A simulation optimization framework for shipment planning at RDC considering time and quantity consolidation with uncertain demands

Shipment planning (SP) at regional distribution center (RDC) involves order consolidation and vehicle routing decisions under uncertain demands, which is generally very hard to be solved by traditional analytical methods such as mathematical programs. To cope with the complexity of this important problem existing in logistics systems, a general-purpose simulation optimization framework is proposed. Discrete-event simulation (DES) is employed to model the complicated shipping processes and capture the system's dynamics and uncertainties. A new policy (ID-policy) considering time and quantity consolidation is developed to improve consolidation effectiveness. The consolidated orders and system's performance obtained by simulation are then transformed as input into a genetic algorithm designed to optimize the vehicle routes via evolutionary computation. Experiment results show that the ID-policy outperforms traditional consolidation policies such as T-policy, Q-policy and D-policy under different conditions. The proposed simulation optimization framework is also validated by the exemplary case.