The energy consumption of trains is highly efficient due to the low friction between steel wheels and rails, although the efficiency is also influenced largely by the driving strategy applied and the scheduled running times in the timetable. Optimal energy-efficient driving strategies can reduce operating costs significantly and contribute to a further increase of the sustainability of railway transportation. The railway sector hence shows an increasing interest in efficient algorithms for energy-efficient train control, which could be used in real-time Driver Advisory Systems (DAS) or Automatic Train Operation (ATO) systems. This paper gives an extensive literature review on energy-efficient train control (EETC) and the related topic of energy-efficient train timetabling (EETT), from the first simple models from the 1960s of a train running on a level track to the advanced models and algorithms of the last decade dealing with varying gradients and speed limits, and including regenerative braking. Pontryagin's Maximum Principle (PMP) has been applied intensively to derive optimal driving regimes that make up the optimal energy-efficient driving strategy of a train under different conditions. Still, the optimal sequence and switching points of the optimal driving regimes are not trivial in general, which led to a wide range of optimization models and algorithms to compute the optimal train trajectories and more recently to use them to optimize timetables with a trade-off between energy efficiency and travel times.
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.