Tools
Tools
Ravindran Shanmugam, Pravin (2024) Improvement of Intelligent Task Prediction and Computation Offloading towards mobile-edge cloud computing. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (896kB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
The research focuses on the improvements in the field of edge computing towards the ability to predict the tasks and offload the tasks according to the requirement. There are lots of issues faced during the computation as the mobile devices are insufficient to handle highly intensive tasks which may be led to loss of battery power, bad performance and high execution time. To overcome these drawbacks instead of having fixed decision-making ability, dynamic decision-making ability to act upon sudden spikes in the behavior of the components. Because fixed decision-making ability will not be suitable for the real time tasks. Machine learning model can be applied to predict the task based on the complexity and take decisions to perform the tasks locally or offload them to the edge server based on the length of the complexity. The decision–making ability depends on the factors such as memory availability, task complexity, network latency and CPU usage. The trained random forest model has shown the improved precision in predictions towards the offloading decisions. The observed results indicates that the random forest has the highest accuracy that is 53.3% followed by the XGBoost model with 52.5% and then the Logistic Regression with the 49.1%. The research leads to enhanced accuracy in the process of making decisions in the real time by the utilization of optimized machine learning model in the AWS SageMaker and iFogSim Environment.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Jaswal, Shivani UNSPECIFIED |
| Uncontrolled Keywords: | Edge computing; Machine learning model; offloading decisions; AWS SageMaker; iFogSim Environment |
| 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: | 16 Jul 2025 11:11 |
| Last Modified: | 16 Jul 2025 11:11 |
| URI: | https://norma.ncirl.ie/id/eprint/8144 |
Actions (login required)
 |
View Item |