Fraunhofer ISE, EDF developing AI-based heat pump controller

The Fraunhofer Institute for Solar Energy Systems (Fraunhofer ISE) and EDF are leading an international consortium developing AI-driven heat pumps that adapt to environmental conditions and learn from changing circumstances.

Self-learning heat pump control with AI system model

Image: Fraunhofer ISE

Share

Germany's Fraunhofer ISE is leading an international consortium developing AI-driven heat pumps designed to avoid incorrect settings and adapt to environmental conditions.

The consortium includes French energy giant EDF, German heating manufacturer Stiebel Elton, and French research institutes CEA List and LPNC.

The AI-powered heat pumps will feature a smart controller capable of tracking room temperature changes. Using an artificial neural network, the system analyzes a building's thermal behavior and calibrates the heat pump's flow temperature accordingly.

“In this project, the specific building behavior patterns, e.g., how it changes with varying solar radiation, is learned by artificial intelligence (AI) which continuously analyzes recorded measured values,” Fraunhofer ISE said in a statement. “Only reliable and trustworthy methods that guarantee safe operation will be accepted by heat pump manufacturers and their customers.”

The research team conducted a series of simulations on the AI-based heat pump controller in three different buildings for a period of one heating season.

“The questions on self-calibration and the adaptability to new environmental conditions were both answered positively,” the scientists said. “Depending on the building, the resulting energy savings were shown to be 13% on average compared to the standard heating curve.”

Matching the reference room temperature with the setpoint temperature was crucial for the controller's performance. “Further energy savings can be expected if the controller is extended to include the efficiency characteristics of the heat pump,” the researchers said.

They also tested the controller in a real building for one week and found it “significantly” improved the heat pump's coefficient of performance (COP).

“Compared to the reference period, the AI controller recorded a COP increase of 25%, although this needs to be evaluated in more detail during longer field test series and with different building types,” they said. “Notable is that the algorithm led to the establishment of stable heating curve parameters after just a few days.”

EDF has tested the controller's efficiency for producing domestic hot water (DHT) and found the heat pump reduced power consumption by up to 8%.

This content is protected by copyright and may not be reused. If you want to cooperate with us and would like to reuse some of our content, please contact: editors@pv-magazine.com.

Popular content

Daikin launches air-to-water heat pumps for single-family homes
16 December 2024 Daikin has released a line of residential heat pumps, using propane (R290) as the refrigerant, with outdoor unit dimensions of 1,122 mm x 1,330 mm x 6...