Human-centric, data-driven model predictive control strategies for buildings

   School of the Built Environment

   Applications accepted all year round  Self-Funded PhD Students Only

About the Project

There is significant potential for big data and data science (e.g. Artificial Intelligence- AI, Machine Learning and Deep Learning) for optimising HVAC and electrical services and controls in buildings in order to achieve energy demand reductions as well as increase building occupants' comfort, performance, productivity and health. Current building management systems (BMS) are typically inefficient in their use of energy for maintaining building occupants’ comfort, performance and productivity as they lack real-time input of dynamic factors, such as, occupancy, occupant preferences and comfort perceptions, occupant actions and decisions. The aim of this PhD project is to develop human-centric, data-driven model predictive control strategies for large non-domestic buildings that learn their goals from real-time environmental conditions and building occupant data, instead of operating on fixed schedules, maximum design occupancy assumptions or code defined occupant comfort ranges. Coupling this dynamic data input with data science will enable the MPC strategy to learn from the indoor environments and predict internal conditions at future time instants to identify optimal operating scenarios for maintaining building occupants comfort, performance and productivity whilst reducing energy use.    

For informal enquiries about this PhD, contact Dr Rory Jones at

Architecture, Building & Planning (3) Computer Science (8) Engineering (12)

Register your interest for this project

Where will I study?

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.