This paper presents the use of advanced simulation modeling to optimize the operation of a fully automated modular conveyor system in a large-scale warehouse. At its peak capacity, the smooth flow of material in the system was greatly impaired due to the appearance of bottlenecks. A full-scale 3D discrete event simulation (DES) model of the system was built and time-dependent statistical models were carefully designed and implemented in the model in order to capture the randomness and complex dynamics of the operation. The model was verified and validated, and several scenarios have been analyzed. The paper demonstrates a practical example of how data-driven simulation modeling provided a cost-effective solution to enhance efficiency. The paper highlights the crucial aspects that must be taken into account in the modeling of the system in order to create a reliable standalone decision support system. Moreover, the paper highlights the identified key steps that are yet to be taken from dynamical modelling towards a Digital Twin.