Maintenance scheduling optimization using a genetic algorithm (GA) with a probabilistic fitness function

Preventive maintenance scheduling of generating equipment is an important task in an electric power system. Removal from service of generating units for maintenance will reduce the available capacity and increase the system risk. Maintenance requests, therefore, in both vertically integrated and deregulated power systems, must be carefully coordinated. This article uses the genetic algorithm optimization technique to maximize the overall system reliability for a specified future time period in which a number of generating units are to be removed from service for preventive maintenance. The system reliability is assessed using the well-being approach in which an accepted deterministic criterion is embedded in a probabilistic approach that incorporates the uncertainty in demand and generating unit unavailabilities.