A New Concept of Genetic Operators for Scheduling Problems

When a genetic algorithm (GA) is applied to scheduling problems, various crossovers and mutations can be applicable. We have to carefully select appropriate operators for constructing high performance GA, because GA performance depends on the choice of such operators as well as crossover and mutation probabilities. First, we present a new concept of genetic operators for scheduling problems. Then, we developed a software tool, called HybFlexGA, to examine the performance of various crossover and mutation operators by computing simulations of job scheduling problems. Finally, we applied in the HybFlexGA the best genetic operators obtained from our computational tests.