Event-driven security-constrained unit commitment with component outage estimation based on machine learning method

Hurricanes can cause significant damages to the electric power systems and result in widespread and prolonged loss of electric services. A preventive scheduling of available resources in response to these events can be of significant importance in reducing the related undesirable aftermath. An Event-driven Security-Constrained Unit Commitment (E-SCUC), as discussed in this paper, can be used as a viable tool to schedule available grid resources in minimizing possible supply interruptions during component outages as a consequence of these events. An accurate estimation of the component outages, however, is of ultimate importance in ensuring a viable resource schedule. In this work, a machine learning method, based on regression and data mining, is proposed to model the power system components that can potentially fail during an anticipated extreme event. The proposed model is trained on artificial and historical data of storm-related damages, where the prediction is further used in the proposed E-SCUC problem. Numerical simulations on the standard IEEE 30-bus system in various hurricane path and intensity scenarios illustrate the effectiveness of the proposed model.