Journal of Earth & Environmental Waste Management
ISSN: 3065-8799 | DOI: 10.64030/3065-8799
Jasphynth J, Jasperline T and Daniel Raj.K
The rapid growth of artificial intelligence (AI) has revolutionized industries but has also led to significant energy consumption, primarily due to reliance on centralized cloud computing. Edge AI, which processes data locally on edge devices, presents a sustainable alternative by reducing energy-intensive data transmission and reliance on energy-hungry data centers. This research explores the designand implementation of energy-efficient AI algorithms tailored for edge devices, focusing on minimizing computational and memory requirements. Key areas of investigation include lightweight neural networks, model compression techniques, and hardwaresoftware co- optimization. The study also highlights the role of Edge AI in enabling sustainable Internet of Things (IoT) applications, such as smart cities, precision agriculture, and renewable energy management. By addressing challenges like device power constraints, security, and scalability, this research aims to establish Edge AI as a cornerstone of sustainable computing. The findings emphasize the potential of Edge AI to contribute to global sustainability goals by reducing the carbon footprint of AI systems while ensuring efficient and localized intelligence.