COMBINED USE OF UNSUPERVISED AND SUPERVISED LEARNING FOR DYNAMIC SECURITY ASSESSMENT

It is highly desirable that we be able to assess the security and stability of electric power systems after exposure to large disturbances. In this connection, the critical clearing time(CCT) is an attribute which provides significant information about the quality of the post-fault system behavior. It may be regarded to be a complex mapping of the prefault, fault-on, and post-fault system conditions into the time domain. In previous work, we have shown that a feedforward neural-network can be used to learn this mapping and successfully perform under variable system operating conditions and topologies. In that work we described the system in terms of some conventionally used parameters. In contrast to using those pragmatic features selected on the basis of the engineering understanding of the problem, we consider in this paper the possibility of using unsupervised and supervised learning paradigms to discover what combination of "raw" measurements are significant in determining CCT. Correlation analysis and Euclidian metric are used to specify inter-feature dependencies. An example of 4-machine power system is used to illustrate the suggested approach.