Equipment Usage Detection for Reducing Building Energy Demand

Abstract

In response to the global imperative to address energy consumption and reduce carbon emissions in the built environment, we present a novel approach leveraging computer vision, deep learning, and IoT technologies. Our research focuses on developing an intelligent building management system to optimize Heating, Ventilation, and Air Conditioning (HVAC) operations. The primary objective is to dynamically adjust HVAC settings based on real-time occupancy detection, ensuring energy efficiency without compromising occupant comfort. Our methodology involves the implementation of computer vision algorithms for human presence detection, with occupancy data stored centrally in a Firebase database. Additionally, we introduce a user-friendly 3D interactive website enabling comprehensive visualization and management of room settings alongside occupancy monitoring. The backend of the system, powered by a Raspberry Pi, acts as a central hub for data processing, communication, and HVAC management. Results demonstrate the efficacy of our solution in reducing energy consumption, cutting carbon emissions, and enhancing occupant comfort through optimized HVAC operations and a comprehensive management platform. The interactive 3D interface facilitates efficient monitoring and control of indoor settings, improving overall building management practices.

In conclusion, our research highlights the potential of cutting-edge technology to drive intelligent and sustainable solutions in the built environment. By integrating advanced technologies and providing users with intuitive tools, our system contributes to the overarching goal of achieving energy efficiency and environmental sustainability.