Optimization of Traffic Flow Operation Mode in Railway Hubs

Abstract

The optimization of traffic flow in railway hubs is a critical issue given the complexities and dynamic constraints inherent in these systems, where existing methods often prove inadequate, particularly in the effective coordination of heavy and empty vehicle flows. To address these limitations, a comprehensive optimization model was developed that integrates the coordination of heavy and empty vehicle flows within railway hubs, aiming to enhance overall operational efficiency and minimize costs. This study employs an artificial bee colony (ABC) algorithm enhanced by a logistic chaos map (LCMABC) to optimize the proposed model. The effectiveness of this method was validated using real-world data from a major railway hub, where the LCMABC algorithm successfully reduced the total operational costs by 5.02% compared with traditional ABC and 4.36% compared with Q-learning-based multi-strategy artificial bee colony (QMABC). Moreover, the algorithm demonstrated faster convergence and lower computational time across different problem sizes, with its advantage becoming more prominent in large-scale scenarios such as 100-vehicle and 150-vehicle scheduling. The experimental results show that the LCMABC algorithm significantly reduces overall operational costs while achieving a more balanced distribution of heavy and empty vehicles, thereby reducing vehicle waste and resource usage. These concrete findings support the conclusion that the LCMABC algorithm holds broad application potential for optimizing traffic flow in other large-scale transportation networks, contributing to more efficient and cost-effective railway operations.