An Intelligent Optimization for the Vehicle Routing of Multi-commodity and Multi-trip Supply Chain Logistics in the Internet of Things

In the complex supply chain logistics environment, enterprises face core challenges such as multi-commodity transportation, multi-trip distribution planning, and supply chain stability maintenance. However, existing studies often fail to fully balance workload allocation equilibrium and dynamic coordination of supply chain Safety Inventory (SI) when addressing multi-commodity and multi-trip distribution issues, leading to practical operational problems such as cost fluctuations, low distribution efficiency, and inventory imbalance. Thus, achieving workload balance, optimizing vehicle routes, and setting appropriate SI are crucial for improving supply chain efficiency and stability. This study constructs a multi-commodity and multi-trip supply chain logistics vehicle routing optimization model considering SI and Workload Balance Constraint (WBC), and uses an Improved Ant Colony Optimization (IACO) for solution. Internet of Things (IoT) technology enables real-time inventory monitoring, data collection, and demand forecasting using historical data, supporting intelligent decision-making. SI is critical for supply chain stability; its proportion positively correlates with optimal cost, path length, and vehicle count, with specific dynamics analyzed in simulations. The WBC reduces total costs and overtime expenses, with larger scale scenarios (70 collection points) showing the most significant improvement (13.09% cost reduction). Taking some areas in Runan County, Zhumadian City as examples, the results verify the model’s comprehensiveness and the algorithm’s effectiveness.