Institute for Software Research
School of Computer Science, Carnegie Mellon University
Agent-based Modeling and Simulation for an
John Villarraga*, Kathleen M. Carley, John Wassick**, Nikolaos Sahinidis*
Center for the Computational Analysis of Social and Organizational Systems
This paper presents a study on the Order-To-Cash process of a supply chain using agent-based modeling. Supply chains are composed of multiple decision makers where each of them play an important role in the entire system. If one of the variables controlled by these entities malfunctions, this can significantly increase a customer’s order fulfillment time. This study investigates organizational issues of a supply-chain and presents solutions by conducting a variety of experiments using NetLogo. Results show that the performance of the model is affected by a large volume of orders due to errors and exceptions that occur throughout the simulation. We also found that our system contains bottlenecks that cause significant amount of delays in the model. Our analysis demonstrates that in some scenarios hiring new individuals where there is a bottleneck could greatly increase the efficiency of the model. Moreover, hiring new people on the same role proved to be more relevant than investing in training of individuals as the agents of the model improve their efficiency in the simulation run.
*Department of Chemical Engineering, Carnegie Mellon University