Seasonal performance of an energy pile heat pump system and prediction of building thermal load

Ground source heat pumps (GSHPs) are widely used for cooling and heating buildings, which can reduce the burning of fossil fuels and contribute to the reduction of carbon emissions. Energy piles, as underground heat exchangers, have advantages over conventional buried borehole pipes, saving drilling costs and accelerating the construction period. However, few studies have focused on the actual operation of an energy pile heat pump system, and the prediction of the building thermal load can reduce the instrument arrangement and test recording time. Hence, a heat pump system was built in this study to serve a single lab using energy piles with a cap structure as the energy supply, and summer cooling and winter heating tests were conducted. Under the test conditions in this study, the GSHP had a faster start-up speed and less power consumption than the air source heat pump (ASHP), and the average coefficient of performance (COP) of the energy pile heat pump system was 3.78, which is 40.0∼51.2% higher than that of the corresponding air source heat pump system (the normative reference COP is 2.50∼2.70). The methods of higher-order surface fitting and an artificial neural network model were both suitable for predicting building thermal load.