Digital Twins in a Transport Hub

Reading Station, one of the oldest and busiest railway stations in the UK, opened in 1840 and serves as a major transport hub connecting London Paddington to the west of England and South Wales. Like many stations across the UK, Reading Station’s asset managers had a basic Building Information Modelling System and access to limited data.

With Optimise AI’s technology, they were able to understand the rhythm of Reading Station’s energy usage with total clarity. By understanding how train schedules and major dates interacted with facility usage, Reading Station was able to ensure that all facilities were only being powered when they needed to.

As a result of the insights gained from Optimise AI’s digital twin, Reading Station was able to implement strategies that saved energy and carbon emissions. This modern approach aligns with the station's recent redevelopment efforts, which included sustainable features such as energy-efficient lighting and improved accessibility, making it a more environmentally friendly and user-friendly station.

The Process

The digital twin development unfolded through:

1. An energy audit of the station.

2. Engagement with asset management team to understand operational details

3. Creation of an energy simulation model.

4. Enhancement of the existing Building Information Modelling (BIM) data.

5. Integration of data from a variety of meters and sensors.

Reading station’s key issue was a lack of data. The asset management staff had limited data collection capacities, and a basic BIM model. We therefore installed sensors on energy-intensive devices like lifts, escalators and lights. We used the data collected to build an enhanced energy model of the building. 

Our enhanced model, combined with data from the meters and sensors, formed a comprehensive digital twin of the station. Asset management staff were then able to use this digital twin to forecast various different energy-usage scenarios based on times of day or during particular events.

The Outcome

As a result of the digital twin technology, Reading’s Asset Management staff were able to:

• Visualize the energy usage of the station’s escalators, lifts and LED lights.

• Understand the impact of footfall on energy usage

• Compare real-time data with predicted data

• Understand energy requirements at different times of the day

• Correlate energy usage with C02 emissions

• Match energy usage with busy events and train schedules

• Compare the energy impact of different energy reduction strategies.

By giving Reading staff full visibility over their data, they were able to create energy strategies that improved efficiency, saved money, and reduced Reading Station’s carbon footprint.

This continues as energy management with further gains is a journey. Further submetering and sensors are being introduced to increase the insights and maximise the savings.