Stochastic model for the real-time train rescheduling

Abstract

The article explores the problem of train rescheduling based on the actual situation. The proposed stochastic model uses specific distributions of operating times which are dependent on the current traffic conditions. The arrival time distribution is considered as a result of adjusting the train trajectory by speed control. The results of modelled arrival distributions correspond well with the experimental data received at the russian railways. The proposed model is used for prevention of sequence-of-trains conflicts and violations of connections. The basis of deviation prediction is two-train model of mesalevel which uses actual features of scattering of the operation times both at sites and at stations. The article also proposed a new measure of arrival delay which considers the share of satisfied passengers.

Robust Capacitated Train Rescheduling with Passenger Reassignment under Stochastic Disruptions

“…A self-learning decision making procedure determines appropriate relevance weights for the distribution of buffer times when disturbances of the same type affect the network. Davydov et al propose a stochastic model by using specific distributions of operating times, which depend on the actual traffic conditions ( 21 ). The arrival time distribution is obtained by adjusting the train trajectory and corresponds well with the experimental data derived by Russian Railways.…”

“…Conversely, if they consider the train operation a priority, a relatively larger weight can be set for the minimization of the total train delay. Pareto-optimal solutions can be identified by means of the weighted-sum method with the normalization ( 21 ). In this paper, we will not occupy too much space to discuss the trade-off problem.…”

Dispatching and Rescheduling Tasks and Their Interactions with Travel Demand and the Energy Domain: Models and Algorithms

“…In addition to delays, also other randomnesses have been modelled. Within this framework, [122] introduced a stochastic disturbance on train performance, while stochasticity of arrival and recovery times is taken into account in the rescheduling models proposed by [123,124]. Furthermore, [125] analysed the impact of considering uncertainty in the rescheduling framework by comparing the results of different algorithms, both in deterministic and in stochastic scenarios.…”