In this study, an artificial neural network (ANN) based real-time predictive control and optimization algorithm for a chiller-based cooling system was developed and applied to an actual building to analyze its cooling energy saving effects through in-situ application and actual measurements. For this purpose, we set the cooling tower’s condenser water outlet temperature and the chiller’s chilled water outlet temperature as the system control variables. During the analysis, unexpected abnormal data were observed due to insufficient training data and a limited consideration of the outdoor air wet-bulb temperature when determining the condenser water temperature set-point. Therefore, it is necessary to build training data under a wide range of conditions and to set the condenser water temperature set-point lower limit to be outdoor air wet-bulb temperature +3.6°C in the outdoor wet-bulb temperature region above 23°C, so that further energy savings can be achieved.

This content is only available via PDF.
You do not currently have access to this content.