Reading Train Station

In 2022/23, OptimiseAI, in collaboration with Cardiff University and AtkinsRealis, unveiled a digital twin of Reading train station, pioneering energy and carbon emissions optimization within the station's operations.

This project exemplified the potential of deriving actionable insights from limited data through a digital twin methodology.

The digital twin development process unfolded as follows:

Conducting an energy audit of the station.
Engaging with asset management staff to grasp operational intricacies.
Creating an energy simulation model.
Enhancing the existing Building Information Modelling (BIM) data.
Integrating data from meters and sensors.

Given the station's basic BIM model and limited sensor infrastructure, the developed BIM/Energy model acted as a surrogate, simulating performance, and predicting outcomes. Additional sensors were installed on high-energy-consuming devices like lifts and escalators to provide granular insights. These surrogate models, combined with meters and sensors, formed a digital twin used to forecast, implement optimised energy, and carbon reduction strategies, aligning with operational scenarios outlined by Network Rail.

The Optimise Product deployed at Reading station provides the following capabilities:

Detailed energy consumption pattern analysis.
Graphical representation of energy usage for specific station elements.
Comparison of live, simulated, and predicted data.
Selection of analysis time intervals for focused examination.
Visualization of model predictions alongside actual data.
Scenario simulation to explore operational strategy impacts on energy consumption.
Parameter adjustments for escalator operation and lighting.
Visualization of scenario impact on energy usage.
Integration of energy usage with footfall and train schedules.
Pursuit of energy consumption optimization through scenario exploration.

By juxtaposing modelled energy consumption against real-world data and conducting scenario simulations, the system facilitates predictive and proactive energy management, driving operational efficiency, reducing energy consumption, and advancing sustainability goals.

In 2022/23, OptimiseAI, in collaboration with Cardiff University and AtkinsRealis, unveiled a digital twin of Reading train station, pioneering energy and carbon emissions optimization within the station's operations.

This project exemplified the potential of deriving actionable insights from limited data through a digital twin methodology.

The digital twin development process unfolded as follows:

Conducting an energy audit of the station.
Engaging with asset management staff to grasp operational intricacies.
Creating an energy simulation model.
Enhancing the existing Building Information Modelling (BIM) data.
Integrating data from meters and sensors.

Given the station's basic BIM model and limited sensor infrastructure, the developed BIM/Energy model acted as a surrogate, simulating performance, and predicting outcomes. Additional sensors were installed on high-energy-consuming devices like lifts and escalators to provide granular insights. These surrogate models, combined with meters and sensors, formed a digital twin used to forecast, implement optimised energy, and carbon reduction strategies, aligning with operational scenarios outlined by Network Rail.

The Optimise Product deployed at Reading station provides the following capabilities:

Detailed energy consumption pattern analysis.
Graphical representation of energy usage for specific station elements.
Comparison of live, simulated, and predicted data.
Selection of analysis time intervals for focused examination.
Visualization of model predictions alongside actual data.
Scenario simulation to explore operational strategy impacts on energy consumption.
Parameter adjustments for escalator operation and lighting.
Visualization of scenario impact on energy usage.
Integration of energy usage with footfall and train schedules.
Pursuit of energy consumption optimization through scenario exploration.

By juxtaposing modelled energy consumption against real-world data and conducting scenario simulations, the system facilitates predictive and proactive energy management, driving operational efficiency, reducing energy consumption, and advancing sustainability goals.

In 2022/23, OptimiseAI, in collaboration with Cardiff University and AtkinsRealis, unveiled a digital twin of Reading train station, pioneering energy and carbon emissions optimization within the station's operations.

This project exemplified the potential of deriving actionable insights from limited data through a digital twin methodology.

The digital twin development process unfolded as follows:

Conducting an energy audit of the station.
Engaging with asset management staff to grasp operational intricacies.
Creating an energy simulation model.
Enhancing the existing Building Information Modelling (BIM) data.
Integrating data from meters and sensors.

Given the station's basic BIM model and limited sensor infrastructure, the developed BIM/Energy model acted as a surrogate, simulating performance, and predicting outcomes. Additional sensors were installed on high-energy-consuming devices like lifts and escalators to provide granular insights. These surrogate models, combined with meters and sensors, formed a digital twin used to forecast, implement optimised energy, and carbon reduction strategies, aligning with operational scenarios outlined by Network Rail.

The Optimise Product deployed at Reading station provides the following capabilities:

Detailed energy consumption pattern analysis.
Graphical representation of energy usage for specific station elements.
Comparison of live, simulated, and predicted data.
Selection of analysis time intervals for focused examination.
Visualization of model predictions alongside actual data.
Scenario simulation to explore operational strategy impacts on energy consumption.
Parameter adjustments for escalator operation and lighting.
Visualization of scenario impact on energy usage.
Integration of energy usage with footfall and train schedules.
Pursuit of energy consumption optimization through scenario exploration.

By juxtaposing modelled energy consumption against real-world data and conducting scenario simulations, the system facilitates predictive and proactive energy management, driving operational efficiency, reducing energy consumption, and advancing sustainability goals.