Enhancing Cyber Security in Power Sector using Machine Learning
R Prabhakaran1, S Asha2

1Prof. R. Prabhakaran, Assistant Professor (Senior) from the School of Computing Science and Engineering, VIT University, Chennai (Tamil Nadu), India.
2Dr. S. Asha, Associate Professor from the School of Computing Science and Engineering, VIT University, Chennai (Tamil Nadu), India.

Manuscript received on 03 July 2019 | Revised Manuscript received on 07 July 2019 | Manuscript published on 30 July 2019 | PP: 3382-3386 | Volume-8 Issue-9, July 2019 | Retrieval Number: I7860078919/19©BEIESP | DOI: 10.35940/ijitee.I7860.078919

Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Nowadays, our lives have become very much dependent on the power systems, whether it is in home or in offices or anywhere. Any failure in the power systems can bring our lives to a halt. To ensure no power fault, a continuous and remote monitoring, control and automation are needed. The implementation of constraints increases the efficiency of the power systems. But, to put monitoring, control and automation into practice we need network, and with this come the threat of cyber-attacks. With more open standard-based communication network, the automated power systems have become the target of the cyber-attacks. By exploiting the cyber components in networks, critical cyber components can be manipulated. Intruders can tamper the communication links by injecting false or modified data. To come up with security measures against these attacks, vulnerabilities of the power systems are being assessed to analyze the impacts of the cyber-attacks. Several techniques have been implemented so far to make the power systems less prone to threats. In this paper, technology like Machine Learning is used as anomaly discriminator and to provide security to the power system against the cyber threats.
Keywords: Smart Grid, SCADA, IEC 61850, Cyber-Attack, Security.

Scope of the Article: Machine Learning