Simulating resource management in fog computing systems
Loading...
URL
Journal Title
Journal ISSN
Volume Title
Perustieteiden korkeakoulu |
Master's thesis
Unless otherwise stated, all rights belong to the author. You may download, display and print this publication for Your own personal use. Commercial use is prohibited.
Authors
Date
2023-10-09
Department
Major/Subject
Computer Science
Mcode
SCI3042
Degree programme
Master’s Programme in Computer, Communication and Information Sciences
Language
en
Pages
76
Series
Abstract
The fog computing paradigm was introduced to address the new challenges and requirements posed by the Internet of Things (IoT). It extends the cloud to the edge of the network, thereby facilitating processing and storing a massive amount of data where it is created and used. This novel computing paradigm is widely studied in both the academy and the industry, primarily by simulation. Today, a large variety of edge and fog computing simulators exist and are reviewed by several surveys. These reviews, however, mainly focus on high-level comparisons of these simulators and often make contradictory statements, which makes it difficult to assess what studies are feasible with a simulation tool. To address these challenges, we focus on a single state-of-the-art fog simulation tool, iFogSim2. In this paper, we provide an in-depth review of the simulator and examine its model, assumptions, and technical characteristics. Our analysis describes the details of fog resource management mechanisms implemented by iFogSim2 and discusses what it is capable of and where its limitations lie. We construct a case study to assess the tool's suitability for a mobile 5G scenario, namely, road surface weather analysis with smart vehicles. The case study is used to retrieve qualitative results of what is feasible with the tool, and what is not. We demonstrate that iFogSim2 has a valid locality model for the mobile 5G use case, but it is not suitable for experimenting with vehicular fog computing, dynamic placement, server-side service discovery, and load-balancing. In addition, we present a modeling and analytics framework, built for iFogSim2, to improve the simulation software and facilitate future research with the tool.Description
Supervisor
Hirvisalo, VesaThesis advisor
Harjuhahto, JaakkoKeywords
fog computing, simulation, Internet of Things, road weather analysis, fog resource management, service placement