Orchestrating Contextual Bandits Algorithm for Resource Scheduling in Kubernetes on Multiple Cloud Environments using Linear regression model

Gadikota, Bramha Theja (2024) Orchestrating Contextual Bandits Algorithm for Resource Scheduling in Kubernetes on Multiple Cloud Environments using Linear regression model. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (769kB) | Preview

Abstract

Resource allocation in Kubernetes clusters refers to the efficient distribution and management of computing resources, such as CPU, memory, and storage to workloads running in the cluster. Traditional resource scheduling approaches often struggle with issues like suboptimal resource utilization, inability to handle dynamic workloads, and lack of adaptability to varying application demands. These problems are addressed in this study by employing the Contextual Bandits algorithm, which enables more intelligent and adaptive decision-making based on real-time resource usage patterns. The proposed approach uses a Linear Regression model within the Contextual Bandits framework to predict the most efficient allocation of resources based on historical data and the current context. The algorithm attempts to find a balance between maximizing resource efficiency and maintaining application performance. The objective of this study is to compare the performance of the proposed Linear Regression-based scheduling approach between AWS and Azure cloud platforms using Kubernetes, which uses a more static and simplistic allocation mechanism. The experimental results demonstrated that the proposed approach outperforms the scheduler in terms of resource utilization, application responsiveness, and scalability. The findings indicate that Linear Regression scheduling with Kubernetes can significantly enhance cloud resource management, offering improved performance in handling dynamic and fluctuating workloads compared to traditional methods.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Shaguna UNSPECIFIED
Uncontrolled Keywords:	Cloud Computing; AWS (Amazon Web Services); Microsoft Azure; Kubernetes; Docker Containerization; Cloud
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:	Ciara O'Brien
Date Deposited:	15 Jul 2025 08:39
Last Modified:	15 Jul 2025 08:39
URI:	https://norma.ncirl.ie/id/eprint/8098

Actions (login required)

View Item