Optimizing and Controlling Building Electric Energy Using Cat Boost Under the Energy Internet of Things

Abstract

This paper describes innovative research on the data-driven control policy for building energy-saving based on a cloud platform under four-story building energy Internet of Things (IoT) architecture. The platform devotes to provide data representation and interpretability analysis for different stakeholders to achieve flexibility and scalability; simultaneously, to improve thermal comfort while reducing building power consumption. The platform manages data from the IoT devices and builds energy management systems using a cloud-based, user-friendly human-computer interaction interface. Decisions on how to optimize the operation of building energy systems are becoming increasingly complex. Data-driven predictive control (DPC) is a control technology that replaces conventional strategies, such as rule-based control and model-based predictive control (MPC). When applied to complex building operations, control-oriented data-driven models are used to implement finite time receding horizon control. This paper adopts the CatBoost algorithm for model prediction, which is highly interpretable and easy to operate for different stakeholders. A numerical simulation case study is utilized to compare the control performance, such as the residential building power consumption, R Squares, RMSE, and Test time, with other strategies: XGBoost, TDNN, LightGBM. The results show that the investigated algorithm’s performance outperforms others’, while significantly reducing the complexity and implementation cost.