The Potential of Control Models Based on Reinforcement Learning in the Operating of Solar Thermal Cooling Systems

The objective of this research work was to investigate the potential control models based on reinforcement learning in optimization solar thermal cooling systems (STCS) operation through a case study. In this, performance installation working with traditional predictive approach and (RL)-based analyzed compared using specific realistic simulation tool. order achieve proposed objective, system module capacity for interacting aforementioned tool developed Python. For studied period STCS operating RL, following observed: 35% reduction consumption auxiliary energy, 17% electrical pump that feeds absorption machine more precise generation energy regarding under approach. Through obtained results, advantages RL controlling regulation were verified.