Title: Rapid anomaly detection for smart grid infrastructures through hierarchical pattern matching

Authors: Zubair A. Baig

Addresses: Department of Computer Engineering, King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia

Abstract: The Smart Grid Infrastructure has emerged as a necessary and critical platform for provisioning intelligent and accurate services to consumers of the electric grid, in recent times. The need for securing the same from malicious attempts by the adversary class to disrupt routine operations cannot be understated. In this paper, a brief description of various types of malicious attacks against the SGI is presented. Secondly, two light-weighted pattern matching techniques for detecting anomalous behaviour of the smart grid devices are elaborated upon. The single-layer pattern matching scheme operates as one module within each level of the SGI hierarchy, with bottom-up communications taking place for pattern exchange, reconstruction and holistic visualisation of the SGI state. The multi group-based scheme operates as c clusters individually reconstructing patterns, and communicating with corresponding SGI devices one level above. The proposed schemes were found to impose minimal overhead in terms of communication and storage needed.

Keywords: smart grid communications; network security; attack modelling; pattern recognition; anomaly detection; grid infrastructures; pattern matching; electricity grid; malicious attacks; power distribution; electricity networks.

DOI: 10.1504/IJSN.2012.050025

International Journal of Security and Networks, 2012 Vol.7 No.2, pp.83 - 94

Published online: 24 Oct 2012 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article