Neural predictive control for single-speed ground source heat pumps connected to a floor heating system for typical French dwelling

Abstract

Ground source heat pumps connected to a floor heating system can offer high efficiency for heating and cooling. However, the inertia of the floor heating creates a thermal lag that can lead to discomfort with conventional controllers. For this reason, a neural predictive controller for single-speed ground source heat pumps systems was developed. The objective of the controller is to minimize the energy consumption and maintain a good comfort level anticipating the thermal behavior of the building and external disturbances. A new neural network module for the heating power prediction of a single-speed ground source heat pumps system is proposed. The operation of the controller has been tested by simulation on a typical French dwelling during the month of March. In addition to an increase of comfort, numerical results showed that the predictive controller can provide up to 18% energy savings with the studied building in comparison with conventional controllers. Practical Implications: Ground source heat pumps are currently equipped with conventional controllers that are not necessarily suited for such systems, leading to overconsumption and discomfort. In the medium term, ground source heat pumps could be equipped as standard with predictive controllers as presented here. Further work needs to be done to evaluate the feasibility of such an implementation as regards the return on investment and the controller’s robustness.