Train Delays Research Articles

Trust and Accountability: Legal Implications of Train Delays

This normative legal research with statutory and conceptual approaches aims to analyze the implications of train delays according to schedule in a progressive legal perspective and to construct ethical and legal responsibility for such delays. The results reveal that train delays not only harm passengers but also decrease public trust in rail services. In a progressive legal perspective, trust is the fundamental element for law to serve human interests. To address this issue, a minister of transportation regulation should be established to hold train service managers accountable for delays and provide ethical and legal obligations to passengers. By learning from the accountability of aircraft delays, such regulations can be adapted to rail transportation.
 
 Highlights:
 
 Train delays have negative consequences for passengers and public trust in rail services.
 Trust is a fundamental element for law to serve human interests.
 A minister of transportation regulation should be established to hold train service managers accountable for delays and provide ethical and legal obligations to passengers.
 

Rescheduling Out-of-Gauge Trains with Speed Restrictions and Temporal Blockades on the Opposite-Direction Track

Out-of-gauge trains are trains with loading freight that exceeds the loading limitation border. Considering collision avoidance, the out-of-gauge trains have speed restriction of their own, and the trains running on the parallel track. Therefore, it is necessary to execute a train rescheduling procedure to rearrange the train paths of the out-of-gauge trains and the affected trains based on the fundamental timetable. For rescheduling the timetable, considering the blockades and the speed restrictions caused by the out-of-gauge trains, this paper proposed a time-space-state network representation for describing the out-of-gauge train rescheduling problem. A novel concept, speed allowance, is introduced to describe the train speed restriction due to the out-of-gauge trains. An integer programming model based on the time-space network is proposed to minimize the total train delay when running the out-of-gauge trains. The model can be solved by the rolling-time horizon approach for reducing computational time. A numerical example is conducted based on the conventional railway in China, demonstrating the solution performance of the model and the practical use of the methodology. Gurobi solver cannot obtain an optimal solution within 1 h when the planning-time horizon is greater than 120 min. With the rolling-time horizon approach, the rescheduled timetable can be obtained within 124 s for the 300 min planning-time horizon using 180 min rolling-time window.

Dynamic train dwell time forecasting: a hybrid approach to address the influence of passenger flow fluctuations

AbstractTrain timetables and operations are defined by the train running time in sections, dwell time at stations, and headways between trains. Accurate estimation of these factors is essential to decision-making for train delay reduction, train dispatching, and station capacity estimation. In the present study, we aim to propose a train dwell time model based on an averaging mechanism and dynamic updating to address the challenges in the train dwell time prediction problem (e.g., dynamics over time, heavy-tailed distribution of data, and spatiotemporal relationships of factors) for real-time train dispatching. The averaging mechanism in the present study is based on multiple state-of-the-art base predictors, enabling the proposed model to integrate the advantages of the base predictors in addressing the challenges in terms of data attributes and data distributions. Then, considering the influence of passenger flow on train dwell time, we use a dynamic updating method based on exponential smoothing to improve the performance of the proposed method by considering the real-time passenger amount fluctuations (e.g., passenger soars in peak hours or passenger plunges during regular periods). We conduct experiments with the train operation data and passenger flow data from the Chinese high-speed railway line. The results show that due to the advantages over the base predictors, the averaging mechanism can more accurately predict the dwell time at stations than its counterparts for different prediction horizons regarding predictive errors and variances. Further, the experimental results show that dynamic smoothing can significantly improve the accuracy of the proposed model during passenger amount changes, i.e., 15.4% and 15.5% corresponding to the mean absolute error and root mean square error, respectively. Based on the proposed predictor, a feature importance analysis shows that the planned dwell time and arrival delay are the two most important factors to dwell time. However, planned time has positive influences, whereas arrival delay has negative influences.

Adjusting Train Timetables Based on Passenger Flow for Cross-Line Trains

Urban rail transit becomes increasingly convenient for passengers by networking single lines. The urban rail transit network with cross-line trains has different characteristics from the traditional network. The trains can run to different lines at the crossing station, and the operation delay may be spread to different lines because of the operation schedule. A model for adjusting the running delay of cross-line trains is proposed in this paper. The optimization objective is to minimize the total delay time and the number of stranded passengers. In this paper, different scales of delay are analyzed and the operation order of the trains is allowed to be changed at the crossing station. Case simulations achieve good optimization results on the total delay time and the number of stranded passengers. Optimization diagrams are given under different strategies. The model and methodologies are also applied to Beijing Metro Line 13, and good simulation results are achieved for different scales of delay.

Optimal Control Strategies for Metro Trains to Use the Regenerative Braking Energy: A Speed Profile Adjustment Approach

The Regenerative Braking Energy (RBE) of metro trains plays an important role in metro energy saving. If the regenerative energy can be directly absorbed by the adjacent trains, the investment in other RBE usage equipments like super capacitors will be reduced. To increase the RBE usage, the overlaps of traction and braking processes of adjacent trains can be increased by timetable optimization or real-time train regulation. But if the overlaps cannot be realized, the RBE cannot be efficiently absorbed by the other trains. To solve this problem, this paper proposes an optimal train control method to absorb the RBE of the braking train by adjusting the speed profile of an adjacent train that runs at non-braking stage. A speed profile adjustment algorithm for the adjacent train is given considering the speed limits and gradients, in which a traction process is incorporated in the adjusted speed profile. Connected and unconnected DC power supply networks are both considered. In the connected DC power supply network, the RBE of the braking train can be absorbed by the adjacent adjusted train, which runs in the different power supply section. To test the robustness of the proposed algorithm, random train delays are considered in the simulations. The interstation running time will be regulated to reduce the train delay by a linear programming model, based on which, the speed profile of the cooperative train will be adjusted. Simulations are conducted based on a whole day data of Beijing Metro Line 4. The simulation results show that the proposed method improves the energy efficiency over 13% by improving RBE usage, and the proposed method also shows strong robustness in the train delay simulations, which makes it a promising method to be applied in real metro system.

A novel deep learning model for short-term train delay prediction

As the density of railway operations increases annually, train delays typically result in a greater degree of economic loss. If we can accurately assess the current evolution of delayed trains, railway authorities will be able to make timely decisions and reduce travel anxiety among passengers. In this paper, a deep learning model integrating wavelet transform (WT), fully connected neural network (FCNN), and long short-term memory (LSTM) network is proposed to address the short-term delay prediction problem for trains. Its predictive performance is enhanced by introducing two front train selection schemes, two methods for converting train operating time features into time-series data, and five commonly used wavelet functions. For validation purposes, the model is tested using real-world operational data from two distinct high-speed railway lines in China, and common machine learning algorithms are compared, including random forest (RF), gradient boosting regression tree (GBRT), XGBoosting (XGB), and support vector regression (SVR). The final experimental results demonstrate that our proposed model outperforms the benchmark models and can be effectively applied to practical prediction problems.

Integrated rescheduling of train timetables and rolling stock circulation for metro line disturbance management: a Q-learning-based approach

Disturbance occurs inevitably on a metro line, resulting in train delays and low service quality. To improve the efficiency of disturbance management, this article investigates the integrated rescheduling problem of train timetable and rolling stock circulation. To balance service quality and operational cost, the considered problem is formulated as a multi-objective optimization model by capturing train operation processes as running arcs, dwell arcs and coming-out/back arcs based on the classical space–time network. For the purpose of improving computational efficiency, a Q-learning-based solution approach is proposed to derive a hierarchical policy for integrated rescheduling. The decisions on train timetable follow a lower-level policy that can be learned in the pre-training process, and the decisions on rolling stock circulation follow a higher-level policy that can be generated in the real-time planning process. Finally, two sets of numerical examples are carried out to evaluate the proposed method.

Inequity averse optimization of railway traffic management considering passenger route choice and Gini Coefficient

Traffic management is crucial for improving the punctuality and reliability of train operations, enabling train operating companies (TOCs) to maintain their competitiveness and further increases the share and profits. A common goal of the train rescheduling problem is to minimize train delays, which fails to examine the results from the perspective of passengers. Moreover, focusing only on the punctuality performance overlooks how the delay is distributed among entities (i.e., trains, passengers, and train operating companies).We study the train rescheduling problem with the inclusion of passenger choices and the equity concerns. A mixed-integer linear programming (MILP) model is proposed to find the optimal train schedules and the best route for passengers at the same time, with respect to the demanded equity level. Passengers choose a sequence of train services to complete their trip with the least amount of costs (i.e., delays). To evaluate the equity performance of the system, we define equity by means of Gini Coefficient and Maximal Deviation, included in the MILP model as constraints.Experiments are conducted to explore the impacts of the objective change, i.e., from reducing train delays to reducing passenger delays, and to compare the system performance of using the two equity measures in terms of punctuality and equity. According to the results, the average passenger delay decreases by 34% when minimizing passenger delays, compared with that of minimizing train delays. Moreover, the Gini Coefficient yields less cost of equity (i.e., less increase of delays), compared to that of the Maximal Deviation.

A novel Markov model for near-term railway delay prediction

Predicting the near-future delay with accuracy for trains is momentous for railway operations and passengers’ traveling experience. This work aims to design prediction models for train delays based on the Netherlands Railway data. We first develop a chi-square test to show that the delay evolution over stations follows a first-order Markov chain. We then propose a delay prediction model based on non-homogeneous Markov chains. To deal with the sparsity of the transition matrices of the Markov chains, we propose a novel matrix recovery approach that relies on Gaussian kernel density estimation. Our numerical tests show that this recovery approach outperforms other benchmark approaches in prediction accuracy. The Markov chain model we propose also shows to be better than other widely-used time series models with respect to both interpretability and prediction accuracy. Moreover, our proposed model does not require a complicated training process, which is capable of handling large-scale forecasting problems.

Train traffic control in merging stations: A data-driven approach

Railway operations are subject to deviations from the planned schedule, i.e., delays. In those situations, high-quality traffic control actions are needed to reduce the delays. Existing studies mainly used prescriptive techniques (e.g., mathematical programming, heuristics) to identify the best control action. These methods have limitations in the firm reliance on deterministic parameters prescriptively or normatively determined beforehand, and little understandability by the practitioners. These drawbacks hinder their acceptance in practice.This study exploits instead past realization data to provide decision support for traffic control. The realized data describe the traffic control actions taken by human controllers, and their effects; those latter are more complex than a linear sum of predetermined parameters. We use decision graphs to identify which traffic control action leads to the best solution, in terms of reduction of delays, based on the past performance of the same action in similar conditions. We are also able to explain the reasons and the factors that lead to each suggested action.We focus on the relevant case of merging stations, where multiple lines merge as one line, deciding the relative order between two consecutive trains. The method determines the stochastic effects of the two possible decisions at merge points, which allows for choosing the best one. Compared within the framework of realized data, the action suggested is the best out of a series of benchmarks, including simple rules and optimization, improving (reducing delays) approximately 11.7% on the common benchmarks. The variables with the highest impact on the utility are the length of the planned dwell time and the planned presence of an overtaking. The variables influencing the utility most are the actual delays of trains, the train type, and the order actually implemented.

An Efficient Distributed Machine Learning Framework in Wireless D2D Networks: Convergence Analysis and System Implementation

Facing the heavy traffic burden and data privacy, distributed machine learning (DML) has been envisioned as a promising computing paradigm to enable edge intelligence by extracting and establishing models collaboratively in wireless networks. Unlike centralized methods, DML involves frequent local model exchanging among distributed devices, which confronts low efficiency referring to the convergence rate and delay. To enable edge intelligence, how to train DML efficiently has recently attracted extensive interest in wireless networks. Rather than over a fixed or centralized topology, we study the convergence and system implementation of DML over a wireless device-to-device (D2D) network in this paper. First, we introduce the DML training process and system model in this network, where the total delay in reaching convergence is minimized. Second, we analyze the convergence rate to figure out the special effects of synchronization frequency and network topology. To improve the efficiency of DML training, we propose a system implementation approach to reduce the convergence rate and delay of one iteration, where the network topology and synchronization frequency are set, followed by an optimal resource allocation policy. At last, we perform experiments with an image classification task. Simulation results indicate that our proposed D2D framework can effectively reduce training delay and promote computation efficiency by 39% in a heterogeneous environment, which is concordant with the theoretical analysis.

A Novel Disease Prediction Model Based on Blockchain and Federated Learning

With the advent of the era of big data, the model architecture of disease prediction has been transformed from cloud computing architecture to edge computing architecture to alleviate problems, such as single point of failure, huge burden of computing and long communication delays.However, due to the lack of trust among edge computing participants (herein referred to as medical institutions with data resources or data storage nodes), the patients’ personal privacy and security issues are still challenging, and there is an urgent need to propose new solutions with higher security. In this paper, we proposed a new disease prediction model with the edge computing framework based on blockchain and federated learning technology to realise full mining of data value, as well as protecting local data sharing security and privacy. In the process of federated learning with blockchain as the underlying platform working environment, we propose the concept of model accuracy as the selection indicator of data nodes in federated learning, which improves the accuracy of the federated learning model and optimizes the training delay.

Optimizing Training Efficiency and Cost of Hierarchical Federated Learning in Heterogeneous Mobile-Edge Cloud Computing

Federated learning (FL), an emerging distributed machine learning (ML) technique, allows massive embedded devices and a server to work together for training a global ML model without collecting user data on a server. Most existing approaches adopt the traditional centralized FL paradigm with a single server: one is the cloud-centric FL paradigm and the other is the edge-centric FL paradigm. The cloud-centric FL paradigm is able to manage a large-scale FL system across massive user devices with high communication cost, whereas the edge-centric FL paradigm is capable of coordinating a small-scale FL system benefiting from the low communication delay over wireless networks. To fully exploit the advantages of both, in this paper, we develop a distinctive hierarchical FL framework for the promising mobile-edge cloud computing (MECC) system, called HELCHFL, to achieve high-efficiency and low-cost hierarchical FL training. In particular, we formulate the corresponding theoretical foundation for our HELCHFL to ensure hierarchical training performance. Furthermore, to address the inherent communication and user heterogeneity issues of FL training, our HELCHFL develops a utility-driven and heterogeneity-aware heuristic user selection strategy to enhance training performance and reduce training delay. Subsequently, by analyzing and utilizing the slack time in FL training, our HELCHFL introduces a device operating frequency determination approach to reduce training energy cost. Experiments demonstrate that our HELCHFL can enhance the highest accuracy by up to 52.93%, gain the training speedup of up to 483.74%, and obtain up to 45.59% training energy savings compared to state-of-the-art baselines.

Statistical learning for train delays and influence of winter climate and atmospheric icing

This study investigated the climate effect under consecutive winters on the arrival delay of high-speed passenger trains. Inhomogeneous Markov chain model and stratified Cox model were adopted to account for the time-varying risks of train delays. The inhomogeneous Markov chain modelling used covariates weather variables, train operational direction, and findings from the primary delay analysis through stratified Cox model. The results showed that temperature, snow depth, ice/snow precipitation, and train operational direction, significantly impacted the arrival delay. Further, by partitioning the train line into three segments as per transition intensity, the model identified that the middle segment had the highest chance of a transfer from punctuality to delay, and the last segment had the lowest probability of recovering from delayed state. The performance of the fitted inhomogeneous Markov chain model was evaluated by the walk-forward validation method, which indicated that approximately 9% of trains may be misclassified as having arrival delays by the fitted model at a measuring point on the train line. With the model performance, the fitted model could be beneficial for both travellers to plan their trips reasonably and railway operators to design more efficient and wiser train schedules as per weather condition.

Quantifying the Influence of Volume Variability on Railway Hump Classification Yard Performance with AnyLogic Simulation

On North American freight railways, railcars transported in manifest (carload) freight trains are required to stop and be resorted at multiple intermediate classification (marshalling) yards before reaching their destination. Yard dwell time comprises the majority of total railcar transit time, and railway yard congestion can further promote mainline train delay. However, most of the literature on railroad performance has focused on the mainline, and few of the previous yard studies specifically examined the yard performance impacts of vast volume fluctuation because of variable shipping demand. To further understand yard behavior under these conditions, this paper explores the influence of inbound traffic volume variability on classification yard performance and outbound train size using a novel AnyLogic simulation model. A series of simulation experiments quantify the interaction between inbound and outbound train size variability as measured by different yard performance metrics under different overall traffic volumes and blocking patterns. The results quantify the impact of volume variation on railway classification yard level of service, and suggest that forming longer blocks leads to shorter dwell times but larger sensitivity to volume variation compared to forming multiple short blocks. Comparison of arrival and departure train size distributions indicates that classification yards moderate volume fluctuations while causing departure delays. These results serve as a quantitative foundation for further study of yard performance recovery patterns following traffic volume surges and the resulting interactions between yards and mainlines in the railway network, and can inform railroad operating plan adjustments to better manage yard traffic and utilize existing resources.

Improving multimodal passenger transportation technology under the wartime conditions in Ukraine

Abstract. Problem. Ukraine has a rather complex transport network, so the mismatch between the work of carriers when transferring from one mode of transport to another can create a large number of inconveniences for passengers. Issuance of various travel documents, the complexity of processing luggage and its movement between vehicles, a more thorough check of documents and luggage by employees of law enforcement agencies at border crossings and transfer points lead to an increase in travel time. On the other hand, ensuring the demand for some main directions of transportation can only be through the use of several modes of transport, so there is a need to improve the existing logistics technology for multimodal passenger transportation.
 Goal. The goal of this publication is to improve the technology of multimodal passenger transportation under martial law Methodology. Analytical research methods were used to form the relationship between the train delay at the border station and the number of passengers in it. Mathematical modulation methods were used in the formation of a new agreed schedule for the arrival of international passenger trains at the Kyiv-Passenger transport hub. Results. The research has shown that even under the current wartime conditions, it is possible to improve the operation of various types of passenger transport and the consistency of their traffic schedules to better meet the needs and quality of passenger transportation. The authors of the article analyzed the state and causes of delays in passenger trains at the Mostyska-2 border crossing, through which the largest railway passenger flows between Ukraine and the EU countries currently follow. Based on the analysis, the dependence of the train delay time at the border station on the number of passengers in the train was revealed, and in order to reduce the duration of these delays, it was proposed to improve the existing technology for calculating the travel time of a passenger train by introducing and using value F, corresponding to the train delay time at the border station per passenger. Originality. It is suggested to improve the model for organizing the interaction of different types of transport in the transport interchange Kyiv-passenger hub, by introducing a new value φ based on the dependence of the train delay time at the border station on the number of passengers transported in it, taking into account the specifics of the introduction of martial law in Ukraine. Practical value. The introduction and integration of the proposed technology into the existing mathematical models for the formation of a rationally coordinated schedule of multimodal passenger transportation will significantly reduce the waiting time for passengers at transfer points, rationalize the capacity and population of the rolling stock and increase the financial profit for carriers, it can also be used for the development of the system, information technologies and the use of a "single ticket".

Modelling the cascading effects of train delay patterns and inter-train control actions with Bayesian networks

ABSTRACT Based on train operation data, Bayesian networks (BN) are used to model the cascading effects of traffic control actions and their influences (such as changes in train delays) for two and three consecutive trains. Influence factors are first determined to describe the interactions between train delays and control actions, i.e. the delay changes due to control actions over time and space. Considering the interdependence of these factors, their causal relationships are obtained, and the BN model’s connection paradigm is determined based on these causal ties. The BN structures are then proposed by combining domain knowledge and a data-driven method. The proposed models are tested on the train operation data from the Chinese high-speed railways. The results show that the proposed method exhibits a good fit for the train operation data and outperforms other conventional train operation models in terms of various evaluation metrics. Besides, the strength of train control actions’ cascading effects is investigated. It shows that section train control actions are stronger than those in stations, and both are considerably correlated with train delays and recovery times in sections and stations. Finally, a macroscopic model for control actions between several trains (more than three) is obtained based on the learned paradigm of the presented models and the cascading effects between two and three trains, demonstrating the model’s extensibility. The proposed models are intended to support traffic controllers with the estimation of future train delay change patterns, the expected control actions, and the cascading effects of control actions, and they are imperative for aiding the decision-making of controllers to manage high-speed railway traffic.

Capturing complexity over space and time via deep learning: An application to real-time delay prediction in railways

Predictive analytics is an increasingly popular tool for enhancing decision-making processes but is in many business settings based on rule-based models. These rule-based models reach their limits in complex settings. This study compares the performance of a rule-based system with a customised LSTM encoder-decoder deep learning model for predicting train delays. For this, we use a purposefully built real-world dataset on railway transportation, where trains’ interdependence over the network makes delay prediction more difficult. Results show that the deep learning model, which incorporates rich spatiotemporal interdependency information in real-time, outperforms the rule-based system by 18%, with the difference increasing to above 23% with higher complexity. The study also dissects the performance difference across different settings: dense versus rural areas, peak versus off-peak hours, low versus high delay, and before versus during the COVID-19 pandemic. The deep learning model is implemented as a proof of concept for decision support within Belgium’s railway infrastructure company Infrabel.

Impact of COVID-19 on operating assignments in residency training of endocrine surgery: A retrospective cohort study

PurposeAirborne pandemics illustrate a significant problem in training grounds. From the endocrine surgery point of view, we scrutinized the impact of Covid-19 on general surgery residency training in our university hospital. MethodsThe number of endocrine procedure curves was forecasted using the expert modeler in a time series model from March to September 2020 based on data from previous years. We then compared the estimation curves to actual numbers. ResultsThere were 1340 resident participants in thyroid procedures, 405 in parathyroid procedures, 65 in other neck procedures, and 304 in adrenal procedures. In 884 of the endocrine procedures, the operating surgeon was a resident. The median experience of operating residents in endocrine procedures was 3.2 years (interquartile range 2.7–3.6) before the impact and 3.8 years (interquartile range 3.1–4.1) after it (p = 0.023). The monthly number of actual procedures with at least one resident participation in the Covid-19 period was significantly lower (8.7 ± 7.5 vs. 19.9 ± 3.7, p = 0.012) than the forecasted numbers. There were no semi-autonomous operating chief residents, although we expected a moderate level (0 actual vs. 0.5 ± 0.2 predicted, p = 0.002). ConclusionThis study clearly represents sustainability in surgical training and includes usual trends. Essential endocrine surgical procedures the pandemic disrupted the most were the treatment of thyroid and parathyroid diseases. Covid-19 reduced our surgical volume and resulted in delays in training. A full-scale disaster plan is necessary for possible crises threatening surgical education.

A Federated Learning-Based Edge Caching Approach for Mobile Edge Computing-Enabled Intelligent Connected Vehicles

Massive map data transmission and the strict demand for the privacy of high-precision maps have brought significant challenges to the cache of high-precision maps in intelligent connected vehicles (ICV). Federal learning (FL) was introduced to reduce the pressure on the edge network and protect privacy. But the high dynamics of cars and limited resources lead to low accuracy and high training delay. We propose a joint optimization scheme of participant selection and resource allocation for federated learning. In each time slice, vehicles are determined whether to participate in training, which minimizes long-term training delay with limited energy consumption. To meet the delay and privacy requirements of high-precision map caching, we present an edge cooperative caching scheme based on federated deep reinforcement learning (F-DRL), which aims to achieve dynamic adaptive edge caching while protecting user privacy. The collaborative caching model is formulated as a Markov decision process (MDP). Dueling Deep Q Network (Dueling-DQN) is used to solve the optimal strategy, and federal learning is used for training. Enough comparative experiments to evaluate the performance of the proposed schemes. The aspects of reliability, cache hit rate, and training accuracy prove that the method effectively improves the training parameters of federated learning while meeting a high-precision map cache’s delay and reliability requirements.