Ku58kQoBB2kAAAAA:IAGZ26abp3IqLNmlQnSgVkqD4zRz3UC3nH2jy41tivedPDawuTavhWCpkLQL9hzotSMxuIJHjuI |
Web Address (URL) of Conference Proceedings | https://ieeexplore.ieee.org/xpl/conhome/9948701/proceeding |
Conference/Event | 2022 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) |
Event Details | 2022 IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) Parent IEEE/IAS Industrial and Commercial Power System Asia (I&CPS Asia) Delivery In person Event Date 08 to end of 11 Jul 2022 Event Location Shanghai, China |
Abstract | Due to the vulnerability of the wide-area monitoring systems (WAMS) communication, malicious data integrity attacks on WAMS records could be initiated by adversaries which may lead to disastrous events. In response to the cybersecurity challenges raised by WAMS, recently some machine learning-based methods have been developed to authenticate the source information of WAMS measurements. Most existing source authentication methods are designed for authenticating WAMS data from a small number of locations at a large geographical scale which may not reflect the complete operating condition of WAMS in practical networks. This paper aims to examine the feasibility of using machine learning-based methods to achieve reliable source authentication of WAMS measurements for practical power grids. Four "state-of-the-art" machine learning-based approaches (including both shallow learning and deep learning methods) are examined and their performance is compared using real-life data collected from a significantly large number of locations at a small geographical scale. The simulation results demonstrate that the continuous wavelet transforms - convolution neural network (CWT-CNN) based model outperforms other algorithms due to its high identification accuracy and low computational time which has the potential to be applicable for real-time data source authentication of smart grids. |
Keywords | Source authentication; machine learning; cybersecurity; PMU |
ANZSRC Field of Research 2020 | 400803. Electrical energy generation (incl. renewables, excl. photovoltaics) |
460308. Pattern recognition | |
460403. Data security and protection | |
Public Notes | File reproduced in accordance with the copyright policy of the publisher/author. |
Byline Affiliations | University of Queensland |
Griffith University | |
Energy Queensland, Australia |
https://research.usq.edu.au/item/x8zv8/machine-learning-based-cybersecurity-defence-of-wide-area-monitoring-systems
Download files
49
total views39
total downloads5
views this month1
downloads this month