Title: Computational intelligence applications to crisis management in power systems

Authors: Michael Negnevitsky

Addresses: Centre for Renewable Energy and Power Systems, University of Tasmania, Private Bag 65 Hobart, Tasmania, 7001, Australia

Abstract: In emergency conditions, power system operators deal with large amounts of data. Due to psychological stress, operators may not be able to adequately respond to critical conditions and make correct decisions. Mistakes can damage expensive power system equipment or worse lead to major emergencies. Intelligent systems can play an advisory role suggesting the necessary actions to be taken to deal with a given emergency as well as identifying failures of protection systems and circuit breakers. This paper outlines some experience obtained at the University of Tasmania in developing intelligent systems for power systems security. An expert system for clearing overloads applies the network sensitivity factors to reschedule power generation, reconfigure networks and shed loads. An expert system for voltage control is developed for detecting voltage violations and providing a set of control actions to solve voltage problems. Neural networks are used to identify multiple failures of protection and circuit breakers.

Keywords: computational intelligence; power systems; emergency conditions; crisis management; emergency management; psychological stress; decision making; protection systems; circuit breakers; protection system failure; circuit breaker failure; expert systems; network sensitivity; power generation rescheduling; network reconfiguration; load shedding; voltage control; neural networks; intelligent control; intelligent support.

DOI: 10.1504/IJAAC.2008.022180

International Journal of Automation and Control, 2008 Vol.2 No.2/3, pp.247 - 273

Published online: 22 Dec 2008 *

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