Performance improvement of air-source heat pump via optimum control based on artificial neural network

Abstract

The use of air source heat pump (ASHP) systems is an economically viable strategy for building decarbonization. However, the ASHP energy performance deteriorates under severe conditions around a building. Researchers have conducted studies for optimal compressor control to overcome these limitations. Despite these efforts, users can seldom perform the optimal regulation of heat pump systems because manufacturers are reluctant to relinquish control to them. Therefore, we developed an artificial neural network (ANN)-based optimum control logic (OCL) system such that users can directly control and optimize heat pump systems without a compressor. The developed ANN-based OCL controls the secondary-side working fluid of the heat pump considering general building conditions, and its practical applicability has been verified using dynamic simulation. The improvement in the energy performance of the optimum models with respect to the conventional models was: 1.52% and 3.58% for the cooling and heating system COP, respectively, and 0.76% and 0.81% for the heat pump COP. These results demonstrate the potential for reduction in the carbon footprint of a building while maintaining comfort by enabling the energy-efficient operation and stable load response of the heating and cooling system.