Abstract
Most of the works that address the flowshop scheduling problem presume unlimited buffers between successive machines. However, with the advent of new technologies in the manufacturing systems, limited capacity storage between machines has become profitable. Aimed at makespan minimization, the flowshop scheduling problem with buffer constraints is NP-hard in the strong sense. Therefore, several approximate algorithms have been proposed in the literature. In this chapter, we propose an Estimation of Distribution Algorithm for solving a flowshop scheduling problem with buffer constraints. The main characteristics of the problem, such as the order of jobs and similar blocks of jobs in the sequence, are taken into account while building the probabilistic model. In order to enrich the search procedure of the algorithm, a skewed variable neighbourhood search algorithm is embedded into it, restricted by a calculated probability which depends on the quality of the created offspring. The computational results show that our algorithm outperforms genetic algorithm and particle swarm algorithm, and can obtain several optimal solutions in a short time.