A new method for hybridizing metaheuristics for multi-objective flexible job shop scheduling

Flexible job shop scheduling problem (FJSP) is an important extension of the classical job shop scheduling problem, where each operation could be processed on more than one machine and vice versa. Since it has been proven that this problem is strongly NP-hard, it is difficult to achieve an optimal solution with traditional optimization algorithms. In this paper a new approach is proposed to solve the multi-objective FJSP. This new approach has three steps. First, an initial population of feasible solutions with good distribution in the search space is created by using a parameter called neighborhood. Second, this population, based on fitness and neighborhood parameters, explores the search space until it will form several dynamic clusters around good areas, including local optimums. Finally, in parallel, a local search is performed on the best solution for each cluster by using Tabu Search algorithm and eventually the optimal solution is obtained among them. Computational results on benchmark problems show that the optimal solutions are obtained much faster than other approaches.