This paper proposes a novel rolling-horizon-based optimization framework for managing railway operations, which integrates dynamic train timetable rescheduling and rolling stock reassignment under uncertain disruption durations. Unlike existing approaches that assume fixed-duration disruptions, our method explicitly incorporates real-time uncertainty by enabling adaptive recovery strategies. These include resource schedule adjustments, service cancellations, short-turning, stop-skipping, and the strategic insertion of additional train services. The problem is formulated as a mixed-integer linear programming model that aims to minimize total delay, operational costs, penalties for cancellations, and costs related to slot planning for additional train services. The formulation respects a variety of operational constraints, including fleet feasibility and service continuity, enabling dynamic and feasible rescheduling. To overcome the computational challenges of real-time decision-making with gradually revealed disruption information, we develop an improved Benders decomposition (IBD) algorithm. The method decomposes the model into a master problem (rolling stock reassignment) and a subproblem (timetable rescheduling), and incorporates custom multi-optimality cuts within a rolling horizon framework to enhance convergence. For benchmarking, we also implement a two-stage sequential algorithm (TSA). Numerical experiments on the Beijing Batong metro line demonstrate that IBD significantly outperforms both TSA and commercial solvers in computational efficiency. Our approach provides practically viable solutions for railway operators facing uncertain disruptions, bridging the gap between theoretical models and real-world applicability.
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号