This work introduces a resource scheduler that factors in the carbon intensity of data centers. It routes AI workloads to low-emission zones, ensuring sustainable operations in globally distributed cloud environments.

Robert Jennings, Emily Clarke, Olivia Hamilton, Sarah Bennett, James Matthews

This paper introduces a predictive maintenance system that alerts users before device failure. It promotes timely intervention and component reuse, aligning consumer electronics use with circular economy goals and sustainability principles.

Neha Meera Sivan, Jean Claude Boucher, Fatima Noor Al-Saleh, Priya Kavitha Ramesh, Carlos Fernando Martinez

We propose a solar-powered AI edge system for water monitoring. It detects pollution in real-time with minimal energy use, enabling autonomous, eco-friendly surveillance of lakes, reservoirs, and protected watersheds.

Chen Ming Rui, Liu Hao Sheng, Zhang Yuan Cheng, Gao Wen Jie, Xu Fang Bo

This paper proposes a federated learning model that schedules client tasks based on solar energy availability. It enhances training efficiency while promoting carbon-conscious computation in energy-constrained edge networks for long-term, sustainable AI deploymen

Amit Ramesh Iyer, Fatima Noor El-Sayed, Jean Claude Laurent, Priya Sushma Reddy, Carlos Manuel Gutierrez

We present a cloud service load balancer that dynamically distributes workloads based on carbon intensity and data center heat metrics. It ensures sustainable operations while preserving service quality across multi-zone cloud deployments.

Chen Zhi Liang, Xu Hao Wei, Liu Feng Rong, Zhang Ming Ze, Gao Rui Chen

This research introduces a smart waste sorting solution using low-power edge AI. It classifies recyclables at collection points, reducing labor and emissions from waste transportation while supporting scalable, sustainable urban sanitation.

Emily Peterson, James Carter, Laura Simmons, Nathan Brooks, Sarah Monroe