Development of Smart Real-time Monitoring System for the Determination of Household's Carbon Footprint using Interactive Energy Audits.

Abstract

The digital transformation ushering in Industry 4.0 has heightened energy consumption and carbon emissions, necessitating energy-efficient methods. This thesis tackles carbon reduction and energy efficiency through a smart real-time monitoring system for household carbon footprints using Interactive Energy Audits (IEAs), in alignment with Sustainable Development Goal 12 (SDG 12). The system aims to empower households to monitor and control energy usage, fostering awareness and behavior change towards a sustainable future. The research focuses on developing a user-friendly IEA interface for real-time energy consumption input and tracking, a robust backend system for data collection, linear regression machine learning algorithms for personalized recommendations, and cloud infrastructure for data storage and analysis. Despite advancements in energy monitoring, integrating these components with real-time data analytics and machine learning remains underexplored. The methodology includes designing an intuitive user interface, developing a robust backend for real-time data analysis, implementing machine learning for tailored recommendations, and utilizing cloud storage for data. Results demonstrate that the proposed system can reduce household carbon emissions by up to 98%, as determined by the linear regression algorithm. The model provided insights into the impact of energy consumption on the carbon footprint, enabling users to make informed, sustainable decisions and save costs. Recommendations include refining machine learning models for greater accuracy, expanding user education programs, and broader system deployment to achieve significant carbon footprint reduction. This research advances the goal of responsible consumption and production by promoting household energy efficiency and environmental awareness