| 1. |
- Minbashi, Niloofar, 1990-
(författare)
-
Application of Predictive Analytics for Shunting Yard Delays
- 2023
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Increasing the modal share of rail freight transport is one of the main ways to achieve carbon neutrality in Europe. The perceived low reliability and predictability of rail freight services is one of the main challenges to overcome in reaching this target. Shunting yards play an important role in providing more reliable and predictable freight trains. Shunting yard departure deviations impact other trains on mixed-traffic railway networks. Predictable departures from shunting yards increase the overall predictability of freight train runs along the network.The primary focus of this thesis is on how to apply data-driven approaches to increase the predictability of shunting yard departures. Descriptive analytics were used to provide enhanced insight into shunting yard departures, and predictive analytics were applied to develop shunting yard departure deviation prediction models. Finally, hybrid modeling was used to integrate the yard departure prediction model with other simulation models for wider application. The results from this thesis contribute to providing a deeper understanding of shunting yard departure deviations, interactions between shunting yards and the network through departure and arrival deviations, and how to model these deviations by applying data-driven approaches. These results from five published research papers are included and presented in this doctoral thesis.Descriptive analytics methods are applied in papers I and II to explore the probability distribution of departure deviations and the impact of the network on departure delays. The results show that positive and negative departure deviations have different distributions for different shunting yards. Moreover, network usage fluctuations over shorter timespans impact departure delays, whereas no correlation is established between network impact, defined as congestion in the arrival yard, and departure delays.Predictive analytics is applied in paper III by developing tree-based algorithms to classify the status of shunting yard departures. The departure status are imbalanced; the majority are early, and the minority are delayed. The results show that applying methods to overcome imbalanced data sets can improve the prediction of delayed departures.The models developed in paper III are extended in papers IV and V to predict departure deviations in a combined modeling approach for two separate applications. In paper IV, a machine learning-assisted macro simulation model framework is introduced to integrate yard departure predictions into a macro simulation network model and predict the arrivals to the next yard. The results show improved prediction accuracy compared to a basic machine learning model and a baseline timetable model.Finally, in paper V, the generalization of the yard departure prediction model is explored by applying a simulation-assisted machine learning modeling approach where the model is trained on real-world European yard data and North American simulation yard data. The results show the model has a notable generalized performance with both data types.
|
|
| 2. |
- Warg, Jennifer, 1983-
(författare)
-
Timetable Analysis based on Social Cost and Simulation
- 2022
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The timetable is essential for railway traffic. Its design affects rail operations – and by extension all operators, passengers, and freight clients. International practice for capacity allocation varies and there is no common algorithm for designing and evaluating timetable changes. Especially challenging is coordinating heterogeneous services competing for track capacity. Aim of this thesis is to improve efficiency and transparency in capacity allocation by new methods to assess timetable adjustments. Although integration of capacity analysis and socio-economic evaluation is beneficial, combination of the two methods is rare. Because of that, two types of model are proposed in this thesis: The first combines capacity variables and social costs to represent the goodness of a timetable slot or a timetable using performance indices describing the travelling time experience of passengers riding the trains. Historical delay data from existing timetables provides information about the performance under operation. For strategies, a combined timetable and simulation approach is proposed to reveal variables for input to performance evaluation models. We show that microscopic simulation is advantageous for estimating operational data. Because departures ahead of schedule are common for freight trains suffers a simulation that does not include that feature of inaccuracies. Because of that, we suggest an approach for including early freight train departures to improve the accuracy of simulation results. Simulation with a macroscopic tool can speed up evaluation and improve user-friendliness of the method. For relatively small changes such as changed departure times and supplements which is focus in this work however, the microscopic tool shows greater advantage. The second model type considers conflicts between commercial long-distance trains and publicly controlled short-distance traffic competing for track capacity. We propose a method to calculate the loss of societal benefits incurred by changing the commuter train timetable to accommodate a commercial train path request. The calculation of these benefits considers changes in commuter train passengers’ travel times, waiting times, transfers and crowding for all trips in the system in combination with changes in operating costs for operator(s) of the short-distance services. All methods are applied in case studies and can (with adaptions) be used for other lines to improve the timetable allocation process, and to support transparent conflict solution. However, choosing an adequate model configuration is essential as it can affect results significantly.Research was conducted for the two Swedish mainlines for passenger traffic (one articles includes an extension for a freight-focussed line), plus the Stockholm commuter network. The majority of the thesis concentrates on passenger traffic, and in particular, the conflict between long- and short-distance services. In addition to methodological contributions, we provide several practical results. We present strategies for improving reliability and evaluate them. Simple small changes in the timetable (such as changed departure times or time supplements) can have significant impact on the goodness of one or several timetable slots.
|
|
