Optimizing Resource Allocation and Offloading for Long-Term Load Balancing Solutions in Fog Computing

Sulimani, Hamza H.

Optimizing Resource Allocation and Offloading for Long-Term Load Balancing Solutions in Fog Computing

Sulimani, Hamza H.

Permalink

Publication Type:: Thesis
Issue Date:: 2024

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download thesisAdobe PDF (4.63 MB)

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Sulimani, Hamza H.
dc.date.accessioned	2024-04-16T02:35:37Z
dc.date.available	2024-04-16T02:35:37Z
dc.date.issued	2024
dc.identifier.uri	http://hdl.handle.net/10453/177955
dc.description	University of Technology Sydney. Faculty of Engineering and Information Technology.	en_US.UTF-8
dc.description.abstract	Nowadays, most emerging critical IoT applications have unique requirements and restrictions to operate efficiently; otherwise, they could be useless. Latency is one of these requirements. Fog computing is the complement system for cloud computing, proving it is the ideal computing environment for critical IoT applications. Distributed computing systems, such as fog computing, have an inherent problem when the computing units have different computing loads, called load difference problems. Offloading and service placement are some techniques used to fix these problems. Although prevalent offloading is the appropriate technique for this research, its procedures generate hidden costs in a system, such as decision time, distant offloading, and network congestion. Many researchers attempt to reduce these costs to get the results of static offloading (in stable environments). However, this research seeks to overcome the hidden costs in the prevalent offloading techniques to balance the load in a fog environment by utilising the sustainability concept. This research believes that increasing physical resources is the only way to improve efficiency as a long-term solution. The study consists of two consecutive phases. The first phase attempts to find the optimum solution between task offloading and service placement. The solution must revive the low-cost offloading solution. A Sustainable load-balancing monitoring system (SlbmS) is the comprehensive solution for the optimum solution to release its limitations. SlbmS uses the sustainability concept to solve the problem of the limitation of resources in edge computing using reinforcement learning. The experiment results of the two phases show that hybrid offloading outperforms the service placement policy in the first stage and prevalent offloading in the second stage when utilising the behaviour of static offloading to reduce the offloading costs in unpredictable environments. The study aims to explore a new area of research that attempts to amend the network topology to improve resource provisioning to provide a free resource at the edge of the network. This research paved the way for a new dimension of analysis. It is the first research to recommend the physical expansion in the fog layer using the sustainability concept.	en_US.UTF-8
dc.format	Thesis (PhD)
dc.language.iso	en_US	en_US.UTF-8
dc.relation	https://opus.lib.uts.edu.au/bitstream/10453/177955/1/thesis.pdf
dc.rights	info:eu-repo/semantics/openAccess
dc.rights	The author owns the copyright in this thesis including all reproduction and reuse rights for the work. The work may not be altered without the permission of the copyright owner. Attribution is essential when quoting or paraphrasing from this thesis.
dc.rights	© 2024 Hamza H. Sulimani
dc.rights	au.edu.uts.lib/cph
dc.title	Optimizing Resource Allocation and Offloading for Long-Term Load Balancing Solutions in Fog Computing	en_US.UTF-8
dc.type	Thesis
utslib.copyright.status	open_access	*

Abstract:

Nowadays, most emerging critical IoT applications have unique requirements and restrictions to operate efficiently; otherwise, they could be useless. Latency is one of these requirements. Fog computing is the complement system for cloud computing, proving it is the ideal computing environment for critical IoT applications. Distributed computing systems, such as fog computing, have an inherent problem when the computing units have different computing loads, called load difference problems. Offloading and service placement are some techniques used to fix these problems. Although prevalent offloading is the appropriate technique for this research, its procedures generate hidden costs in a system, such as decision time, distant offloading, and network congestion. Many researchers attempt to reduce these costs to get the results of static offloading (in stable environments). However, this research seeks to overcome the hidden costs in the prevalent offloading techniques to balance the load in a fog environment by utilising the sustainability concept. This research believes that increasing physical resources is the only way to improve efficiency as a long-term solution. The study consists of two consecutive phases. The first phase attempts to find the optimum solution between task offloading and service placement. The solution must revive the low-cost offloading solution. A Sustainable load-balancing monitoring system (SlbmS) is the comprehensive solution for the optimum solution to release its limitations. SlbmS uses the sustainability concept to solve the problem of the limitation of resources in edge computing using reinforcement learning. The experiment results of the two phases show that hybrid offloading outperforms the service placement policy in the first stage and prevalent offloading in the second stage when utilising the behaviour of static offloading to reduce the offloading costs in unpredictable environments. The study aims to explore a new area of research that attempts to amend the network topology to improve resource provisioning to provide a free resource at the edge of the network. This research paved the way for a new dimension of analysis. It is the first research to recommend the physical expansion in the fog layer using the sustainability concept.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/177955