Tools
Tools
Warekar, Prathamesh Vijay (2024) Forecasting the Future: Enhancing Cloud Efficiency through Dynamic CPU Utilization Allocation. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (3MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (2MB) | Preview |
Abstract
CPU utilization in the cloud describes the percentage of time that a central processing unit (CPU) is actively executing instructions, reflecting the workload demand placed on the CPU. The abstract of this report is the exploration for forecasting CPU utilization in the cloud for dynamic allocation in the cloud. Various traditional methods have been used for forecasting CPU utilization which lack in their RMSE, MSE and failed. However, this study is using few time-series and forecasting algorithms to develop better results and adaptive predictive models. The dataset is of Microsoft Azure which is a publicly accessible dataset for accurately forecasting future CPU utilization patterns and all so that it can enable some sort of cloud service providers and optimize resource allocation as well. For preprocessing the data, this research uses scaling and window rolling techniques, and training multiple machine learning models such as Support Vector Regressor, Extra Trees Regressor, AdaBoost Regressor, and Stacking Regressor, the study aims to identify the most effective approach for CPU utilization forecasting. The stacking regressor has been considered and found the best model for forecasting CPU utilization in the cloud which combined multiple base estimators, including Support Vector Regressor (SVR) and AdaBoost Regressor, with a final estimator, Extra Trees Regressor, to improve prediction accuracy which means evaluation metrics. This has also enhanced cloud efficiency through dynamic CPU utilization allocation.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Heeney, Sean 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: | 03 Jun 2025 14:33 |
| Last Modified: | 03 Jun 2025 14:33 |
| URI: | https://norma.ncirl.ie/id/eprint/7731 |
Actions (login required)
 |
View Item |