Our projects

The overall goal of the UrbanHP project is a structured analysis for the optimized and system-friendly integration of heat pumps into existing urban districts. The analysis is based on detailed energy models, economic and ecological assessments, as well as on a semi-virtual implementation in the real case study of a large building complex.

More information about the project can be found HERE.

In the RINGs project, various operating modes of a building complex with different weightings between costs, degree of self-sufficiency and emissions are evaluated using an optimization model to be developed. Rules and strategies are derived from this to maximize the efficiency of the hybrid energy system in relation to various objective functions in order to obtain information about resilience and behavior in blackout scenarios. A catalog of criteria and recommendations for action for the design of energy systems based on anergy networks is created.

More information about the project can be found HERE.

WELLFIT investigates sleep quality, thermal well-being and productivity using smartwatch-based mobile sensor technology in combination with Ecological Momentary Assessment (EMA). In the course of the project, nudging and just-in-time adaptive interventions (JITAIs) are developed and tested together with low-tech & low-cost cooling solutions. This enables well-informed and tailored interventions to be implemented to maintain health and productivity.

More information about the project can be found HERE.

The OctoAI project is developing the next generation of high-performance edge AI for smart buildings. We combine the concept of edge AI with user-centered energy services and are testing two edge-ready applications. More information is available here.

The semantic description (ontology) of data points is central to the scaling of data-based optimization measures in buildings. The overarching project goal is the automated extraction and generation of metadata to create ontologies from the building automation system using innovative, AI-based approaches.

The central project result is a virtual reality digital twin environment of the test areas "My Smart City Graz" and "TU Graz - Innovation District Inffeld". In this environment, users can interactively operate and visualize energy-related building simulations and Internet of Things monitoring data of the districts. Furthermore, several research questions on previously unexplored topics, such as the possibilities of coupling virtual reality with simulation models or IoT platforms, will be answered and the research results will be published internationally.

Prosumers and energy communities are part of modern energy systems. By using machine learning to detect and diagnose faults, generation and consumption data will be used to improve the availability and safety of technical systems at prosumer level. The efforts will be demonstrated and validated in the five international ECom4Future test facilities and laboratories, including a large-scale test facility with a grid-connected battery storage capacity of 140 kWh.

Always keeping an eye on water and energy in TU Graz buildings: This is to be realized with the INFRAMONITOR project. The project demonstrates how an Internet-of-Things platform enables real-time communication between buildings, various systems and staff, and how higher-level artificial intelligence optimizes and monitors energy and water consumption. The project aims to develop intelligent and sustainable buildings and energy systems. The first demonstrator is the Electronics Based Systems Center on the Inffeldgasse campus, where the water and energy supply is monitored and visualized in real time. The INFRAMONITOR is currently being further developed in several national and European projects.

The ALFA project promotes synergies between model-based and ML diagnostic methods in connection with fault diagnosis in building automation. One goal is to defuse the so-called 'cold start problem' (generally a lack of data for newly commissioned buildings). Simulations are used to create an ML model. By taking a critical look at the interpretability of ML diagnoses by XAI for transparent decision-making processes and at other synergies, new standards are set in building automation.

More information about the project can be found HERE.

In the VENTUS project, we apply current research in physics-informed AI and probabilistic-causal AI to dramatically optimize the operation and maintenance of wind turbines. Based on an analysis of failure cases and performance degradations conducted jointly with relevant stakeholders, we will aim for an explainable AI system that has the potential to reduce losses due to downtime and maintenance by 50%.

More information about the project can be found HERE.

The SELF²B project is about an AI-based self-learning and self-diagnostic fault detection and diagnostic solution (FDD) in the building portfolio of the Federal Real Estate Company. The solutions developed are demonstrated as real-time online FDD prototypes in real operation (including constant monitoring of HVAC systems and PV systems). A technology concept for "self-learning, self-optimizing" existing buildings is also being created for the next generation of efficient building operation.

More information about the project can be found HERE.

The GreenHeat project is developing interpretable AI methods for fault detection and diagnosis as well as for the optimal control of heat pumps. On the one hand, the interdisciplinary GreenHeat project aims to achieve scientific developments that go beyond the international state of the art. At the same time, the industrial partners are striving for global technology leadership for innovative energy services.

The developments in PersonAl are aimed at a radical innovation in the area of user-centered energy services in the building sector through the application of "Personal Comfort Models PCM". For the first time, personal comfort models with innovative energy services are to be integrated into building automation in a proof of concept and, in addition to modeling-specific performance indicators, a focus will also be placed on energy efficiency effects.

​The COOL-KIT project develops, demonstrates and structures system solutions for cooling buildings, with a focus on the Gründerzeit. Selected system configurations are implemented in several buildings of the participating universities, predictive control approaches are tested with the help of a digital twin based on an IoT platform and comprehensively evaluated in terms of energy technology, comfort, economy and ecology.

Climate change is causing significant social and health interactions worldwide. Heatwaves are challenging for vulnerable groups in terms of coping with everyday life. The aim of the project is to conduct a comprehensive study in nursing homes and hospitals on the topics of contactless vital sign monitoring using radar technology and linking presence information from the radar sensor to optimize energy-efficient control of building services for a healthy indoor climate.