KubeGreen: A Scheduler for Latency, CPU, and Carbon Optimisation

Gurbhele, Saksham Shailesh (2025) KubeGreen: A Scheduler for Latency, CPU, and Carbon Optimisation. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (994kB) | Preview

Abstract

As adoption of federated Kubernetes for managing applications across distributed environments increases, a challenge emerges: default schedulers lack the intelligence to optime for both performance and environmental sustainability. This research addresses this gap by developing KubeGreen, a smart, multi-objective scheduler that reduces latency and carbon emissions. The proposed scheduler is a lightweight, heuristic-based scoring model that evaluates the suitability of each cluster based on three metrics: real-time network latency, carbon intensity, and real-time CPU utilisation.

KubeGreen was implemented and evaluated in a real multi-cluster Kubernetes testbed spanning three different Google Cloud Platform regions. A continuous 24-hour empirical evaluation demonstrated its effectiveness. Compared to static placement strategies, KubeGreen dynamically adapts to fluctuating conditions, achieving an average reduction of 15% in carbon emissions and 22% in network latency, while maintaining balanced CPU usage across clusters. This work validates that a practical, metric-driven approach can significantly enhance both the performance and sustainability of cloud native workloads, offering a path toward greener and more efficient multi-cluster orchestration. Future work can explore the integration of additional metrics such as cost or network bandwidth to further refine scheduling decisions.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Lugones, Diego UNSPECIFIED
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing T Technology > T Technology (General) > Information Technology
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	26 Mar 2026 10:01
Last Modified:	26 Mar 2026 14:44
URI:	https://norma.ncirl.ie/id/eprint/9219

Actions (login required)

View Item