CBIM - European Training Network
Bachelor’s Degree
Civil and Environmental Engineering, National Technical University of Athens (NTUA), Greece
Master’s Degree
MEng Civil and Environmental Engineering, National Technical University of Athens (NTUA), Greece
Smart Buildings and Digital Engineering, University College London (UCL), UK
PhD Degree (Ongoing)
Environmental Engineering, University College London
Host institution: University College London
Project Title: Enabling Scalable Data-driven Building Operation
Abstract: The value that data generate is being increasingly appreciated in the context of the built environment. In particular, building data can be processed to provide operational insights, detect performance inefficiencies, and identify opportunities to improve building operation. However, these data can be available from different sources, and in a range of formats, throughout the building lifecycle, often creating silos which impede data reuse and make the configuration of data analytics cumbersome, expert-dependent, and building-specific. Recently, knowledge graphs and linked data technologies offer a promising set of tools to create a unified representation of building data and metadata, enabling a new regime of scalable data analytics applications which are developed once and deployed in multiple buildings. This vision has yet to be realised, in part due to the burden related to discovering and reusing siloed data throughout the building lifecycle which leads to ad-hoc metadata representations and incomplete information delivery to analytics application developers. To overcome these barriers, this research seeks to (1) devise a metadata integration method which facilitates data reuse in the building lifecycle to meet such requirements, (2) define a mechanism for specifying metadata requirements of reference analytics employed in building control and fault detection applications, (3) develop a completeness checking tool to ensure that metadata requirements are met and conform with a reusable structure, and (4) validate the metadata requirements of the proposed suite of reference analytics in a group of buildings. These objectives are key to enable scalable and reusable analytics which are expected to minimise dependency on manual interventions, reduce development time and modelling errors, and thus trigger rapid financial returns from massive deployment of energy-saving applications in buildings.
Enrolment in Doctoral degree: University College London, PhD in Environmental Engineering
Advisor: Dimitrios Rovas
This project has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Skłodowska-Curie grant agreement No 860555.
For more information see CBIM on CORDIS
|
Bachelor’s Degree Master’s Degree Smart Buildings and Digital Engineering, University College London (UCL), UK PhD Degree (Ongoing) |
Host institution: University College London
Project Title: Enabling Scalable Data-driven Building Operation
Abstract: The value that data generate is being increasingly appreciated in the context of the built environment. In particular, building data can be processed to provide operational insights, detect performance inefficiencies, and identify opportunities to improve building operation. However, these data can be available from different sources, and in a range of formats, throughout the building lifecycle, often creating silos which impede data reuse and make the configuration of data analytics cumbersome, expert-dependent, and building-specific. Recently, knowledge graphs and linked data technologies offer a promising set of tools to create a unified representation of building data and metadata, enabling a new regime of scalable data analytics applications which are developed once and deployed in multiple buildings. This vision has yet to be realised, in part due to the burden related to discovering and reusing siloed data throughout the building lifecycle which leads to ad-hoc metadata representations and incomplete information delivery to analytics application developers. To overcome these barriers, this research seeks to (1) devise a metadata integration method which facilitates data reuse in the building lifecycle to meet such requirements, (2) define a mechanism for specifying metadata requirements of reference analytics employed in building control and fault detection applications, (3) develop a completeness checking tool to ensure that metadata requirements are met and conform with a reusable structure, and (4) validate the metadata requirements of the proposed suite of reference analytics in a group of buildings. These objectives are key to enable scalable and reusable analytics which are expected to minimise dependency on manual interventions, reduce development time and modelling errors, and thus trigger rapid financial returns from massive deployment of energy-saving applications in buildings.
Enrolment in Doctoral degree: University College London, PhD in Environmental Engineering
Advisor: Dimitrios Rovas