Improving fault tolerance of a task in cloud using ensemble approach

Soneji, Divesh Vashi (2023) Improving fault tolerance of a task in cloud using ensemble approach. Masters thesis, Dublin, National College of Ireland.

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

Abstract

The presented study investigates the improvement of fault tolerance in cloud tasks through the utilisation of an ensemble approach. The study conducted provides a comparative analysis of different models, with a specific emphasis on the classification of tasks into two categories: success and failure. The study involved a comparison between an ensemble model and two machine learning models, with the evaluation of various metrics including F1 score, accuracy, and recall. The performance of the models was evaluated using a split of 80 percent training data and 20 percent testing data. Three case studies were conducted, which involved the utilisation of the K-Nearest Neighbours (KNN) model, Artificial Neural Network (ANN) model, and an ensemble model. The models are evaluated based on the accuracy, root means square error (RMSE), R-Square , F1-score and Recall . Out of the three models considered, the ensemble model that combines both the KNN and ANN using logistic regression demonstrates 15 percent improvement from KNN and 1 percent improvement from ANN in accuracy as seen in the performance metrics. Despite its efficacy, this approach presents challenges in terms of heightened resource demands and increased complexity. The results emphasise the significance of effectively implementing an ensemble model in task scheduling algorithms in data centres, as it facilitates a robust approach to ensure fault tolerance.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Samarawickrama, Yasantha 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
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	21 Oct 2024 12:08
Last Modified:	21 Oct 2024 12:08
URI:	https://norma.ncirl.ie/id/eprint/7107

Actions (login required)

View Item