Improving Station Dwell Times

UK passenger journeys have doubled over the last 20 years and the high growth trend is expected to continue. Can reducing station dwell times support an increase in capacity and improved performance?
Dwell time image

Dwell times have a significant effect on network capacity. Increased passenger numbers are linked to longer dwell times and in turn, to a reduction in the performance measures. Even small ‘sub-threshold’ delays (i.e. tens of seconds) can adversely impact the overall performance of the network. The challenge for the rail industry is accommodating increasing demand while improving performance, without compromising safety and accessibility at the platform train interface (PTI).

To support long-term growth projections, the industry will need to embrace novel and innovative solutions. RSSB has funded three feasibility studies to explore opportunities to reduce dwell times.

The first, part of a competition to support ‘Faster, safer and better boarding and alighting’, looked at how on-board and station-mounted cameras could be used to optimise the flow rates of passengers. The project, led by the University of Lancaster, demonstrated how autonomous and data-driven techniques can alert drivers of unusual behaviour near the PTI and help operators to direct passengers to less busy parts of the platform and train to avoid potential crowding.

More recently, two projects from the ‘Data Sandbox: Improving Network Performance’ competition have been exploring how machine learning and data visualisation techniques can be applied to the dwell time challenge.

The University of Middlesex, with support from Southeastern, identified correlations and recurring patterns in an integrated dataset that were used to predict real to-the-second timing patterns of passenger services. A case study suggested that it is possible to achieve a 20% increase in real-time timetable accuracy.

The University of Southampton, with support from South Western Railway, developed high-resolution maps and visualisations for identifying dwell time hotspots. This approach was used to identify unexpected sites that could be targeted for mitigation measures. The model is expected to be able to communicate real time predictions of variation in expected dwell time to operational staff, allowing them to take the appropriate actions to reduce network delay.

Topics covered

  • Dwell time
  • Capacity
  • Platform train interface (PTI)
  • Sub-threshold delay
  • Machine learning
  • Data visualisations


Predicting and mitigating small fluctuations in station dwell times (COF-INP-03)
spark bulb
How can train dwell times be reduced? (S287)
spark bulb
Providing data analysis insights into real to-the-second timing patterns of passenger rail services using Machine Learning techniques (COF-INP-04)
Platform Train Interface Strategy (section 17)
Intelligent Computer Vision Agents Optimising PTI Safety and Train Dwell Times COF-PTI-04
Haven’t found what you’re looking for?
Get in touch with our Health and Wellness expert for more information on all aspects of Health and Wellbeing.
Cookies help us improve your website experience.
By using our website, you agree to our use of cookies.