Adaptive, data-driven, online prediction of train event times

Kecman, Pavle; Goverde, Rob M.P.

doi:10.1109/itsc.2013.6728330

Cited by 4 publications

(5 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, calibration of the global model as well as the application in real-time is computationally more demanding than creating the multiple local models and using them for prediction. Therefore, the local models were used for real-time calibration of the railway traffic prediction model described in Kecman and Goverde (2014).…”

Section: Discussionmentioning

confidence: 99%

“…The errors of running time estimates are within 10 % of the corresponding scheduled running times, whereas the error of dwell time estimates may be even larger than the corresponding scheduled dwell times. The methodology presented in this paper was used for the calibration of a realtime prediction model described in Kecman and Goverde (2014). Having in mind the real-time character of the tool, the main criteria for comparing the data-driven approach with other relevant approaches are prediction accuracy and computational requirements.…”

Section: Comparison Of Prediction Accuracy For Scheduled Processesmentioning

confidence: 99%

“…Similarly, on the tactical level, the accurate estimation of running and dwell times is important for creating feasible and realizable timetables (Goverde 2007;Büker and Seybold 2012;Medeossi et al 2011). Finally, on the operational control level, process times need to be estimated for real-time traffic prediction and conflict detection (Dolder et al 2009;D'Ariano et al 2007;Kecman and Goverde 2014), as well as to provide reliable passenger information (Berger et al 2011).…”

Section: Introductionmentioning

confidence: 99%

“…Each local model represents an independent statistical model. The global and local approaches are compared by their accuracy and applicability for calibrating a real-time railway traffic prediction model described by Kecman and Goverde (2014).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Predictive modelling of running and dwell times in railway traffic

Kecman

Goverde

2015

Public Transp

Self Cite

View full text Add to dashboard Cite

Accurate estimation of running and dwell times is important for all levels of planning and control of railway traffic. The availability of historical track occupation data with a high degree of granularity inspired a data-driven approach for estimating these process times. In this paper we present and compare the accuracy of several approaches to model running and dwell times in railway traffic. Three global predictive model approaches are presented based on advanced statistical learning techniques: LTS robust linear regression, regression trees and random forests. Also local models are presented for a particular train line, station or block section, based on LTS robust linear regression with some refinements. The models are validated and compared using a test set independent from the training set. The applicability of the proposed data-driven approach for real-time applications is proved by the accuracy of the obtained estimates and the low computation times. Overall, the local models perform best both in accuracy and computation time.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Comparison Of Prediction Accuracy For Scheduled Processesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Predictive modelling of running and dwell times in railway traffic

Kecman

Goverde

2015

Public Transp

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [16] a tool is described that gathers the system information and uses historical data to predict the future process times and future conflicts between trains. In [17], [8] it is explained how the control inputs are implemented and updated step after step.…”

Section: Model Predictive Controlmentioning

confidence: 99%

Distributed model predictive control for rescheduling of railway traffic

Kersbergen

Boom

Schutter

2014

17th International IEEE Conference on Intelligent Transportation Systems (ITSC)

View full text Add to dashboard Cite

In this paper we introduce two distributed model predictive control (DMPC) methods for the rescheduling of railway traffic. In each step of the DMPC approach dispatching actions are determined that reduce the amount of delay in the network as much as possible by solving a mixed integer linear programming (MILP) problem. The constraints of the MILP are based on a model of the railway traffic and network and the possible dispatching actions.In the first method each subproblem consists of the complete constraint matrix and the solver tries to minimize the centralized cost function, but can only change a limited number of binary variables (which correspond to the dispatching actions). By limiting the number of binary variables each subproblem is easier to solve than the centralized problem. For the second method each subproblem consists of only a part of the problem and the solver minimizes a local cost function, and it can only change the binary variables for that part of the problem. This reduces the complexity of the subproblems even further, but the solver can not determine the effects of the binary variables on the solution quality of the other subproblems.Both methods significantly reduce the time needed to determine the dispatching actions. The average time needed to compute the solution is 11.56 times shorter when using method 1 and 39.11 times shorter when using method 2. The solution found is on average only 0.63% less optimal for method 1 and 1.27% less optimal for method 2.

show abstract

Timing of Train Disposition: Towards Early Passenger Rerouting in Case of Delays

Lemnian

Rückert

Rechner

et al. 2014

View full text Add to dashboard Cite

Adaptive, data-driven, online prediction of train event times

Cited by 4 publications

References 9 publications

Predictive modelling of running and dwell times in railway traffic

Predictive modelling of running and dwell times in railway traffic

Distributed model predictive control for rescheduling of railway traffic

Timing of Train Disposition: Towards Early Passenger Rerouting in Case of Delays

Contact Info

Product

Resources

About