The challenges of using live-streamed data in a predictive digital twin

Ruchi Choudhary

Cambridge University

A key component of a digital twin is the monitored data, communicated from the physical system to the virtual representation for visualization and simulation. Yet little attention has been paid to the practicalities of working with live-streamed data. Strategies are required for providing continuous access and storage, for processing data of indeterminate quality, and for ensuring long-term sustainability of data communication systems. This talk will discuss the informativeness of streamed data, the key to successful digital twin development and operation. It will argue for the need for techniques for ensuring data quality and forecasting efficacy. Digital twins operated commercially are rarely described in detail; the discussion provides a basis for future collaborative development of a consistent operational and interactive framework.

Ruchi Choudhary is Professor of Architectural Engineering in the Engineering Department at University of Cambridge. She specializes in simulation methods for predicting energy demand of the built environment. At Cambridge, she leads the multi-disciplinary Energy Efficient Cities Initiative, initially funded by a Science & Innovation award at Cambridge. She has lead the research group on Digital Twins of Built Environment at the Alan Turing Institute (2018-2022). She is leading projects on modelling underground heat and city-scale geothermal systems, district energy networks, urban-integrated farming, and end-use energy demand in buildings. In 2019 she became fellow of the International Building Performance & Simulation Association (IBPSA). She is on the editorial board of J. of Building Performance Simulation, BSER&T the CIBSE Journal, Sustainable Cities and Society, and ICE J. of Smart Infrastructure & Construction.

https://columbiauniversity.zoom.us/j/93791853269?pwd=cm5BZm1xSTcwZmg2L256QUVWOFQ2QT09

Meeting ID: 937 9185 3269

Passcode: 103368