Machine Learning Based Load Balancing Algorithm For Efficient Power Consumption And Reduced Carbon Emission In Cloud Computing Environment

Nanthakumar, Adithiyan (2023) Machine Learning Based Load Balancing Algorithm For Efficient Power Consumption And Reduced Carbon Emission In Cloud Computing Environment. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (2MB) | Preview

Abstract

Cloud computing is a popular and growing technology that allows businesses and organizations to access computing resources on demand. Load balancing is an important aspect of cloud computing, as it ensures that tasks are distributed evenly across processing nodes to prevent bottlenecks. However, traditional load balancing methodologies, like the Round Robin algorithm, have revealed limitations in adaptive task distribution, often leading to inefficiencies in heterogeneous cloud environments. This research introduces an innovative approach by integrating machine learning-based models—specifically, Support Vector Classification (SVC) and Recurrent Neural Network (RNN)—into the load balancing paradigm where a different set of experiments has been performed in a simulated environment, developed using Python. Our results show that RNN model outperforms as compared to SVC and Round Robin algorithm, achieving the highest load processing efficiency with minimal energy consumption and carbon emissions.

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 Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	10 Oct 2024 14:46
Last Modified:	10 Oct 2024 14:46
URI:	https://norma.ncirl.ie/id/eprint/7095

Actions (login required)

View Item