University of Cambridge > Talks.cam > Engineering Department Structures Research Seminars > Upscaling Building Semantics to Address Urban Sustainability and Resilience Scenarios

Upscaling Building Semantics to Address Urban Sustainability and Resilience Scenarios

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Karen Mitchell.

Smart cities and the industrial systems that compose them, such as power grids, water distribution networks, and district heating / cooling networks, are facing increasing pressures towards sustainability, resilience, and service quality. Artificial intelligence, and ICT in general, has been acclaimed as the solution to these challenges as it offers the potential to sense, contextualise, infer, and actuate the physical environment remotely, informed by wider environmental conditions, whilst using machine processing power to assist with the feedback and decision making process.

Semantics play a key role in facilitating this process. However, the IFCs (commonly referred to as BIM ), have shown their limitation in dealing with complex built environment scenarios. The research community has recently developed a wide range of semantic resources with a higher order semantic expressiveness in the form of ontologies.

The above has formed the focus of the BRE Centre of Excellence at Cardiff University who have developed a TRL 6 Computational Urban Sustainability Platform (CUSP), underpinned by a rich and cross-disciplinary semantic referential. CUSP is a semantic middleware system capable of interpreting (near) real-time data originating from a wide range of sensing nodes at a Zone, Building, Block of Buildings, or District level, to deliver performance accounts informed by domain simulation models, as well as a forecasting and optimisation capability. The unique features of CUSP involve the use of semantics (data models, such as BIM , and ontologies) for the holistic management of the performance of the built environment. Our semantic models are augmented with self-updating intelligence (including algorithms), rooted in the conceptualization of the domain / phenomenon (i.e. our set of loosely coupled ontologies) capable of dealing with heterogeneous data sources and (near) real-time changing conditions.

CUSP adopts a divide-and-conquer approach in that complexity of the built environment is broken down into a set of discrete but related scenarios, each of which formally described and detailed in terms of dependent and independent governing variables and their complex interactions through mathematical approximations. These variables and the resulting mathematical formulations are also rooted in the ontology in that all used variables are semantically described within our conceptualization of the domain / phenomenon under investigation.

In that respect, our proposed approach addresses the limitations of current IoT and SCADA -based commercial systems and paves the way to the emerging vision of Semantic Web of Things. Moreover, our approach factors in the intrinsic relationship between: (a) the network of sensing nodes present in a building or a district that capture a dynamically changing environment, (b) the intrinsic / physical properties of the artefacts involved (e.g. buildings) and© the actuation system delivered through a control system (e.g. building management system).

Biography: Professor Yacine Rezgui is a BRE (Building Research Establishment) Chair in `Building Systems and Informatics`. He is the Director of the BRE Trust Centre of Excellence in Sustainable Engineering. He conducts research in the following areas: (a) Building Informatics with a focus on semantics (BIM and Ontologies), (b) Building and District Energy Management (with a focus on the next generation energy control systems), (c) Catchment and Urban Water Management (including modelling, data analytics, and optimization), (d) Resilience of the Built Environment to Natural Disasters, and (e) Smart Cities. He has over the last 20 years completed in the capacity of principal investigator and co-investigator over 40 RCUK , InnovateUK, and EC (FP5, FP6 , FP7) projects. He is currently progressing as Principal Investigator 4 H2020 projects and as Co-Investigator an FP7 and a NERC project all addressing semantic-based analytics for building and district performance modelling, simulation, and optimisation. He has over 180 refereed publications in the above areas, which appeared in international journals such as IEEE Transactions on Systems, Man, and Cybernetics; Proceedings of the Royal Society A; Expert Systems with Applications; IEEE Transactions on Service Computing; and IEEE Transactions on Automation Science and Engineering.

This talk is part of the Engineering Department Structures Research Seminars series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

 

© 2006-2017 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity