Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Denmark

Marie Skłodowska-Curie Action · Running

AI-Heat Pump AI-Optimized Control and Integration of Transcritical R744 Heat Pumps for Sustainable Heating Solutions

Coordinator
Syddansk Universitet, Denmark
Runs
1 September 2026 to 31 August 2028
Status
Running
EU funding
€263k
Total cost
—
Partners
2 organisations in 2 countries
Type
Marie Skłodowska-Curie Action
Grant agreement
101267081

What the project is doing

In the project's own words, from its summary on CORDIS.

The heating sector is a critical challenge in the global transition toward a low-carbon society, particularly for hard-to-abate applications requiring substantial energy (e.g., residential applications). Among various green technologies, transcritical R744 (CO2) heat pumps have emerged as a future-proof solution thanks to their eco-friendly and safe refrigerant (i.e., R744). On the one hand, R744-based heating systems can reduce dependence on fossil fuels, including Russian gas, especially by integrating renewable energy sources (RESs) and hot thermal energy storages (HTESs), enhancing resilience to energy price fluctuations.

On the other hand, its energy and economic performance is hindered by suboptimal control between the heat pump and heat distribution/domestic hot water system, which becomes more complex when integrating RESs and HTES. Thus, the AI-Heat Pump project aims to develop and demonstrate the first ever artificial intelligence (AI)-driven real-time optimization algorithm to allow R744-based heating systems integrated with RESs and a HTES to always operate at the highest cost-effective conditions.

The algorithm will be implemented with respect to RES availability, HTES status, heating demand, heat pump/heat distribution status and, electricity price and it will be tested on the transcritical R744 heat pump setup at SDU. Compared to the heat pumps using conventional refrigerants, i.e., synthetic refrigerants often classified as PFAS and/or slightly flammable, the algorithm will allow R744-based heating systems to be about 15 % more cost-effective in multi-family houses.

The project will be carried out in close collaboration with the University of Edinburgh (HTES modelling) and Bitzer Electronics A/S (enhanced system control and integration). Therefore, as concrete value and impact, this project will lay robust foundations for sustainable future and thus pave the way for remarkable enhancements for business and society concerning the green heating sector.

Topics

Who is involved

OrganisationCityCountryRole
Syddansk UniversitetOdense MDenmarkCoordinator
The University of EdinburghEdinburghUnited KingdomAssociatedpartner

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI