IoT based building energy management system

Abstract

The ever-growing demand for energy and uncertainty of supply lead towards a major crisis in the energy sector, especially in building energy management. In case of power outages it is crucial to utilize the scarce power sources for the most vulnerable cause of demand. Furthermore, it is evident that due to the lack of monitoring and automation present in building energy management systems, a considerable percentage of energy wastage gets reported. Thus the need for a proper load forecasting methodology has arisen in the recent past. Researchers have formulated statistical methods and machine learning based models to facilitate energy forecasting for future periods. This paper addresses the load forecasting challenge by proposing an IoT (Internet of Things) based energy management system that incorporates an XGBoost (Extreme Gradient Boost) machine learning model to forecast energy consumption. The energy management system consists of a user-friendly central dashboard that acts as a mediator between a NodeMCU device and a cloud-hosted database with the aforementioned machine learning model. The paper concludes with a summarized discussion on the research.