Technology Category
Planning, Routing, and Scheduling: Planning with Language ModelsMachine Learning: Efficient ML / Green AIConstraint Satisfaction and Optimization: Distributed CSP/Optimization
COUNTER: Cluster GCN based Energy Efficient Resource Management for Sustainable Cloud Computing Environments
🤖 AI Summary
To address the critical challenge of escalating energy consumption in cloud data centers driven by surging AI workloads—thereby impeding sustainable operations—this paper proposes a carbon-aware resource scheduling framework based on Cluster Graph Convolutional Networks (Cluster GCN). It is the first work to introduce Cluster GCN into cloud resource management, integrating joint energy-performance modeling with a QoS-constrained reinforcement learning scheduling policy to jointly optimize dynamic load balancing and low-carbon operation. Evaluated on a simulation platform against the carbon-neutral baseline HUNTER model, the proposed approach achieves a 23.6% improvement in resource utilization, an 18.4% reduction in energy consumption per unit computation, and a 15.2% decrease in operational cost. The framework features architectural lightweighting and synergistic energy-efficiency optimization, establishing a scalable new paradigm for sustainable cloud infrastructure.
Technology Category
Application Category
📝 Abstract
Cloud computing, thanks to the pervasiveness of information technologies, provides a foundational environment for developing IT applications, offering organizations virtually unlimited and flexible computing resources on a pay-per-use basis. However, the large data centres where cloud computing services are hosted consume significant amounts of electricity annually due to Information and Communication Technology (ICT) components. This issue is exacerbated by the increasing deployment of large artificial intelligence (AI) models, which often rely on distributed data centres, thereby significantly impacting the global environment. This study proposes the COUNTER model, designed for sustainable cloud resource management. COUNTER is integrated with cluster graph neural networks and evaluated in a simulated cloud environment, aiming to reduce energy consumption while maintaining quality of service parameters. Experimental results demonstrate improvements in resource utilisation, energy consumption, and cost effectiveness compared to the baseline model, HUNTER, which employs a gated graph neural network aimed at achieving carbon neutrality in cloud computing for modern ICT systems.
Problem
Research questions and friction points this paper is trying to address.
Reduce energy consumption in cloud data centers
Improve resource utilization for AI models
Achieve sustainable cloud computing cost-effectively
Innovation
Methods, ideas, or system contributions that make the work stand out.
Cluster GCN for energy-efficient cloud resource management
Simulated environment validates reduced energy consumption
Improves resource utilization and cost effectiveness
🔎 Similar Papers
No similar papers found.
