570. Keeping Track of Energy Efficiency in Rail Networks: A Trajectory-Based Approach
Invited abstract in session TA-57: Railways applications, stream Transportation.
Tuesday, 8:30-10:00Room: Liberty 1.12
Authors (first author is the speaker)
| 1. | Lars Geese
|
| Institute for Railway Engineering, Technical University of Darmstadt | |
| 2. | Cedric Steinbach
|
| Department of Civil and Environmental Engineering, Technical University of Darmstadt, Institute of Railway Engineering | |
| 3. | Andreas Oetting
|
| TU Darmstadt |
Abstract
The efficiency of rail operations can be improved by energy-efficient train control through Driver Advisory Systems (DAS). Practice shows that energy consumption varies significantly over time and within subsets of a network, vehicle types, and scheduled trains. For railway operators, identifying affected parts of their fleet or network and addressing the causes of increased energy consumption are crucial for improving efficiency.
A cost-effective way to collect operational data is retrofitting trains to track basic trajectory data, such as time-distance and speed-distance diagrams. This research aims to develop and implement a method for analyzing trajectory data and identifying inefficiency causes, adaptable to different rail networks and their characteristics.
The approach aims to identify patterns in deviations between calculated optimal trajectories and actual driving behavior. Beyond trajectory data, additional factors such as disruptions, equipment failures, occupancy rates, and weather conditions must be incorporated into the analysis to understand causal relationships. Therefore, statistical methods, exact trajectory and energy consumption calculations, and expert or user knowledge acquisition techniques are combined.
Preliminary findings on the key requirements of individual methods and the overall framework for their integrating are presented. Additionally, initial insights from a dataset of a German rail network, used as a case study, are included.
Keywords
- Analytics and Data Science
- Railway Applications
- Transportation
Status: accepted
Back to the list of papers