Queuing Models and Subspace Identification in Logistics

Abstract

In modern logistics it might be helpful to describe the behavior of a complex logistical process as well as to determine the strength of relations between certain parameters of the system. In this paper a subspace identification approach has been applied to estimate the relation between the features of the system based on measured input-output pairs. In order to validate the suitability of the approach for logistical processes a queuing based model has been proposed and used to generate simulation data. Our analysis as well as the obtained results clearly reflect that subspace identification approaches can advantageously be applied to model the relation between certain parameters of the system, nevertheless to characterize the strength of this relation, as well.