Supply chain network design: an MILP and Monte Carlo simulation approach

• Autor(a) principal: Bhowmik, Oyshik
• Data de Publicação: 2024
• Outros Autores: Parvez, Shohel
• Tipo de documento: Artigo
• Idioma: eng
• Título da fonte: Brazilian Journal of Operations & Production Management (Online)
• Texto Completo: https://bjopm.org.br/bjopm/article/view/1936
• topic: Supply Chain Network; Supply Chain Network Design; Mixed Integer Linear Programming; Monte Carlo Simu-lation; Demand Uncertainty

Goal: This study aims to minimize the total cost of a supply chain network and determine the optimal product flow under demand uncertainty. Design / Methodology / Approach: A mathematical model is presented to minimize the total supply chain cost by identifying the optimal facility locations and product flows. The applicability of the proposed model is evaluated through a real-life case study of a multinational sporting goods retailer with sensitivity analysis. Moreover, Monte Carlo simulation is used to capture the demand uncertainty and test the robustness of the model. Results: The minimized cost is achieved with optimal facility locations and product flows. The optimal result shows a 3% reduction in the total cost, making it the most robust solution under demand uncertainty. Limitations of the investigation: The proposed model is only applicable to a single-commodity supply chain network. In addition, the cost components of the network are limited to facility costs and transportation costs, disregarding the other cost components. Practical implications: This research demonstrates a methodology that can be used as a decision support system by managers to make strategic and tactical decisions in a supply chain network when demand is uncertain. Originality / Value: The MILP and simulation techniques used together to construct a three-tiered supply chain under uncertainty receive little attention in the literature. In addition to developing a novel three-echelon MILP model, this research makes use of a real-world case study to illustrate the methodology's performance in the context of demand uncertainty through simulation.