Lotsizing and scheduling on parallel machines with sequence-dependent setup costs

Industrial lotsizing and scheduling pose very difficult analytical problems. We propose an unconventional model that deals with sequence-dependent setup costs in a multiple-machine environment. The sequence-splitting model splits an entire schedule into subsequences, leading to tractable subproblems. An optimization approach based on a column generation/branch and bound methodology is developed, and heuristically adapted to test problems including five real-world problem instances gathered from industry.