Cloud Resource Forecasting and Prediction Methodology Framework

Ladouari, Karim (2023) Cloud Resource Forecasting and Prediction Methodology Framework. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration manual) Download (998kB) | Preview

Abstract

Cloud computing has dramatically changed the management of web applications, software development and information technology. Anyone, anywhere in the world, can provision a virtual machine on the platform of one of the Cloud computing service providers. One of the many advantages of Cloud computing is to provide resources on demand. The challenge for Cloud customers is to size and optimise Cloud applications while controlling over-capacity. The current research established a mechanism to select the optimal time series forecasting technique to predict Cloud systems requirements. A Deep learning Recurrent Neural Network (RNN) time series technique combined with Extreme Gradient Boosting (XGBoost) feature selection algorithm is designated to produce the optimal short-term prediction, while Seasonal Auto-Regressive Integrated Moving Average with exogenous factors (SARIMAX) combined with Random Forest is for long-term predictions. The defined prediction methodology framework would help Cloud application owners maintain their running cost and associated low carbon footprint and improve performance.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Iqbal, Zahid 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 Data Analytics
Depositing User:	Tamara Malone
Date Deposited:	19 May 2023 15:30
Last Modified:	19 May 2023 15:30
URI:	https://norma.ncirl.ie/id/eprint/6606

Actions (login required)

View Item