Combined Genetic Algorithm and Gradient Descent Algorithm to Optimize Server Selection in Mobile Edge Computing

Pibowei, Tamaraebi Besife (2021) Combined Genetic Algorithm and Gradient Descent Algorithm to Optimize Server Selection in Mobile Edge Computing. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (501kB) | Preview
Preview	PDF (Configuration manual) Download (1MB) | Preview

Abstract

MEC has become the new frontier in minimizing latency in data transmission for mobile devices that are limited in resources. Firstly, the constraints of an edge server in terms of processing capacity and distance that can be covered result in only a limited number of users being able to have their requests completed at the same time. Secondly, because of the varied geographical locations of user mobility pathways in MEC, edge user mobility is significantly connected to data transmission rate and influences edge server latency. Furthermore, when multiple users in an edge server covered region require the same resources at the same time, they interfere with each other and may reduce the experience of service if an effective strategy for requests distribution to different capable edge servers is not in place. Therefore, to reduce latency and computational overhead, we consider the above constraints and propose a novel approach that combines genetic algorithm (GA) and gradient descent (GD) to find an approximately solution to the edge server selection optimization problem. We validate our model by conducting experiment on the EUA dataset. The outcome of the experiments conducted demonstrates that, our model significantly outperforms the baseline approaches.

Item Type:	Thesis (Masters)
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
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Tamara Malone
Date Deposited:	02 Dec 2022 15:15
Last Modified:	06 Dec 2022 17:57
URI:	https://norma.ncirl.ie/id/eprint/5955

Actions (login required)

View Item