Metaheuristic-Based Supply Chain Network Optimization and Inventory Management Using Ant Colony Algorithm

Abstract

Integrating ant colony algorithms in supply chain network optimization and inventory management provides a new approach to improving efficiency and reducing costs. The global search capability of the algorithm is utilized to optimize the supply chain network to minimize total costs and improve service levels. The strategy of dynamically adjusting inventory levels based on demand forecasts and the ACO algorithm solves the inventory management problem, aiming to achieve customer demand fulfillment and inventory cost reduction. The approach's effectiveness was validated through case study simulations, which significantly improved over traditional optimization methods. Supply chain optimization efficiency increased by 20%, inventory cost was reduced by 10%, and response time was accelerated to 1 day. These results highlight the ACO algorithm's practical applicability and potential advantages in supply chain management. This study contributes to the theoretical framework of supply chain management and provides innovative solutions for companies to achieve more efficient supply chain operations.