Empowering Sustainability: The Crucial Role of IoT-Enabled Distributed Learning Systems in Reducing Carbon Footprints

Electrical energy plays a pivotal role in modern society by powering homes, industries, and transportation systems. However, the production of electricity is associated with significant carbon emissions, primarily from fossil fuel-based power generation, and there is 1.1% rise in carbon emissions by 2023 compared to 2022. Mitigating carbon emissions from electrical energy is a critical global challenge that requires a multifaceted approach. Transitioning to cleaner energy sources and improving energy efficiency are essential steps to reduce the environmental impact of electricity generation. Energy management is crucial to reduce energy consumption effectively. So this study proposes a Multi-Model Energy Management System (MEnMS) integrated with a Fractal Internet of Things (IoT) architecture to address enhanced energy management by reducing energy usage, and carbon footprint. The study conducts a detailed energy consumption analysis across distinct cases. From the analysis, it can be seen that an average of 25% of energy can be saved with MEnMS without IoT energy overhead. Key observations include, EnMS with IoT devices and automation offers smartness, they do not lead to a significant reduction in energy consumption. Moreover, these IoT devices and centralized learning consume more energy. However, integrating IoT devices with distributed learning and multiple models significantly reduces energy consumption as well as the carbon footprint. The analysis reveals that the MEnMS system outperforms alternative approaches, particularly at higher occupancy levels, establishing itself as the most efficient energy management solution. At an occupancy level of 25 users, it achieves an impressive 8% reduction in energy consumption compared to the Traditional System, showcasing its unique capability to scale energy savings as occupancy increases. This innovative system combines advanced local processing with EQC optimization, providing a cutting-edge approach to sustainable energy management in high-occupancy scenarios. Furthermore, the algorithms driving occupant-centric automation and the indoor localization method demonstrate remarkable performance, achieving an efficiency of 92% and an accuracy of 90%, respectively. Therefore, the MEnMs framework can be used to monitor energy usage thereby reducing energy consumption, which results in a low-carbon footprint. By tracking the activity, the occupants get a clear understanding of their carbon footprint and they can make adjustment to reduce carbon emissions.