This paper presents a reinforcement learning-based scheduler for energy-aware task distribution in hybrid computing architectures. The model balances energy efficiency with performance by learning from dynamic resource states, supporting sustainable operations across interconnected edge, fog, and cloud computing platforms.

Amit Rajeev Sharma, Fatima Noor Al-Kazemi, Jean Claude Bernard, Priya Sangeetha Menon, Carlos Andres Gutierrez

This paper introduces a blockchain-enabled model for energy trading. The lightweight framework enables secure peer-to-peer transactions while providing load balancing in smart grid networks, ensuring traceability and sustainability in decentralized energy exchange ecosystems with minimal computational overhead.

Chen Li Wei, Zhang Min Hao, Xu Jian Tao, Liu Feng Rong, Gao Zhi Sheng

This study presents a bio-inspired control algorithm for embedded system cooling. Mimicking biological thermoregulation, the model dynamically adjusts thermal profiles in real time, improving energy efficiency and extending hardware lifespan in embedded devices used in green technology applications.

Ravi Suresh Iyer, Elena Maria Rossi, Aditya Ramesh Kulkarni, Taro Hiroshi Nakamura, Maria Elena Gomez

We propose a neural model for optimizing wastewater treatment. It fuses multi-sensor inputs with reinforcement learning while enforcing sustainability constraints, improving operational precision, energy savings, and chemical efficiency in water treatment facilities aligned with environmental preservation goals.

Thomas Carter, Rachel Foster, Emily Wallace, Michael Bennett, Olivia Brooks

This paper introduces a predictive maintenance solution for smart agriculture. Powered by renewable energy and edge-based processing, it employs lightweight learning models to predict equipment failures while minimizing energy consumption, supporting sustainable farming and reducing operational costs.

Chen Tian Lei, Liu Xiu Wen, Zhang Hao Ming, Gao Liang Zhi, Xu Min Cheng

We present a carbon-aware orchestration approach for Kubernetes. Using real-time emission forecasting and green node prioritization, the system intelligently schedules workloads to minimize carbon impact, promoting sustainable deployment of containerized applications in cloud-native environments.

Emily Patterson, Nathaniel Clark, Laura Simmons, Benjamin Scott, Robert Hayes

This research proposes a solar-aware task allocation strategy for data centers. It integrates load forecasting and thermal modeling to optimize resource usage under renewable energy constraints, reducing environmental impact while maintaining computational reliability and uptime in sustainable digital infrastructure.

James Harrison, Olivia Matthews, Benjamin Wright, Laura Dawson, Sarah Jenkins