Tools
Tools
Malik, Abhishek (2023) Autonomous Cloud Resource Allocation: A Hybrid Machine Learning 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
This research looks at Autonomous Cloud Resource Allocation using a Multiscale Deep Learning Architecture, comparing two models for forecasting CPU consumption. Deep learning was used to train and assess Bidirectional Long Short-Term Memory (BILSTM) and STACKED LSTM GRU models on performance measures. The BILSTM model emerged as the clear winner, with remarkable predictive ability. In a comparison examination, the BILSTM model produced a validation loss of 8.6205e-04, an RMSE of 0.0294, and an outstanding R-squared value of 0.9743. Meanwhile, the STACKED LSTM GRU model performed well, with a validation loss of 9.1896e-04, an RMSE of 0.0303, and an R-squared of 0.9726. The results demonstrate the BILSTM model’s superior accuracy in estimating CPU consumption, recognising detailed patterns, and explaining data volatility. These findings highlight the effectiveness of deep learning models for improving cloud resource allocation. The research adds to our understanding of how to implement powerful predictive models for autonomous resource management in cloud computing, opening the path for more efficient and responsive cloud architecture.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Makki, Ahmed 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: | 08 Apr 2025 17:02 |
| Last Modified: | 08 Apr 2025 17:02 |
| URI: | https://norma.ncirl.ie/id/eprint/7388 |
Actions (login required)
 |
View Item |