Energy-Efficient Virtual Machine Consolidation in Cloud Datacenters

Moradiya, Parth Ishvarbhai (2024) Energy-Efficient Virtual Machine Consolidation in Cloud Datacenters. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (626kB) | Preview

Abstract

In this research, an innovative approach is presented for energy efficiency optimization in cloud datacenters via intelligent virtual machine (VM) consolidation. This work attempts to address the growing environmental and operational concerns regarding datacenter energy consumption through a multi-objective optimization framework that utilizes machine learning and predictive analytics. A methodology of combining workload prediction by LSTM networks with the classification of the server load using Random Forest algorithms to make informed consolidation decisions is also presented. It extends to incorporate energy minimization, and VM migration optimization objectives traditionally addressed, as well as CO2 emissions, workload prediction accuracy, and performance impact metric objectives. Evaluation utilizes CloudSim simulation environment extended with Python-based optimization algorithms. Adaptive learning mechanisms were shown to provide for significant improvements in energy efficiency with no sacrifice in service quality. Performance of the framework is extensively evaluated against traditional consolidation approaches using energy consumption and resource utilization as evaluation metrics, seeing substantial improvements. This research is of direct relevance for large-scale cloud providers who want to trade operational efficiency with environmental responsibility. It shows how advanced machine learning techniques and multi-objective optimization can improve datacenter operations while saving on environmental impact.

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 > 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:	15 Jul 2025 14:32
Last Modified:	15 Jul 2025 14:32
URI:	https://norma.ncirl.ie/id/eprint/8123

Actions (login required)

View Item