Closing the loop in real-time railway control: Framework design and impacts on operations

Railway traffic is heavily affected by disturbances and/or disruptions, which are often cause of delays and low performance of train services. The impact and the propagation of such delays can be mitigated by relying on automatic tools for rescheduling traffic in real-time. These tools predict future track conflict based on current train information and provide suitable control measures (e.g. reordering, retiming and/or rerouting) by using advanced mathematical models. A growing literature is available on these tools, but their effects on real operations are blurry and not yet well known, due to the very scarce implementation of such systems in practice.In this paper we widen the knowledge on how automatic real-time rescheduling tools can influence train performance when interfaced with railway operations. To this purpose we build up a novel traffic control framework that couples the state-of-the art automatic rescheduling tool ROMA, with the realistic railway traffic simulation environment EGTRAIN, used as a surrogate of the real field. At regular times ROMA is fed with current traffic information measured from the field (i.e. EGTRAIN) in order to predict possible conflicts and compute (sub) optimal control measures that minimize the max consecutive delay on the network. We test the impact of the traffic control framework based on different types of interaction (i.e. open loop, multiple open loop, closed loop) between the rescheduling tool and the simulation environment as well as different combinations of parameter values (such as the rescheduling interval and prediction horizon). The influence of different traffic prediction models (assuming e.g. aggressive versus conservative driving behaviour) is also investigated together with the effects on traffic due to control delays of the dispatcher in implementing the control measures computed by the rescheduling tool.Results obtained for the Dutch railway corridor Utrecht–Den Bosch show that a closed loop interaction outperforms both the multiple open loop and the open loop approaches, especially with large control delays and limited information on train entrance delays and dwell times. A slow rescheduling frequency and a large prediction horizon improve the quality of the control measure. A limited control delay and a conservative prediction of train speed help filtering out uncertain traffic dynamics thereby increasing the effectiveness of the implemented measures.     

Reinforcement learning approach for train rescheduling on a single-track railway

Optimal rail network infrastructure and rolling stock utilization can be achieved with use of different scheduling tools by extensive planning a long time before actual operations. The initial train timetable takes into account possible smaller disturbances, which can be compensated within the schedule. Bigger disruptions, such as accidents, rolling stock breakdown, prolonged passenger boarding, and changed speed limit cause delays that require train rescheduling. In this paper, we introduce a train rescheduling method based on reinforcement learning, and more specifically, Q-learning. We present here the Q-learning principles for train rescheduling, which consist of a learning agent and its actions, environment and its states, as well as rewards. The use of the proposed approach is first illustrated on a simple rescheduling problem comprising a single-lane track with three trains. The evaluation of the approach is performed on extensive set of experiments carried out on a real-world railway network in Slovenia. The empirical results show that Q-learning lead to rescheduling solutions that are at least equivalent and often superior to those of several basic rescheduling methods that do not rely on learning agents. The solutions are learned within reasonable computational time, a crucial factor for real-time applications.     

Train rescheduling model with train delay and passenger impatience time in urban subway network

This paper considers the train rescheduling problem with train delay in urban subway network. With the objective of minimizing the negative effect of train delay to passengers, which is quantified with a weighted combination of travel time cost and the cost of giving up the planned trips, train rescheduling model is proposed to jointly synchronize both train delay operation constraints and passenger behavior choices. Space–time network is proposed to describe passenger schedule‐based path choices and obtain the shortest travel times. Impatience time is defined to describe the intolerance of passengers to train delay. By comparing the increased travel time due to train delay with the passenger impatience time, a binary variable is defined to represent whether the passenger will give up their planned trips or not. The proposed train rescheduling model is implemented using genetic algorithm, and the model effectiveness is further examined through numerical experiments of real‐world urban subway train timetabling test. Duration effects of the train delay to the optimization results are analyzed. Copyright © 2017 John Wiley & Sons, Ltd.     

Macroscopic multiple-station short-turning model in case of complete railway blockages

In case of railway disruptions, traffic controllers are responsible for dealing with disrupted traffic and reduce the negative impact for the rest of the network. In case of a complete blockage when no train can use an entire track, a common practice is to short-turn trains. Trains approaching the blockage cannot proceed according to their original plans and have to short-turn at a station close to the disruption on both sides. This paper presents a Mixed Integer Linear Program that computes the optimal station and times for short-turning the affected train services during the three phases of a disruption. The proposed solution approach takes into account the interaction of the traffic between both sides of the blockage before and after the disruption. The model is applied to a busy corridor of the Dutch railway network. The computation time meets the real-time solution requirement. The case study gives insight into the importance of the disruption period in computing the optimal solution. It is concluded that different optimal short-turning solutions may exist depending on the start time of the disruption and the disruption length. For periodic timetables, the optimal short-turning choices repeat due to the periodicity of the timetable. In addition, it is observed that a minor extension of the disruption length may result in less delay propagation at the cost of more cancellations.     

A robust,tactic-based,real-time framework for public-transport transfer synchronization

Missed transfers affect public transport (PT) operations by increasing passenger’s waiting and travel times and frustration. Because of the stochastic and uncertain nature of PT systems, synchronized transfers do not always materialize. This work proposes a new mathematical programming model to minimize total passenger travel time and maximize direct (without waiting) transfers. The model consists of four policies built on a combination of three tactics: holding, skip-stops, and short-turn, the last applied, for the first time, as a real-time control action. The concept is implemented in two steps: optimization and simulation. An agent-based simulation framework is used to represent real-life scenarios, generate random input data, and validate the optimization results. In order to assess the robustness of this framework, a wide range of schedule-deviation scenarios are defined using efficient algorithms for solving the control models within a rolling horizon structure. A case study of the Auckland, New Zealand, PT system is described for assessing the methodology developed. The results show a 4.7% reduction in total passenger travel time and a more than 150% increase in direct transfers. The best impressive results are attained under short headway operations.     

The airline perturbation problem: considering disrupted passengers

Abstract

When airlines are faced with some unforeseen short-term events, they have to reconstruct their flight schedules. Although aircraft recovery decisions affect passengers, these disrupted passengers and recovering them have not been explicitly considered in most previous aircraft recovery models. This paper presents an assignment model for airline schedule recovery which recovers both aircraft and disrupted passengers simultaneously, using a rolling horizon time framework. Our model examines possible flight retiming, aircraft swapping, over-flying, ferrying, utilization of reserve aircraft, cancellation and passenger reassignment to generate an efficient schedule recovery plan. The model ensures that the schedule returns to normal within a certain time and the objective is to minimize operational recovery aircraft cost, cancellation and delay cost as well as disrupted passenger cost. The model is tested using a data-set with two disruption scenarios. The computational results show that it is capable of handling the integrated aircraft and passenger recovery problem successfully.     

The dynamic shortest path problem with time-dependent stochastic disruptions

The dynamic shortest path problem with time-dependent stochastic disruptions consists of finding a route with a minimum expected travel time from an origin to a destination using both historical and real-time information. The problem is formulated as a discrete time finite horizon Markov decision process and it is solved by a hybrid Approximate Dynamic Programming (ADP) algorithm with a clustering approach using a deterministic lookahead policy and value function approximation. The algorithm is tested on a number of network configurations which represent different network sizes and disruption levels. Computational results reveal that the proposed hybrid ADP algorithm provides high quality solutions with a reduced computational effort.     

Energy-efficient metro train rescheduling with uncertain time-variant passenger demands: An approximate dynamic programming approach

In a heavily congested metro line, unexpected disturbances often occur to cause the delay of the traveling passengers, infeasibility of the current timetable and reduction of the operational efficiency. Due to the uncertain and dynamic characteristics of passenger demands, the commonly used method to recover from disturbances in practice is to change the timetable and rolling stock manually based on the experiences and professional judgements. In this paper, we develop a stochastic programming model for metro train rescheduling problem in order to jointly reduce the time delay of affected passengers, their total traveling time and operational costs of trains. To capture the complexity of passenger traveling characteristics, the arriving ratio of passengers at each station is modeled as a non-homogeneous poisson distribution, in which the intensity function is treated as time-varying origin-to-destination passenger demand matrices. By considering the number of on-board passengers, the total energy usage is modeled as the difference between the tractive energy consumption and the regenerative energy. Then, we design an approximate dynamic programming based algorithm to solve the proposed model, which can obtain a high-quality solution in a short time. Finally, numerical examples with real-world data sets are implemented to verify the effectiveness and robustness of the proposed approaches.     

A hierarchical line planning approach for a large-scale high speed rail network: The China case

Planning a set of train lines in a large-scale high speed rail (HSR) network is typically influenced by issues of longer travel distance, high transport demand, track capacity constraints, and a non-periodic timetable. In this paper, we describe an integrated hierarchical approach to determine line plans by defining the stations and trains according to two classes. Based on a bi-level programming model, heuristics are developed for two consecutive stages corresponding to each classification. The approach determines day-period based train line frequencies as well as a combination of various stopping patterns for a mix of fast trunk line services between major stations and a variety of slower body lines that offer service to intermediate stations, so as to satisfy the predicted passenger transport demand. Efficiencies of the line plans described herein concern passenger travel times, train capacity occupancy, and the number of transfers. Moreover, our heuristics allow for combining many additional conflicting demand–supply factors to design a line plan with predominantly cost-oriented and/or customer-oriented objectives. A range of scenarios are developed to generate three line plans for a real-world example of the HSR network in China using a decision support system. The performance of potential train schedules is evaluated to further examine the feasibility of the obtained line plans through graphical timetables.     

Rolling horizon stochastic optimal control strategy for ACC and CACC under uncertainty

This paper presents a rolling horizon stochastic optimal control strategy for both Adaptive Cruise Control and Cooperative Adaptive Cruise Control under uncertainty based on the constant time gap policy. Specifically, uncertainties that can arise in vehicle control systems and vehicle sensor measurements are represented as normally-distributed disturbances to state and measurement equations in a state-space formulation. Then, acceleration sequence of a controlled vehicle is determined by optimizing an objective function that captures control efficiency and driving comfort over a predictive horizon, constrained by bounded acceleration/deceleration and collision protection. The optimization problem is formulated as a linearly constrained linear quadratic Gaussian problem and solved using a separation principle, Lagrangian relaxation, and Kalman filter. A sensitivity analysis and a scenario-based analysis via simulations demonstrate that the proposed control strategy can generate smoother vehicle control and perform better than a deterministic feedback controller, particularly under small system disturbances and large measurement disturbances.     

Passenger oriented railway disruption management by adapting timetables and rolling stock schedules

In passenger railway operations, unforeseen events require railway operators to adjust their timetable and their resource schedules. The passengers will also adapt their routes to their destinations. When determining the new timetable and rolling stock schedule, the railway operator has to take passenger behavior into account. The operator should increase the capacity of trains for which the operator expects more demand than on a regular day. Furthermore, the operator could increase the frequency of the trains that serve stations with an additional demand.This paper describes a real-time disruption management approach which integrates the rescheduling of the rolling stock and the timetable by taking the changed passenger demand into account. The timetable decisions are limited to additional stops of trains at stations at which they normally would not call. Several variants of the approach are suggested, with the difference in how to determine which additional stops should be executed.Real-time rescheduling requires fast solutions. Therefore a heuristic approach is used. We demonstrate the performance of the several variants of our algorithm on realistic instances of Netherlands Railways, the major railway operator in the Netherlands.     

Disruption risk management in railroad networks: An optimization-based methodology and a case study

We propose an optimization-based methodology for recovery from random disruptions in service legs and train services in a railroad network. A network optimization model is solved for each service leg to evaluate a number of what-if scenarios. The solutions of these optimization problems are then used in a predictive model to identify the critical disruption factors and accordingly design a suitable mitigation strategy. A mitigation strategy, such as adding flexible or redundant capacity in the network, is an action that is deliberately taken by management in order to hedge against the cost and impact of disruption if it occurs. It is important that managers consider the trade-offs between the cost of mitigation strategy and the expected cost of disruption. The proposed methodology is applied to a case study built using the realistic infrastructure of a railroad network in the mid-west United States. The resulting analysis underscores the importance of accepting a slight increase in pre-disruption transportation costs, which in turn will enhance network resiliency by building dis-similar paths for train services, and by installing alternative links around critical service legs.     

Real-time schedule recovery in liner shipping service with regular uncertainties and disruption events

This paper studies real-time schedule recovery policies for liner shipping under various regular uncertainties and the emerging disruption event that may delay a vessel from its planned schedule. The aim is to recover the affected schedule in the most efficient way. One important contribution of this work is to explicitly distinguish two types of uncertainties in liner shipping, and propose different strategies to handle them. The problem can be formulated as a multi-stage stochastic control problem that minimizes the total expected fuel cost and delay penalty. For regular uncertainties that can be characterized by appropriate probabilistic models, we develop the properties of the optimal control policy; then we show how an emerging disruption may change the control policies. Numerical studies demonstrate the advantages of real-time schedule recovery policies against some typical alternatives.     

Service-cost tradeoffs for carload freight traffic in the U.S. rail industry

Railroad technology permits a single train to move a large number of individual freight cars. However, cars which are not in dedicated unit train or intermodal service experience considerable delay due to the consolidation and breakup of trains. Rail operations thus involve a tradeoff between the economies of shipment consolidation, and the resulting delays. More direct and/or more frequent train connections will increase costs, but reduce transit times. This article quantifies the cost of providing a range of transit times for general carload traffic for several representative U.S. rail systems. It shows that significant reductions in transit time will require a large increase in the number of train connections and operating cost. Changes in labor contracts to reduce train crew cost will provide some incentive for higher service levels, but reductions in crew cost alone cannot be expected to dramatically improve the performance of the carload segment of the industry.     

Rescheduling through stop-skipping in dense railway systems

Based on the analysis of the railway system in the Paris region in France, this paper presents a rescheduling problem in which stops on train lines can be skipped and services are retimed to recover when limited disturbances occur. Indeed, in such mass transit systems, minor disturbances tend to propagate and generate larger delays through the shared use of resources, if no action is quickly taken. An integrated Integer Linear Programming model is presented whose objective function minimizes both the recovery time and the waiting time of passengers. Additional criteria related to the weighted number of train stops that are skipped are included in the objective function. Rolling-stock constraints are also taken into account to propose a feasible plan. Computational experiments on real data are conducted to show the impact of rescheduling decisions depending on key parameters such as the duration of the disturbances and the minimal turning time between trains. The trade-off between the different criteria in the objective function is also illustrated and discussed.     

A practical capacity model of a single track line

The paper presents a model for determining the practical capacity of a single track line, i.e. the maximum number of trains which can be run along it in a time unit under the condition that each train enters its bottleneck segment with a definite delay.

The input data used in the model are: geometrical characteristics of the bottleneck segment of the line under study, the intensity and structure of demand expressed by a number of trains which are run over the line in a given time unit, the scenario of traffic running over the line under study and the operational tactics of individual train categories processing on the bottleneck segment.

(Two tactics can be applied in the train processing on the line under study; first, the trains of individual categories are given different priorities in the processing, and second, all the trains have the same priority).

The output results of the model are average delays of trains of each category occurring within the train processing performed on the bottleneck segment of the line under study in a given time unit.     

A green intermodal service network design problem with travel time uncertainty

In a more and more competitive and global world, freight transports have to overcome increasingly long distances while at the same time becoming more reliable. In addition, a raising awareness of the need for environmentally friendly solutions increases the importance of transportation modes other than road. Intermodal transportation, in that regard, allows for the combination of different modes in order to exploit their individual advantages. Intermodal transportation networks offer flexible, robust and environmentally friendly alternatives to transport high volumes of goods over long distances. In order to reflect these advantages, it is the challenge to develop models which both represent multiple modes and their characteristics (e.g., fixed-time schedules and routes) as well as the transhipment between these transportation modes. In this paper, we introduce a Green Intermodal Service Network Design Problem with Travel Time Uncertainty (GISND-TTU) for combined offline intermodal routing decisions of multiple commodities. The proposed stochastic approach allows for the generation of robust transportation plans according to different objectives (i.e., cost, time and greenhouse gas (GHG) emissions) by considering uncertainties in travel times as well as demands with the help of the sample average approximation method. The proposed methodology is applied to a real-world network, which shows the advantages of stochasticity in achieving robust transportation plans.     

A delay root cause discovery and timetable adjustment model for enhancing the punctuality of railway services

Knock-on delay, which is the key factor in punctuality of railway service, is mainly related to two factors including the quality of timetable in the planning phase and disturbances which may result in unscheduled trains’ waiting or meeting in operation phase. If the delay root cause and the interactions among the factors responsible for these can be clearly clarified, then the punctuality of railway operations can be enhanced by taking reactions such as timetable adjustment, rescheduling or rerouting of railway traffic in case of disturbances. These delay reasons can be used to predict the lengths of railway disruptions and effective reactions can be applied in disruption management. In this work, a delay root cause discovery model is proposed, which integrates heterogeneous railway operation data sources to reconstruct the details of the railway operations. A supervised decision tree method following the machine learning and data mining techniques is designed to estimate the key factors in knock-on delays. It discovers the root cause delay factor by logically analyzing the scheduled or un-scheduled trains meetings and overtaking behaviors, and the subsequent delay propagations. Experiment results show that the proposed decision tree can predict the delay reason with the accuracy of 83%, and it can be further enhance to 90% if the delay cause is only considered “prolonged passengers boarding” and “meeting or overtaking” factors. The delay root cause can be discovered by the proposed model, verified by frequency filtering in operation records, and resolved by the adjustment of timetable which is an important reference for the next timetable rescheduling. The results of this study can be applied to railway operation decision support and disruption management, especially with regard to timetable rescheduling, trains resequencing or rerouting, system reliability analysis, and service quality improvements.     

Multi-stage stochastic program to optimize signal timings under coordinated adaptive control

In the wake of traffic congestion at intersections, it is imperative to shorten delays in corridors with stochastic arrivals. Coordinated adaptive control can adjust green time flexibly to deal with a stochastic demand, while maintaining a minimum through-band for coordinated intersections. In this paper, a multi-stage stochastic program based on phase clearance reliability (PCR) is proposed to optimize base timing plans and green split adjustments of coordinated intersections under adaptive control. The objective is to minimize the expected intersection delay and overflow of the coordinated approach. The overflow or oversaturated effect is explicitly addressed in the delay calculation, which greatly increases the modeling complexity due to the interaction of overflow delays across cycles. The notion of PCR separates the otherwise related green time settings of consecutive cycles into a number of stages, in which the base timing plan and actual timing plan in different cycles are handled sequentially. We then develop a PCR based solution algorithm to solve the problem, and apply the model and the solution algorithm to actual intersections in Shanghai to investigate its performance as compared with Allsop’s method and Webster’s method. Preliminary results show the PCR-based method can significantly shorten delays and almost eliminates overflow for the coordinated approaches, with acceptable delay increases of the non-coordinated approaches. A comparison between the proposed coordinated adaptive logic and a coordinated actuated logic is also conducted in the case study to show the advantages and disadvantages.     

Railway traffic disturbance management—An experimental analysis of disturbance complexity,management objectives and limitations in planning horizon

With the increasing traffic volumes in European railway networks and reports on capacity deficiencies that cause reliability problems, the need for efficient disturbance management becomes evident. This paper presents a heuristic approach for railway traffic re-scheduling during disturbances and a performance evaluation for various disturbance settings using data for a large part of the Swedish railway network that currently experiences capacity deficiencies. The significance of applying certain re-scheduling objectives and their correlation with performance measures are also investigated. The analysis shows e.g. that a minimisation of accumulated delays has a tendency to delay more trains than a minimisation of total final delay or total delay costs. An experimental study of how the choice of planning horizon in the re-scheduling process affects the network on longer-term is finally presented. The results indicate that solutions which are good on longer-term can be achieved despite the use of a limited planning horizon. A 60 min long planning horizon was sufficient for the scenarios in the experiments.