Machine learning algorithm for detection of false data injection attack in power system

Kumar, Ajit, Saxena, Neetesh ORCID: https://orcid.org/0000-0002-6437-0807 and Choi, Bong Jun 2021. Machine learning algorithm for detection of false data injection attack in power system. Presented at: 35th International Conference on Information Networking (ICOIN 2021), Jeju Island, Korea, 13-16 January 2021. Proceedings of the 2021 International Conference on Information Networking. IEEE, pp. 385-390. 10.1109/ICOIN50884.2021.9333913

Preview

PDF - Accepted Post-Print Version Download (238kB) | Preview

Abstract

Electric grids are becoming smart due to the integration of Information and Communication Technology (ICT) with the traditional grid. However, it can also attract various kinds of Cyber-attacks to the grid infrastructure. The False Data Injection Attack (FDIA) is one of the lethal and most occurring attacks possible in both the physical and cyber part of the smart grid. This paper proposed an approach by applying machine learning algorithms to detect FDIAs in the power system. Several feature selection techniques are explored to investigate the most suitable features to achieve high accuracy. Various machine learning algorithms are tested to follow the most suitable method for building a detection system against such attacks. Also, the dataset has a skewed distribution between the two classes, and hence data imbalance issue is addressed during the experiments. Moreover, because the response time is critical in a smart grid, each experiment is also evaluated in terms of time complexity.

Item Type:	Conference or Workshop Item (Paper)
Date Type:	Published Online
Status:	Published
Schools:	Schools > Computer Science & Informatics
Publisher:	IEEE
ISBN:	978-1-7281-9102-7
Date of First Compliant Deposit:	20 January 2021
Date of Acceptance:	18 November 2020
Last Modified:	14 May 2025 14:56
URI:	https://orca.cardiff.ac.uk/id/eprint/136670

Citation Data

Cited 7 times in Scopus. View in Scopus. Powered By Scopus® Data

Actions (repository staff only)

Edit Item