Optimization study of dynamic emergency feeder bus paths with the sudden interruption of urban railway traffic

The rapid expansion of urban rail transit networks has increased their vulnerability to disruptions. When a metro line experiences sudden interruptions, it can severely reduce passenger mobility and degrade the overall transportation system performance. Existing bus feeder programs are often inadequate in responding effectively to dynamic and real-time fluctuations in passenger flow during such disruptions, particularly when combined with complex road traffic conditions. We propose a novel hybrid metaheuristic algorithm for the emergency feeder bus routes with time-window constraints to address this issue. The algorithm combines the Max-Min Ant System (MMAS) and Simulated Annealing (SA) to enhance search performance. A Back Propagation (BP) neural network estimates the emergency demand at each affected station, using historical and structural factors. These estimates are integrated into the hybrid optimization process, improving routing efficiency. The model aims to minimize the total operational time of emergency buses, ensuring timely evacuation. A case study using Beijing Metro validates the model’s effectiveness. Results indicate a 1.7-hour reduction in total passenger travel time and an 84.7% decrease in computation time compared to the Gurobi exact algorithm. These improvements facilitate the identification of optimal feeder paths under varying traffic conditions. The study provides practical guidance for enhancing emergency response strategies in metro systems.