Stability-oriented Optimization of Train Platforming Problem on High Speed Railway

To improve the interaction between train platforming plan (TPP) and train schedule, as well as improve the stability of TPP, this paper proposes a set partition based integer programming model, which excludes the station resource compatible constraints. The objective of the model is to minimize the gap between TPP and fixed usage schemes of platforms, while improves the stability of train schedule by making the headway times among potential conflicting tasks as rational as possible. The paper also presents an ant colony solution algorithm with consideration of problem specifics. Finally, some experiments in the background of Changsha South Railway Station of China are conducted to analyze the parameter and to examine the effectiveness of the proposed solution approach. Results show that the stability of the TPP solutions obtained through the proposed model could be improved by 37% (with an extra 29% resource cost) compared to the traditional models which only focus on optimizing resource utilization.

摘要从高速公路车辆出入口数据中可以直接提取路网中车辆的OD信息，这些信息可以从一定程度上反映出车辆在时空上的运行状态，更可以通过这类数据对高速公路出口流量的未来趋势做出合理有效地预测。本研究从真实数据出发，对交通路网中车辆OD的稳定性进行了分析，并以此为指导，将所得到的领域知识加入到常规的预测方法中，提出了一套基于OD稳定模式的高速公路出口流量预测方法。主要贡献包括：（1）提出了信息熵的概念,以刻画高速公路车辆OD的规律性；（2）提出了基于OD的稳定模式的出口流量预测方法；（3）在大量真实的数据上进行了实验分析。