Kubernetes Proactive Resources Scheduling using Multi-armed bandit Algorithm

Mondhe, Nikhil Shalikram (2023) Kubernetes Proactive Resources Scheduling using Multi-armed bandit Algorithm. Masters thesis, Dublin, National College of Ireland.

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

Abstract

Effective resource allocation in Kubernetes clusters is critical for improving application performance while utilising cluster resources efficiently. Traditional resource scheduling approaches frequently rely on fixed policies, which results in suboptimal resource utilisation and, on occasion, performance bottlenecks. To address these issues, this study employs the Multi-armed Bandit Algorithm in a novel approach for proactive resource scheduling in Kubernetes environments. To dynamically allocate resources to different application workloads, the proposed approach employs Thompson Sampling algorithm, a popular technique in the field of multi-armed bandits. The algorithm seeks to strike a balance between exploring potentially better resource configurations and exploitation of known high-performing configurations by treating each application as a ”arm” and allocating resources based on historical performance data. The objective of this study is to compare the effectiveness of the Thompson Sampling-based proactive scheduling approach to the default Kubernetes scheduler. The comparison is based on minimising CPU and memory usage across multiple workloads. The findings of this study have the potential to make a significant contribution to the field of container orchestration and resource management by providing insights into the effectiveness of advanced algorithms in solving resource allocation challenges. The experimental results demonstrated that proactive resource scheduling strategies can improve the overall scalability, performance, and efficiency of Kubernetes clusters.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Haque, Rejwanul 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 Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	09 Oct 2024 18:30
Last Modified:	09 Oct 2024 18:30
URI:	https://norma.ncirl.ie/id/eprint/7093

Actions (login required)

View Item