Pareto Optimization Framework in Fog and Edge Computing

Gaur, Shubham (2023) Pareto Optimization Framework in Fog and Edge Computing. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (3MB) | Preview
Preview	PDF (Configuration Manual) Download (198kB) | Preview

Abstract

Effective data processing at the source is necessary for the Internet of Things (IoT), frequently necessitating high speeds without depending on high bandwidth. Cloud computing and fog computing (FC) are used in tandem to achieve this. Fog computing is especially useful for real-time applications that require quick internet access. Meeting dynamic real-time needs is one of the main issues in FC, nevertheless, because of the restricted resources of fog nodes. As such, a primary challenge in the fog context is how best to distribute work across fog nodes. It is imperative to use scheduling algorithms that considers the diversity of the fog nodes and their job completion in order to minimize many aspects, such as cost and energy usage. This work highlights important obstacles in the body of literature and provides a thorough taxonomy to improve our comprehension of the research questions pertaining to task scheduling in the cloud-fog environment. As a result, it offers a thorough analysis of work scheduling strategies in this particular setting, highlighting both their benefits and drawbacks. Multiple publications are reviewed in each of the four main kinds of approaches that are examined: deterministic mechanisms, heuristic-based, machine learning-based, and metaheuristic-based. A number of other factors include time taken for execution, utilization of resource, processing latency, network bandwidth, power consumed, execution deadlines, turn around time, unpredictability, and complexity are also compared across different strategies in the study. The results show that 23% of the scheduling algorithms use machine learning algorithms, 38% use metaheuristic-based techniques, 30% use heuristic-based approaches, and 9% use deterministic techniques. Remarkably, energy usage stands up as the most important characteristic discussed in most of the articles, receiving 19% of the attention.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Arun, Shreyas Setlur 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 > QA Mathematics > Algebra > Algorithms > Computer algorithms 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:	28 Mar 2025 08:59
Last Modified:	28 Mar 2025 08:59
URI:	https://norma.ncirl.ie/id/eprint/7342

Actions (login required)

View Item