A new algorithm for flexible job-shop scheduling problem based on particle swarm optimization

Abstract

This paper proposes a new algorithm, named EPSO, for solving flexible job-shop scheduling problem (FJSP) based on particle swarm optimization (PSO). EPSO includes two sets of features for expanding the solution space of FJSP and avoiding premature convergence to local optimum. These two sets are as follows: (I) particle life cycle that consists of four features: (1) courting call—increasing the number of more effective offspring (new solutions), (2) egg-laying stimulation—increasing the number of offspring from the better parents (current solutions), (3) biparental reproduction—increasing the diversity of the next generation (iteration) of solutions, and (4) population turnover—succeeding the population (the current set of all solutions) in the previous generation by a population in a new generation that is as able but more diverse than the previous one; and (II) discrete position update mechanism—moving particles (solutions) towards the flight leader (the best solution), namely, interchanging some integers in every solution with those in both the best solution and itself, using similar swarming strategy as the update procedure of the continuous PSO. The basic objective function used was to minimize makespan which is the most important objective, hence, providing the simplest way to measure the effectiveness of the generated solutions. Benchmarking EPSO with 20 well-known benchmark instances against two widely-reported optimization methods demonstrated that it performed either equally well or better than the other two.