Complex occupancy
Lecture theatres, teaching rooms, offices, libraries, laboratories, residences and sports facilities all follow different usage patterns.
Higher education
HVAC optimisation for university estates
EcoAI helps universities reduce heating, cooling and ventilation energy across complex campus buildings using the BMS infrastructure already in place.
myCoreAI works as an optimisation layer above the existing BMS. It learns how each building responds to weather, occupancy and control changes, then adjusts selected HVAC setpoints every 15 minutes within agreed comfort and operational limits.
The BMS remains the control system. EcoAI does not replace the BMS, estates team, FM provider or controls contractor — it helps the existing systems run more efficiently and continuously.
Campus challenge
University buildings are difficult to optimise manually
University estates rarely operate like standard commercial buildings. Occupancy changes throughout the day, building types vary widely, and comfort requirements can differ between teaching, research, office, residential and specialist spaces.
Specialist environments
Research and technical buildings often have tighter operational constraints, higher ventilation demand and more sensitive comfort requirements.
Large existing estates
Many universities operate mixed-age buildings with different BMS platforms, control strategies and levels of metering.
Limited manual capacity
Estates and BMS teams are skilled, but cannot continuously tune every relevant HVAC setpoint every 15 minutes across a campus.
How EcoAI supports estates teams
Existing BMS control, continuous AI optimisation
EcoAI works through the existing BMS rather than replacing it. The BMS continues to operate the building, while myCoreAI provides predictive optimisation above it.
The BMS controls
The existing BMS continues to run plant, schedules, local control loops, safeties and operational logic.
myCoreAI optimises
myCoreAI uses live BMS data, weather forecasts and learned building behaviour to identify more efficient HVAC setpoint strategies.
EcoAI delivers and verifies
EcoAI supports the implementation journey, configuration, reporting and savings review so university teams can see the operational and financial impact.
The BMS runs the building. myCoreAI continuously optimises how the building is asked to run. EcoAI delivers the UK implementation and verified savings journey.
What the AI adds
More than standard BMS scheduling
A BMS is excellent at executing configured control logic. EcoAI adds a predictive optimisation layer that learns the real behaviour of the building and continuously adjusts agreed setpoints within defined limits.
Learns the actual building
myCoreAI trains on building data to understand how indoor conditions respond to weather, occupancy and plant operation.
Predicts ahead
It forecasts how the building is likely to respond before conditions drift, helping reduce unnecessary heating, cooling and ventilation energy by using thermal inertia and pre-heating or pre-cooling ahead of demand where appropriate.
Optimises every 15 minutes
Rather than relying on occasional manual tuning, myCoreAI continuously adjusts selected HVAC setpoints at the configured cadence, helping smooth demand and avoid inefficient operation.
Protects comfort
Optimisation stays within agreed comfort limits, operating schedules and site constraints set with the university team.
If optimisation is paused or disconnected, the BMS continues to run the building using its existing logic, as it did before.
Proof in practice
Verified savings at the University of St Andrews
At the University of St Andrews Scottish Oceans Institute, EcoAI delivered verified energy and carbon savings using the existing BMS infrastructure, with no rip-and-replace and no disruption to building operation.
21.1%
HVAC electricity reduction
9.2%
Heat reduction
158 MWh
Measured energy saving
29.3 tCO₂e
Operational carbon reduction
The project shows how continuous optimisation can support university estates teams by reducing wasted HVAC energy while maintaining comfort and operational control.
University of St Andrews HVAC optimisation case study →Commercial case
A practical route to self-funding energy reduction
EcoAI is designed to make HVAC optimisation commercially practical for universities. By working with existing BMS infrastructure and avoiding major plant replacement, implementation can be aligned with operational budgets, estate priorities and verified savings.
No major infrastructure replacement
EcoAI uses the building systems already in place, avoiding unnecessary rip-and-replace projects.
Savings-led adoption
The commercial model is designed so verified savings can support the cost of the service.
Clear reporting
Energy, carbon, comfort and savings reporting supports estates, sustainability, finance and senior leadership teams.
Where it can apply
Suitable for a wide range of campus buildings
EcoAI is most relevant where HVAC is BMS-controlled and there is enough building data to support optimisation.
Research buildings
Laboratories and technical facilities
Teaching and lecture buildings
Libraries and study spaces
Sports centres
Office and administration buildings
Residential buildings where suitable BMS control is available
Each building should be assessed individually to confirm BMS access, available data points, controllable setpoints and expected savings opportunity.
Next step
Start with a university savings review
EcoAI can review suitable campus buildings, identify likely HVAC optimisation opportunities and outline a practical route to implementation using existing BMS infrastructure.