ANN Based Optimized AHU Discharge Air Temperature Control of Conventional VAV System for Minimized Cooling Energy in an Office Building

This paper assesses the energy performance of applying optimal control of air handling unit (AHU) discharge air temperature (DAT). An artificial neural network (ANN) model was used through the link between Matlab and EnergyPlus via BCVTB to realize automatic and optimal control of the AHU DAT. As a result of this study, the predictive control algorithm was able to significantly reduce cooling energy by approximately 10%, compared to a conventional control strategy of fixing AHU DAT to 14 degrees C. These findings suggest that the ANN model and the control algorithm showed energy saving potential for various types of forced air systems by taking dynamic operating conditions into account.