Solving Distribute Flexible Flow Shop Scheduling Problem with an Imitation Learning Framework

This paper studies the distributed flexible flow shop scheduling problem (DFFSP), where the transportation time between different factories needs to be considered and each machine has a different startup time. A mixed integer linear programming (MILP) model of DFFSP is proposed, and a smart algorithm based on imitation learning for branch-and-bound (B&B) is used to find the scheduling plan that minimizes the total processing time. The graph convolutional neural network model is trained using imitation learning from strong branch expert rules. Finally, we demonstrate the efficiency of our algorithm with simulation experiments. The results indicate that our algorithm demonstrates the most efficient search performance with respect to both the number of nodes explored and search time compared to the four traditional B&B strategies.