Genetic algorithm parameters selection based on optimal computing budget allocation method

The majority of large size job shop scheduling problem is non-polynomial-hard (NP-hard). In the past decades, GAs have demonstrated considerable success in providing efficient solutions to many NP-hard optimization problems. But there is no literature considers the optimal parameters when designing GAs. Unsuitable parameters may cause terrible solution for a specific scheduling problem. In this paper, we proposed a parameters selection algorithm based on optimal computing budget allocation method, which attempts find the fittest control parameters, namely, number of population, probability of crossover, probability of mutation, and then the fittest parameters are used in the GA for further more search operation to find optimal solution. We develop genetic parameters selection for large size job shop scheduling problem in order to validate the effectiveness and efficiency of the parameter decision method.