A cooperative coevolutionary algorithm with application to job shop scheduling problem

An improved cooperative coevolutionary algorithm, which aims at solving job shop scheduling problem, is proposed in this paper. According to the number of machines, population is naturally divided into some subpopulations whose individuals encode the preference list of jobs. The proposed algorithm introduces steady-state reproduction to crossover and mutation operators, and inserts some new individuals to the subpopulation at some other generations, and uses the improved preference-list-based G&T algorithm to decode the whole solutions to calculate fitness by three types of cooperative partners, and adopts an innovative updating technique to speed up the convergence. The optimization results of numerical experiments have shown that, the proposed algorithm has outperformed traditional genetic algorithms and showed strong competition with other heuristics.