Searching for just a few words should be enough to get started. If you need to make more complex queries, use the tips below to guide you.
Article type: Research Article
Authors: Wang, Chunyea | Sun, Jiana; * | Xu, Xiaoxina | Zou, Bina | Zhang, Minb | Tang, Yangb | Zeng, Minb
Affiliations: [a] School of Electronic and Information Engineering, Southwest University, Chongqing, P. R. China | [b] State Grid Chongqing Electric Power Company, Chongqing, P. R. China
Correspondence: [*] Corresponding author. Jian Sun, School of Electronic and Information Engineering, Southwest University, Beibei District, Chongqing, P. R. China. E-mail: [email protected].
Abstract: The denial-of-service (DoS) attacks block the communications of the power grids, which affects the availability of the measurement data for monitoring and control. In order to reduce the impact of DoS attacks on measurement data, it is essential to predict missing measurement data. Predicting technique with measurement data depends on the correlation between measurement data. However, it is impractical to install phasor measurement units (PMUs) on all buses owing to the high cost of PMU installment. This paper initializes the study on the impact of PMU placement on predicting measurement data. Considering the data availability, this paper proposes a scheme for predicting states using the LSTM network while ensuring system observability by optimizing phasor measurement unit (PMU) placement. The optimized PMU placement is obtained by integer programming with the criterion of the node importance and the cost of PMU deployment. There is a strong correlation between the measurement data corresponding to the optimal PMU placement. A Long-Short Term Memory neural network (LSTM) is proposed to learn the strong correlation among PMUs, which is utilized to predict the unavailable measured data of the attacked PMUs. The proposed method is verified on an IEEE 118-bus system, and the advantages compared with some conventional methods are also illustrated.
Keywords: Integer linear programming, DoS attacks, deep learning, state prediction
DOI: 10.3233/JIFS-212593
Journal: Journal of Intelligent & Fuzzy Systems, vol. 42, no. 6, pp. 5957-5971, 2022
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
USA
Tel: +1 703 830 6300
Fax: +1 703 830 2300
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
IOS Press
Nieuwe Hemweg 6B
1013 BG Amsterdam
The Netherlands
Tel: +31 20 688 3355
Fax: +31 20 687 0091
[email protected]
For editorial issues, permissions, book requests, submissions and proceedings, contact the Amsterdam office [email protected]
Inspirees International (China Office)
Ciyunsi Beili 207(CapitaLand), Bld 1, 7-901
100025, Beijing
China
Free service line: 400 661 8717
Fax: +86 10 8446 7947
[email protected]
For editorial issues, like the status of your submitted paper or proposals, write to [email protected]
如果您在出版方面需要帮助或有任何建, 件至: [email protected]