A new energy consumption prediction method for chillers based on GraphSAGE by combining empirical knowledge and operating data

Abstract

The energy consumption prediction of chillers plays a central role in the optimization of the energy-saving control of central air-conditioning in a high-rise building. Existing deep neural network energy consumption prediction methods hardly combine operating data with empirical knowledge. Therefore, a new energy consumption prediction method based on graph sampling aggregation (GraphSAGE) network by using empirical knowledge to construct association graphs is proposed (EK-GraphSAGE). This method first uses the empirical knowledge that analyzes the operating status of chillers and combines the operating data of chillers to construct an association graph. Then the operating data and the association graph are input into the GraphSAGE network to predict the energy consumption of chillers. At last, an on-site experiment is carried out on the cold source system in a real building. The results show that the proposed method can achieve better prediction results compared with the state-of-the-art methods.