An alternating direction method of multipliers for optimizing (s, S) policies in a distribution system with joint replenishment volume constraints

• Published in: Omega (Oxford) Vol. 116; p. 102800
• Main Authors: Dai, Bo, Chen, Haoxun, Li, Yuan, Zhang, Yidong, Wang, Xiaoqing, Deng, Yuming
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.04.2023; Elsevier
• Subjects: (s, S) policy; Computer Science; Distribution system; e-commerce; Inventory management; Joint replenishment; Operations Research; Scenario optimization; Inventory management; e-commerce; Scenario optimization; Joint replenishment; (s, S) policy; Distribution system; (s;S) policy
• ISSN: 0305-0483; 1873-5274
• DOI: 10.1016/j.omega.2022.102800

•A distribution system of Alibaba with joint replenishment volume constraints considered•A scenario-based model for optimizing (s, S) policies in the system formulated•An alternating direction method of multipliers proposed to solve the model•The scenario optimization approach can reduce costs and improve fill rates of this system In this paper, we study a two-echelon distribution system in which multiple products are jointly replenished at each stocking location and the inventory of each product at each location is controlled by an (s, S) policy. The transportation capacity in volume of products for each joint replenishment is limited, and linear rationing policies are used for both on-hand inventory and transportation capacity allocation in the system in case of shortage. We propose a novel scenario-based model for the optimization of the (s, S) policies in the system that considers the rationing policies. Because of its high complexity when the number of scenarios is large, an Alternating Direction Method of Multipliers is proposed to solve the model. Based on real data, forty instances were generated and tested to evaluate the model and the solution method. Our numerical experiments show that for these instances this method could find a better solution in a much shorter computation time compared with CPLEX 12.9, whereas the latter often runs out of memory for large-size instances on a personal computer. Moreover, the inventory policies found by this scenario-based optimization approach can reduce costs by 5.1% and improve fill rates by 9.7% on average compared with those currently used in Alibaba.