Computational BIM and Intelligent Operations

Development and demonstration of a digital twin platform leveraging ontologies and data-driven simulation models

Jakob Bjørnskov, Avneet Badhwar, De Shikhar Singh, Mohit Sehgal, Rasmus Åkesson, Muhyiddine Jradi

Published 2025

Thumbnail for Development and demonstration of a digital twin platform leveraging ontologies and data-driven simulation models

Abstract

The building sector is currently seeing rapid digitalization through IoT sensor and smart metre networks. In this regard, the concept of digital twins for building operation is a recent but promising research area concerned with the integration of IoT devices, data-driven modelling, monitoring, and optimization. In this work, a digital twin platform is presented and implemented, showcasing various applications and real-time services for improved operation of buildings. The digital twin platform is comprised of three parts: (1) a virtual representation of the physical building in the form of ontology-based and data-driven component models, (2) a data layer responsible for communication between the virtual system and the various measuring devices installed in the physical system, and (3) an interactive user interface layer, visualizing building performance. The validity and added value of the platform are demonstrated in a case study of a university building.

Topics

AI building automationCase StudyOccupant Behavior Analysis and Spatial OptimizationPredictive Analytics and Performance OptimizationSmart Building Systems and IoT Integrationadaptive controlbig data in buildingsbuilding energy forecastingbuilding energy simulationbuilding performance dashboarddigital twinshuman-centric IoTintelligent environmentspredictive analyticsreal-time monitoringsensor data integration

Cite this paper

@article{051147d2,
author = {Jakob Bjørnskov and Avneet Badhwar and Deep Shikhar Singh and Mohit Sehgal and Rasmus Åkesson and Muhyiddine Jradi},
title = {Development and demonstration of a digital twin platform leveraging ontologies and data-driven simulation models},
journal = {Journal of Building Performance Simulation},
volume = {0},
number = {0},
pages = {1--13},
year = {2025},
publisher = {Taylor \& Francis},
doi = {10.1080/19401493.2025.2504005},
URL = {https://doi.org/10.1080/19401493.2025.2504005},
eprint = {https://doi.org/10.1080/19401493.2025.2504005}
}