Optimizing a Vendor Managed Inventory (VMI) Model Considering Delivering Cost in a Three-echelon Supply Chain Using Two Tuned-parameter Meta-heuristics

In the retailer-supplier partnerships, the vendor-managed inventory (VMI) is one of the important policies in the supply chain management (SCM) to reduce the bullwhip effect. As there is a lack of study on the central warehouse via delivering cost in VMI literature, this paper presents a vendor-managed inventory (VMI) model in SCM including single-vendor, multi-retailer, and single-warehouse. While the vendor confronts with two constraints, namely the number of orders and budget, the purpose of this research is to find order size, the shortest possible route, and replenishment frequencies for the vendor and the retailers to minimize the total inventory cost. As the proposed model is an NP-hard problem, a meta-heuristics namely particle swarm optimization (PSO) is employed to optimize the proposed model. Since there is no available benchmark for evaluation of the proposed method, a genetic algorithm (GA) is used to validate and verify the solution presented by PSO. Moreover, Taguchi method in the design of experiments calibrates the parameters of the algorithm to provide the reliable solution. Finally, the conclusion and further studies are presented.

Inventory Model; Delivering Costs; Tuned-parameter Particle Swarm Optimization (PSO); Tuned-parameter Genetic algorithm (GA); Central Warehouse