Optimizing the Resource Utilization in Cloud Computing Environment with Autoscaling using Machine Learning Methods

Shettihalli Anandreddy, Sri Madhan (2023) Optimizing the Resource Utilization in Cloud Computing Environment with Autoscaling using Machine Learning Methods. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (3MB) | Preview

Abstract

In the rapidly evolving cloud ecosystem, maintaining service levels while optimizing resource utilization is paramount. Autoscaling is a technique that can be used to dynamically adjust the resources allocated to an application to meet demand. This can help to improve performance, reliability, and cost-effectiveness. This research introduces a comprehensive study of various autoscaling algorithms applied in a simulated cloud environment. TPerformance of different algorithms for autoscaling including Moving Average, Random forest regressor (RF), Support vector regressor(SVR), Gated recurrent Unit (GRU) and Convolutional LSTM (ConvLSTM) were evaluated. Comprehensive metrics such as load vs. capacity, resource utilization, delayed load, and prediction errors were employed for evaluation. After performing various sets of experiment the most optimal algorithm for autoscaling has been identified. Notably, the random forest emerged as the top-performing algorithm, demonstrating proficiency in managing cloud resources effectively.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Punit 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:	Tamara Malone
Date Deposited:	18 Oct 2024 16:28
Last Modified:	18 Oct 2024 16:28
URI:	https://norma.ncirl.ie/id/eprint/7105

Actions (login required)

View Item