AI in transport and mobility: advanced driver assistance systems in rail transport

Possibilities for reducing energy consumption

KI bei fahrerassistenzsystemen
© den-belitsky - iStock.com

Traction energy consumption is the primary cost factor in the electricity bills of rail transport companies, and is largely determined by how the trains are driven. Energy-efficient speed profiles can therefore lead to significant reductions in power consumption. This includes making the greatest possible use of coasting phases, during which the train consumes no energy. However, it is also vital to coordinate rail traffic with an eye to energy efficiency – for instance by avoiding excessive numbers of simultaneous departures, which result in high peak loads on the electricity grid and therefore additional charges. Moreover, it is important to synchronize arriving and departing trains so that energy recovered while one train is braking can be used to accelerate another.

Optimizing the energy consumption of the Nuremberg subway

In the project entitled »Optimization of the subway timetable to minimize energy consumption,« which was carried out in collaboration with the transit provider VAG Verkehrs-Aktiengesellschaft, experts from the ADA Lovelace Center developed optimization procedures to reduce the energy consumption of Nuremberg’s underground rail traffic. The priority here was to make optimum use of the degrees of freedom in timetable preparation – and particularly the ability to reschedule train departures to improve load balancing in the traction network over time. Building on this, the project also included optimization of the trains’ driving behavior in order to reduce overall energy consumption.

Further opportunities for improvement thanks to algorithms able to operate in real time

Based on the results obtained so far, the ADA Center application »Advanced driver assistance systems in rail transport« aims to develop algorithms that can operate in real time, representing a significant and ambitious step forward in this field. In concrete terms, this involves the real-time control of departures from stations and journeys along the route, implemented with the help of advanced driver assistance systems, with the long-term goal of automatic control of train journeys. On one hand, this requires refinement of the applied optimization models, as their computing time must allow real-time decision-making. On the other, AI methods must also be able to respond to the usual delays in operations in order to ensure that calculated speed profiles remain optimal even in the event of disruption. As these methods do not yet exist, there is a need for fundamental new developments, which should build on the approach of online learning. This AI technique, borrowed from game theory, allows sequential decision-making incorporating feedback.