Digitally Empowered Dynamic Distribution Scheduling Model Development for the Tobacco Industry

This paper presents a digitally empowered dynamic distribution scheduling model tailored for the logistics needs of the tobacco industry. By integrating IoT technologies, ant colony optimization (ACO), and real-time data analytics, the model overcomes the inefficiencies of traditional static scheduling methods. Comparative experiments conducted at the Shijiazhuang Tobacco Company demonstrate significant performance improvements: distribution efficiency increased by 520.92%, vehicle utilization rose from 60.32% to 91.41%, and 54 delivery trips were saved per month. Furthermore, annual economic benefits reached $20,860 through reduced fuel and maintenance costs. These results affirm the model's effectiveness in improving logistics operations while reducing costs.