Designing a green scheduler using containers to optimize workload distribution across multiple clusters based the availability of low carbon energy sources

Kondepudi, Saichandan (2024) Designing a green scheduler using containers to optimize workload distribution across multiple clusters based the availability of low carbon energy sources. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The carbon emitted by the data centers these days is the point of notice. It depends on the variety of factors like constant availability of renewable resources in the data centers and others. Thus, scheduling of the jobs in the available data centers has an elongated impact on the emission of carbon intensity. This research tries to create a new algorithm and simulate the deployment of the algorithm on Kubernetes cluster. The algorithm is then compared with the other two existing algorithms and evaluates the parameters like energy efficiency, job scheduling, Global resource utilization while maintaining high job scheduling percentage. The evaluation was conducted with series of five different sets of available carbon intensities and resources to evaluate the algorithms under different conditions. In every evaluation CAKS algorithm achieved the highest percentage of green utilization ration and achieved better results in scheduling the jobs in each data center. However, research also highlights the drawbacks and areas of the improvement required for future studies. Additionally, the paper suggests the real world implementation of this algorithm to get real time analytics. This research contributes in the concept of green computing by demonstrating the benefits of job scheduling algorithms.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Lugones, Diego UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	03 Jul 2025 11:39
Last Modified:	03 Jul 2025 11:39
URI:	https://norma.ncirl.ie/id/eprint/8027

Actions (login required)

View Item