Decision-making based on sensordata from rail traffic

Purpose and goal:

The project will develop a digital decision support model to identify and prioritize the right measures, which can lessen energy use and power consumption and free up capacity in railsystems. Sensor data from SL´s vehicles & infrastructure are used and potential measures are assessed in financial Business Cases to speed up the implementation process.

The goal is for the model, and a number of measures, to be implemented in SL´s traffic/systems during the project´s three years, and for the model to be made scalable to other railowners/operators with similar energy efficiency needs. Expected results and effects:

The model accelerates the transition to sustainable transport infrastructure through concrete measures that contribute to reduced energy use, and lower and more stable power consumption, in rail traffic. As a results, an increase in capacity makes it possible to produce more public transport, at the same time as costs for public transport production are reduced.

The model as a tool should, with some modification, be able to be used by other infrastructure owners, customers and operators to create transparency and knowledge sharing around decisions on energy saving measures. Approach and implementation:

Slightly simplified, TF provides data & prototype to a Model, and identifies with the operator MTR a number of potential areas in vehicles / infrastructure where there is potential for energy efficiency measures. The areas derived from practice are paired with results from current research by KTH, which becomes a guide for the development of the Model.

It is used to forecast outcomes for concrete energy efficiency measures, and Business Cases are developed to assess the benefits, costs and feasibility of the measures that the parties jointly prioritize as most effective.