Energy usage prediction based on multi-system data for public buildings using machine learning methods

The Heating, Ventilation, and Air Conditioning (HVAC) system accounts for a significant portion of the energy consumption of the public building system, and using an efficient power prediction model can assist engineers in making effective energy-saving improvements. Unlike traditional energy consumption prediction models, this paper uses XGBoost to extract features from large data sets and train them separately. The experimental results show that our model outperforms LightGBM's independent prediction results when using Mean Absolute Error (MAE) to infer power consumption-related variables.that our model outperforms other classical models. The proposed model is successfully applied to an Internet of Things(IoT) platform.