Abstract
Digital Twin systems with real-time requirements are inherently complex, relying on simulation models to enhance decision-making through predictive modelling. However, the complexity of the actual system and digital twins translates into computationally expensive models, posing significant challenges when real-time constraints necessitate in-time decision-making with strict requirements for timeliness, and accuracy. This talk introduces the SACube framework to address the issue of computationally expensive models by dynamically switching between a high- validity model, the model with a broader validity frame, and models with a narrower validity frame, to achieve computational efficiency without compromising accuracy. This framework tackles questions of how, when, and where model switching happens.
About the speaker
Dr. Raheleh Biglari is a postdoctoral researcher at the University of Regensburg, Germany. She received her PhD in Applied Engineering from the University of Antwerp, Belgium, in 2025, and continued her research there as a postdoctoral researcher. Her research interests include digital twin engineering, model-driven engineering, modelling and simulation, self-adaptive systems, and cyber-physical systems. Her work focuses on model validity, runtime adaptation, and model switching, exploring how different models can be used to balance accuracy and computational efficiency in complex systems. She is also interested in AI-supported modelling, decision-oriented validation, and digital twin quality.