SCHEDULING OF SERIAL MULTIPRODUCT BATCH PROCESSES VIA SIMULATED ANNEALING

We present an in-depth study of the simulated annealing approach to the scheduling of serial multiproduct batch processes under the assumption of a permutation schedule. Four versions of the simulated annealing algorithm are studied based on two move acceptance criteria, the Metropolis algorithm and the Glauber algorithm, and two annealing schedules, the exponential schedule and the Aarts and van Laarhoven schedule. Makespan minimization is performed for unlimited intermediate storage (UIS), no intermediate storage (NIS), zero wait (ZW), finite intermediate storage (FIS) and mixed intermediate storage (MIS) flowshop problems using simulated annealing and also the idle matrix search (IMS) heuristic. Of the four versions of the simulated annealing algorithm studied, the Metropolis algorithm with the Aarts and van Laarhoven annealing schedule is found to give the best results, with all four versions giving significantly better results than the IMS heuristic. The Metropolis algorithm with the Aarts and van Laarhoven annealing schedule is studied in more detail for further comparison with the IMS heuristic in terms of the computational effort expended by the simulated annealing algorithm and the solution quality obtained.