Bi-Objective Subway Timetable Optimization Considering Changing Train Quality Based on Passenger Flow Data

The chapter focuses on the bi-objective optimization of subway timetables, considering the dynamic changes in train quality based on passenger flow data. It introduces a novel approach that uses actual passenger demand to optimize train arrival and departure times, making the calculation of energy consumption more accurate. The study presents a comprehensive bi-objective optimization model and employs the elitist non-dominated sorting genetic algorithm (NSGA-II) to solve the problem. A case study on Fuzhou Metro Line 1 demonstrates the effectiveness of the model, resulting in significant reductions in passenger waiting time and energy consumption. The chapter highlights the importance of considering real-time passenger data in subway timetable optimization and provides a practical framework for improving the efficiency and sustainability of subway systems.