I-DCOP: Train Classification Based on an Iterative Process Using Distributed Constraint Optimization

This paper presents an iterative process based on Distributed Constraint Optimization (I-DCOP), to solve train classification problems. The input of the I-DCOP is the train classification problem modelled as a DCOP, named Optimization Model for Train Classification (OMTC). OMTC generates a feasible schedule for a train classification problem defined by the inbound trains, the total of outbound trains and the cars assigned to them. The expected result, named feasible schedule, leads to the correct formation of the outbound trains, based on the order criteria defined. The OMTC also minimizes the schedule execution time and the total number of roll-ins (operation executed on cars, sometimes charged by the yards). I-DCOP extends the OMTC including the constraints of limited amount of classification tracks ant their capacity. However, these constraints are included iteratively by adding domain restrictions on the OMTC. Both OMTC and I-DCOP have been measured using scenarios based on real yard data. OMTC has generated optimal and feasible schedules to the scenarios, optimizing the total number of roll-ins. I-DCOP solved more complex scenarios, providing sub-optimal solutions. The experiments have shown that distributed constraint optimization problems can include additional constraints based on interactively defined domain