Enhancing Air Conditioning System Efficiency Through Load Prediction and Deep Reinforcement Learning: A Case Study of Ground Source Heat Pumps

This study proposes a control method that integrates deep reinforcement learning with load forecasting, to enhance the energy efficiency of ground source heat pump systems. Eight machine learning models are first developed to predict future cooling loads, and the optimal one is then incorporated into deep reinforcement learning. Through interaction with the environment, the optimal control strategy is identified using a deep Q-network to optimize the supply water temperature from the ground source, allowing for energy savings. The obtained results show that the XGBoost model significantly outperforms other models in terms of prediction accuracy, reaching a coefficient of determination of 0.982, a mean absolute percentage error of 6.621%, and a coefficient of variation for the root mean square error of 10.612%. Moreover, the energy savings achieved through the load forecasting-based deep reinforcement learning control method are greater than those of traditional constant water temperature control methods by 10%. Additionally, without shortening the control interval, the energy savings are improved by 0.38% compared with deep reinforcement learning control methods that do not use predictive information. This approach requires only continuous interaction and learning between the agent and the environment, which makes it an effective alternative in scenarios where sensor and equipment data are not present. It provides a smart and adaptive optimization control solution for heating, ventilation, and air conditioning systems in buildings.