The aim of this project is to use machine learning, without explicit modelling, to evaluate and optimize system and operating states of Heating, Ventilation and Air Conditioning (HVAC) systems. The focus of the optimization strategy is to plan predictive maintenance not only according to wear and associated costs but also in respect to their effects on building energy consumption and changes in the building, its environment and use. The focus of the optimization strategy is on the configuration of HVAC settings and the efficiency of maintenance planning. The added value of this approach is that there is no need to intervene in the control of the HVAC system. The developed AI can therefore also be used as a retrofit for existing systems across all manufacturers. In addition, the optimization can also take place on data from multiple systems and the learning phase of the AI algorithms used is massively shortened through pre-trained models. The core of the technical innovation is an approach consisting of a combination of reinforcement learning for HVAC operation, supervised learning for maintenance panning and an iterative control strategy based on a Model Predictive Control (MPC) architecture, which compensates the deviations caused by modelling inaccuracies. With the gained results and the proposed AI approach we want to support building owners and facility managers, planners and system integrators, manufacturers and suppliers of HVAC systems and building management systems, building operators and tenants to improve the energy efficiency of their HVAC systems.


Duration 01/04/2022 - 30/09/2024
Funding FFG

Department for Integrated Sensor Systems

Center for Distributed Systems and Sensor Networks

Principle investigator for the project (University for Continuing Education Krems) Dipl.-Ing. Albert Treytl
Project members
Back to top