Decision support system for inventory policies of complex distribution systems

In today's dynamic market, numerous dynamic influencing factors have seriously aggravated the difficulties of inventory planning of the complex distribution systems. This paper focuses on the decision support system for inventory policies of such complex distribution systems. This decision support system is based on the professional simulation tool OTD-NET, developed by Fraunhofer-Institute for Material flow and Logistics (IML). The special evolutionary algorithm NSGA-II is introduced in the simulation-based optimization model. They function like a black box, which accepts a set of values as the input parameters, and uses the performances collected from simulation to make decisions about the next selection. That means that the metaheuristics start from an initial solution, and then carry out an improving search guided by certain principles. Through comprehensively analyzing the KPIs (logistic service level and logistic costs) of this set of multiechelon inventory policies, their levels of robustness can be clearly ascertained. Based on the simulation results, a metaheuristic-based optimizer regenerates improved (more robust) multiechelon inventory policies, which are once again comprehensively and precisely evaluated through simulation. This closed feedback loop forms a simulation optimization process that enables the autonomous evolution of multiechelon inventory policies of complex distribution systems.