ACTLab coordinates the EU GreenerBuildings project. In GreenerBuildings, ACTLab is working on algorithms for occupant activity and building context recognition to provide the key information needed to adaptively control energy consumers. Moreover, ACTLab makes efforts to establish living-lab facilities and develops ubiquitous sensing solutions, adapted to the needs of public buildings. GreenerBuildings is part of the smart environments projects cluster at ACTLab.
Buildings account for more than 40% of energy consumption and are the largest CO2 producers in many world regions. Thus, making efficient use of energy in buildings is paramount to conserve energy and reduce greenhouse effects. To date, automated control and adaptation in buildings are often limited to occupant commodity changes of indoor climate depending on room temperature, CO2, or lights operated through motion detectors. GreenerBuildings investigates energy-efficient operations based on activity and behaviour of building occupants. The project aims to realise an integrated solution of energy-aware adaptation from basic (partly energy harvesting) sensors and actuators, up to an embedded software for coordinating thousands of smart objects with the goals of optimising a building’s energy consumption and user satisfaction.
Our vision is that buildings can respond to their actual use and changes in their environment; interact with their occupants through novel ubiquitous sensing and occupant behaviour inference techniques and that a building’s function and operation can be transparently adapted. The project embraces the following key principles in order to achieve its goals:
- a living-lab experimentation and validation scheme,
- an agile cross-domain consortium,
- a spiral development model, and
- a user-centric approach.
In particular, the validation will consider test cases with densely distributed devices (sensor and actuator nodes), deployed in living-lab office buildings. It is expected that other building types could similarly benefit from the GreenerBuildings framework. With its multi-national consortium, the project’s outreach will go beyond European borders.
GreenerBuildings aims at developing an energy-aware framework based on embedded service middleware and a building-distributed architecture of smart objects. The framework relies on advances of ubiquitous ultra-low power sensing, sensor-based human activity recognition, and device orchestration, to guarantee responsiveness, scalability, and dependability in its goal to achieve energy savings at the whole building level. The key to effective energy management in buildings depends on several functions, most notably, low-maintenance activity and building context sensing, robust recognition and sensor-based inference, and the framework’s scalability to massively distributed installations.
GreenerBuildings addresses these functions in its technical architecture and allows retrofitting all solutions into existing buildings. The GreenerBuildings architecture specifically emphasises occupant activity and behaviour as the key element for adaptation. The building adaptation concept foreseen in GreenerBuildings follows a layered representation to decouple different abstractions.
The ubiquitous system layer. This layer consists of physical devices, in particular, building-distributed ubiquitous sensing, processing, and actuation architecture of GreenerBuildings. Moreover, it comprises the occupant activity and building context recognition functionalities. These smart objects are physically distributed to support the sensing and actuation tasks. At the same time, nodes interact to perform operational adaptations.
The service composition layer. This layer comprises the abstract composition and orchestration functionalities of the energy-aware framework. Services in the GreenerBuildings architecture are dynamically composed to achieve the energy optimisation and user goals, using triggering events and state change information provided by the ubiquitous system layer’s sensing nodes and user interactions.
Selection of Publications
"Mining hierarchical relations in building management variables", Pervasive and Mobile Computing, ScienceDirect, February 2016.,
"Mining relations and physical grouping of building-embedded sensors and actuators", Proceedings of the International Conference on Pervasive Computing and Communications (PerCom '15), IEEE, March 2015.,
"An Intervention Study on Automated Lighting Control to Save Energy in Open Space Offices", PerEnergy 2015: IEEE International Conference on Pervasive Computing and Communications Workshops, IEEE, March 2015.,
"Using implicit user feedback to balance energy consumption and user comfort of proximity-controlled computer screens", Journal of Ambient Intelligence and Humanized Computing, February 2014.,
"Novel stochastic model for presence detection using ultrasound ranging sensors", IEEE International Conference on Pervasive Computing and Communications Workshops (ACOMORE '14), IEEE, 2014.,
"Recognizing energy-related activities using sensors commonly installed in office buildings", SEIT 2013: Proceedings of the 3rd International Conference on Sustainable Energy Information Technology, Elsevier, 2013.,
"An opportunistic activity-sensing approach to save energy in office buildings", eEnergy 2013: Proceedings of the Fourth International Conference on Future Energy Systems, ACM, 2013.,
"Improving Energy Efficiency through Activity-Aware Control of Office Appliances using Proximity Sensing - A Real-Life Study", SEnAml 2013: Proceedings of the 5th International Workshop on Smart Environments and Ambient Intelligence, IEEE, 2013.,
"Using a thermopile matrix sensor to recognize energy-related activities in offices", SEIT 2013: Proceedings of the 3rd International Conference on Sustainable Energy Information Technology, Elsevier, 2013.,
"Service-Oriented Architecture for Smart Environments (Short Paper)", SOCA 2013: Proceedings of the IEEE 6th International Conference on Service-Oriented Computing and Applications, IEEE, 2013.,
"A distributed PIR-based approach for estimating people count in office environments", EUC 2012: Proceedings of the 10th IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, IEEE, 2012.,