Artificial Intelligence-driven Digital Twin for Smart Buildings

Artificial Intelligence-driven Digital Twin for Smart Buildings

Project leader - main PI:

Co-PI

Researchers

Project period: 2023-08-15 to 2027-08-15

Funding: Atrium Ljunberg


Description

Digital twins and artificial intelligence (AI) are research fields that have recently become increasingly significant, both in academia and in the industry. In a collaboration with the property management company Atrium Ljungberg, this project is located at the intersection of the two fields. The aim of the project is the usage of AI methods within a digital twin, representing smart buildings.

As the data stemming from smart buildings is based on IoT devices, such as temperature sensors, solar panels and other sensors, both the digital twin and the machine learning component are based on sequential data. The role of the machine learning component is to make an accurate prediction of future values and optimization of the digital twin ecosystem. Optimizing the energy consumption of a smart building is a goal that can be achieved with the AI-driven digital twin architecture.

People

Panagiotis Papapetrou, Professor
sequential and temporal data mining, explainability, healthcare applications
Tim Kreuzer
time series analysis for digital twins