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

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