Local vs. integrated control of a variable refrigerant flow system using artificial neural networks

Abstract

Existing studies have treated variable refrigerant flow (VRF) control as a local control problem where control variables are determined using only local state information. This study investigates an integrated VRF control in which the VRF control actions are determined based on not only local information but also the dynamics of the room it serves. For this purpose, two artificial neural network simulation models were developed: one to predict indoor air temperature of the room and the other to predict the VRF’s compressor power. The ANN simulation models were validated with 192 experiments conducted in an experimental chamber. The results revealed that the integrated control reduced cooling and compressor energy use of the VRF by 21.6% and 13.1%, respectively, compared to the local control. These energy savings were achieved because the integrated control ANN models were aware of the dynamic relationship between the VRF and the target room.