Resource Optimization in Cloud Data Centers using Machine Learning

Arkalgud Guruvachari, Jnanashree (2024) Resource Optimization in Cloud Data Centers using Machine Learning. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (704kB) | Preview
Preview	PDF (Configuration Manual) Download (661kB) | Preview

Abstract

In this digital era, everything is considered as data. Hence, it is very important to protect and manage these data in an optimized manner. We have data centers across the globe that are used to store, manage, and protect the data. Many operations are performed within the data center such as workload distribution, power consumption, auto-scaling, resource allocation, etc. It is a crucial job to optimize these operations to avoid higher operational costs and degraded service quality. In this study, we have implemented three machine learning models that can be used to optimize the data center resources to achieve better performance. The three models are- Linear Regression, Random Forest, and Generative Adversarial Networks (GANs). Out of three models, we have achieved excellent results for Linear Regression and Random Forest compared to GANs. These three models are trained on the historical information and predict future data based on the data flow and knowledge of the historical data. We obtain an output from these models which displays the action that needs to be taken. The output indicates if the resources need to be scaled up or down based on the workflow and if the cooling system needs to be activated based on CPU usage. By implementing this solution, we can achieve optimized resource allocation, better workload distribution, reduced power consumption, and lower operational cost which in turn achieves better performance of the data center.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Samarawickrama, Yasantha UNSPECIFIED
Uncontrolled Keywords:	Data Center; Linear Regression; Random Forest; GANs; Optimization
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 > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	14 Jul 2025 14:19
Last Modified:	14 Jul 2025 14:19
URI:	https://norma.ncirl.ie/id/eprint/8081

Actions (login required)

View Item