Abstract
The guaranteed service model (GSM) computes optimal order-points in multi-echelon inventory control under the assumptions that delivery times can be guaranteed and the demand is bounded. Our new stochastic guaranteed service model (SGSM) with Recourse covers also scenarios that violate these assumptions. Simulation experiments on real-world data of a large German car manufacturer show that policies based on the SGSM dominate GSM-policies.
Highlights
Inventory control for a spare part distribution system follows two goals: deliver as promptly as possible to the end customer and minimize inventory costs
We introduce the new Stochastic Guaranteed Service Model (SGSM) with a non-trivial complete recourse consisting of a transportation option besides the penalty cost for non-sales, i.e., requested parts that cannot be delivered in time
We have introduced the Stochastic Guaranteed Service Model (SGSM), a stochastic programming version of the Guaranteed Service Model (GSM) for the computation of safety stock levels in a multi-echelon spare part distribution system of a large German car manufacturer
Summary
Inventory control for a spare part distribution system follows two goals: deliver as promptly as possible to the end customer and minimize inventory costs. Simulation results on real-world data of a large German automobile manufacturer and Poisson-distributed demand with real-world intensity forecasts show that our inventory policies based on the SGSM dominate GSM-policies and yield better results than the considered stochastic service time model. One reason for this is, among others, that the service level guarantees of the GSM do not take into account that non-sales can have quite different impact on the total cost, which depends on the particular part and on the number of parts missing. After the description of the simulation method and some computational results in section 4 we end with some conclusions
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have