Train delays can significantly impact the punctuality and service quality of high‐speed trains, which also play a crucial role in affecting dispatchers with their decision‐making. In this study, a data‐driven train delay prediction framework was proposed and strengthened by considering the impact of dispatching commands and the mechanisms of train delay propagation using XGBoost. Four metaheuristic algorithms were utilized to fine‐tune its hyperparameters. A vast dataset comprising 1.9 million records spanning 38 months of train operation data was utilized for feature extraction and model training. The model's accuracy was evaluated using three statistical metrics, and a comparison of the four tuning frameworks was performed. To emphasize the model's interpretability and its practical guidance for train rescheduling, the relationship of dispatching commands, delay propagation and delay prediction was validated by combining the theory and practical results, and a SHAP (SHapley Additive exPlanations) analysis was used for a clearer model explanation. The results revealed that distinct XGBoost‐Metaheuristic models exhibit unique effects in different criteria, yet they all demonstrated high accuracy and low prediction errors, thereby revealing the potential of using machine learning for train delay prediction, which is valuable for decision‐making and rescheduling.
Enhancing the resilience of train timetables can effectively improve their resistance and recovery capabilities against operational disturbances, thereby ensuring the stable operation of the railway system and the quality of passenger transportation services. This paper defined timetable resilience as three parts: disturbance absorptive capacity, resistance capacity, and post-disturbance recovery capacity. These capacities were quantitatively evaluated using the buffer time of trains, the number of train delays at departures and arrivals, and the duration of delay state. The evaluation metrics of the three resilience capacities and the total travel time of trains were used as the objective to establish a spatiotemporal network model. Utilizing actual operational data from the Beijing–Shanghai high-speed railway in China, the model was validated through a case study. Sensitivity analysis of the model's key parameters was conducted under two experimental scenarios: routine operational disturbances and speed restrictions on specific sections. Results showed that our model can effectively reduce the delay time and the number of delays in both the routine operational disturbance scenario and the 300 km/h speed restriction scenario with a frequent disturbance value of 2 min. Moreover, the model's performance with 3-min frequent disturbance outperformed that with 2-min frequent disturbance in speed restriction at 250 km/h and 200 km/h, yielding a 30% improvement.
22 November 2023 in Quantum Information Processing
Timetable scheduling is a combinatorial optimization problem that presents formidable challenges for classical computers. This paper introduces a pioneering methodology for addressing the high-speed train timetabling problem through quantum computing. Initially, a comprehensive binary integer programming model, grounded in the space–time network, is proposed (M1). To manage the intricacy of model M1, a knapsack problem reformulation is employed to establish a simplified binary integer programming model (M2). Both M1 and M2 are subsequently converted into quadratic unconstrained binary optimization (QUBO) models to harness the potential of quantum computing. Several techniques, including the Gurobi solver, simulated annealing, and the coherent Ising machine (CIM) quantum simulator, are deployed to solve the model across four distinct scenarios of varying complexity. The findings indicate that CIM quantum simulator outperforms the simulated annealing method in terms of solution quality for medium-scale problems.
As the development of High-Speed Railways (HSRs) shifts from scale expansion to quality and efficiency, high-density timetables face increasing challenges regarding operational stability. Traditional capacity metrics often prioritize volume over service quality, neglecting the economic and service implications of delays. To reconcile theoretical capacity with practical reliability, this paper proposes a novel Reliable Value (RV)-oriented framework for HSR timetabling. We construct a Reserve Capacity Incremental Heuristic Optimization Framework that employs a synergetic integrated stochastic optimization strategy. This methodology treats reserve capacity as a systematically varied analytical parameter rather than a static constant, integrating redundancy layout planning with dynamic recovery adjustments under stochastic delay scenarios. The RV metric quantitatively combines efficiency (Expected Running Time) and robustness (Indirect Capacity Loss). A case study on the Beijing–Shanghai high-speed railway corridor demonstrates a non-linear relationship between reserve capacity allocation and system value. The results identify an optimal saturation interval of 5 to 14 min, where the marginal gains in reliability maximize the overall system value without excessively compromising operational efficiency. These findings provide theoretical support for transitioning from static capacity planning to proactive, value-based resilience engineering through optimized redundancy allocation.
The distribution of limited timetable slack shapes delay propagation on high-speed railway corridors, but incorporating fine-grained historical disturbance evidence into event-level allocation decisions remains challenging. This study proposes a predict-then-optimize framework for reallocating running, dwell, and headway slack to strengthen planned-timetable resilience. The prediction stage uses a LightGBM-based multi-threshold model to learn the disturbance exceedance probabilities from historical operations. These probabilities are transformed into normalized coefficients representing the utility of running-time supplement. The optimization stage incorporates the learned utility in a budget-constrained slack allocation model with timetable-deviation control, solved by an ALNS-MILP approach. The proposed predict-then-optimize framework is evaluated on a full-day Beijing-Shanghai HSR timetable with 4197 scheduled events under 120 disturbance scenarios. Reallocating rather than increasing slack reduces total event delay by 36.73% and cross-train secondary delay by 39.77%. The improvements remain consistent and statistically significant across weighting schemes, disturbance types, and strengths. By turning historical operating evidence into event-level absorption value, the framework redesigns resilient timetables where slack matters most.