Smart buildings and digital engineering
The recent revolution in digital technology and cyber-physical systems has the potential to reduce costs and overcome barriers to energy efficiency through advanced control and operation of building HVAC systems. Digitalisation has had a transformative impact in many areas. The Smart Buildings and Digital Engineering theme seeks to envisage how digitalisation changes how built assets are designed, constructed and operated.
The Internet of Things (IoT) provides access to more diverse, low-cost data on the status and activity of equipment and people in buildings. Artificial intelligence and data analytics; enable more comprehensive energy performance assessment and predictive management of assets. Collaborative design and project delivery platforms enable new opportunities for collaboration and multi-stakeholder interaction to achieve improved design and outcomes.
The activities within the Smart Buildings and Digital Engineering theme seek to understand and explore the potential of applying these technologies and how these technologies can be used to create better quality outcomes for end-users and all stakeholders.
The International Energy Agency highlighted in the 2019 Energy Efficiency report the role that digitalisation will have in the built environment; the concept of digitalisation is explained as “the increasing interaction and convergence between the digital and physical worlds” where “the digital world has three fundamental elements: data, analytics, connectivity”.
‘A building that uses digitalisation technologies to dynamically optimise its operation, where optimisation objectives typically relate to site energy use, IEQ, and occupant experience. Ideally, it is sufficiently connected and integrated with markets and processes to respond to externalities adaptively and changing conditions (e.g. weather, electricity prices, energy supply constraints, equipment maintenance, etc.). Ideally, it has sufficient memory of past events and the ability to anticipate future impacts, and it can select an informed course of action for achieving higher-level objectives – reminiscent of human intelligence. To achieve this vision, a Data-Driven Smart Building utilises live and historical data from relevant sensors, IoT equipment, mobile devices, and other sources to provide situational awareness for informed decision-making. Achieving the optimisation objectives will often benefit from advanced supervisory-level automation, driven by computational analysis (e.g. Machine Learning, AI, etc.) applied to available data.’
Topics covered include:
- Advanced use of simulation (whole building, component-based) and co-simulating a building, its systems, control and users.
- Information modelling and management (BIM, ontologies, data integration, interoperability)
- Data-driven applications like smart energy management, demand response, and building-to-grid)
- Digital building twins
- BIMERR - BIM-based holistic tools for Energy-driven Renovation of existing Residences
- BuildOn - Affordable and digital solutions to Build the next generatiON of smart EU buildings
- CBIM – Cloud-based Building Information Modelling
- COGITO - Construction-phase digItal twin model
- DigiBuild - High-Quality Data-Driven Services for a Digital Built Environment towards a Climate-Neutral Building Stock
- IEA Annex 81 on Data-driven Smart Buildings
- IEA Annex 84 on Demand Management in Buildings in Thermal Networks
- LSOM - London Solar Opportunity Map
- Decarbonising Technologies - Knowledge Transfer Partnership with Tesco
Smart buildings and digital engineering in teaching
The Smart Buildings & Digital Engineering MSc is embedded in our teaching at the UCL Institute for Environmental Design and Engineering. The world is changing at a faster and faster rate, and so are our buildings. Digital modelling tools and technological advances, like the Internet of Things, provide unparalleled insights and data on how our buildings are designed and operated. As such, we developed a programme that takes a forward-looking view on the impact of this digital transformation to the established discipline of Building Services Engineering.
Smart Buildings and Digital Engineering MSc
Delivering smarter buildings and a better built environment for the interconnected, sustainable world of tomorrow.
- Machine Learning in Smart Buildings
- Building Systems Modelling
- Integrated Building Design for Health and Wellbeing
- Building Systems Physics
- Engineered Environmental Elements
- Integrated Building Systems Simulation
- Dissertation: Smart Buildings and Digital Engineering
Doctoral Research (PhD)
Our doctoral researchers cover a broad range of topics in the broader context of our UCL Institute for Environmental Design and Engineering vision and themes, looking at factors related to both the physical environment and people. Recent dissertation topics in the area include:
- Explainable Machine Learning for Building Energy Consumption Prediction
- A practical application of linked data technologies for thermal comfort and indoor air quality assessment: UCL Student Centre case study
- Performance analysis of non-intrusive loads disaggregation on non-domestic buildings using machine learning
- Predictive HVAC control based on model-based reinforcement learning
Doctoral research relating to Acoustics & Soundscapes
- Guokai Chen: 'Control Rule Extraction in HVAC systems using Model Predictive Control'
- Alex Fung: 'Timeless Digital Twins for the Energy Health Nexus'
- Cheng Cui: 'A robust and efficient optimisation framework towards heat resilience in retrofitted dwellings'
- Zoe Xie: 'Physics-informed Machine Learning Modelling for Multi-scale Building Energy Systems with Enhanced Accuracy and Interpretability
- Joanna Xie: 'Cognitive Digital Twins for Adaptive Smart Building Energy Management'
- Jingfeng Zhou: 'Cost-benefit analysis of achieving net zero targets across the UK hospitality sector'
- Anneka Kang: 'Investigating the reduction in heating emissions brought about by PVT and storage systems in urban areas'
- Ziyan Wu: 'Reinforcement learning environment for multiple agents at the district level during demand response'
- Dimitrios Mavrokapnidis: 'Enabling Scalable Data-driven Building Operation'
- Seunghyeon Wang: 'Development of a deep learning model for window and blind state prediction'
- Vasiliki Kourgiozou: 'Integrated multi-vector smart energy systems at building, campus and neighbourhood scales'