Different uncertainties may arise in the transportation of orders. Especially for oversea deliveries, where weather conditions may change several times a day. Thus, managing it may be difficult, as, for example, the vessel lead time is not certain. This study investigates a different source of uncertainty, which is the waiting time for the next vessel that is scheduled on a specific route connecting two international ports.
The aim of this research was to determine the booking size for vessels in oversea delivery to minimize transportation costs. In the studied setting, a producer must book transportation space in advance, whereby the arrival processes for containers and vessels are stochastic. Analytical approaches of queueing theory were inconvenient in this case, and a discrete event simulation was therefore used to estimate the objective function.
Moreover, the booking size was optimized for a static and a simple dynamic booking policy using a discretization of the solution space. The simulation model and all the respective processes included in the oversea supply chain were developed in AnyLogic with a discrete-event paradigm. It allowed the researchers to define the waiting times for cars at the port and evaluate the respective waiting and booking costs. Some input parameters were defined based on empirical data.
The results showed that the higher the variance in the shipping cycle, the higher the optimal booking size and the total transportation costs were. The dynamic booking policy significantly outperformed the static policy and indicates potential for future research. Uncertainties in the delivery time of complex supply chain networks (or delivery networks) may occur at many nodes of the network. Future research could shed light on the interdependencies of uncertainties at several points in delivery networks.