Rule-based Task Scheduling in Cloud-Edge Computing for Energy and Resource Utilization Optimization

Chen, Jialing (2025) Rule-based Task Scheduling in Cloud-Edge Computing for Energy and Resource Utilization Optimization. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (3MB) | Preview

Abstract

Smart devices and real-time services are becoming more common nowadays, which shows problems with using only cloud systems. These problems include systems getting too busy. Because of these issues, there is a need to find better ways to use both edge devices and cloud computing together to handle tasks more efficiently. The main goal of this project was to create a basic system that helps decide where to run different tasks - either on edge devices or in the cloud. This decision depends on how busy the system is at any given time, looking at things like how much CPU and memory are being used. The project used a rule-based system running in Kubernetes to make these decisions.

To keep track of how the system was doing, Prometheus was used to watch different measurements in real-time. The system used these measurements to figure out where tasks should go based on some fixed rules that were set up at the start. Different tests were done to check if this basic rule setup actually worked well. Looking at the test results showed that the fixed rules did a decent job handling different amounts of work coming into the system. Even though the rules stayed the same and couldn’t change on their own, the system still managed to run tasks faster and use less power than when no rules were used at all. This shows that sometimes having just a few simple, unchanging rules can actually make things work better, especially when dealing with both cloud and edge computing together.

What’s interesting is that this system worked well without using complicated machine learning. This shows that sometimes simpler approaches using basic rules can be really effective, especially for smaller edge devices. The results suggest this kind of system could be useful in real situations where both edge and cloud computing are needed.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Shaguna UNSPECIFIED
Uncontrolled Keywords:	Edge Computing; Cloud Computing; Rule-based Scheduler; Resource Management; Energy Efficiency; Kubernetes
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing Q Science > QA Mathematics > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science > Computer Systems > Computers > Electronic data processing > Electronic data processing--Distributed processing > Edge computing
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	20 Mar 2026 14:12
Last Modified:	20 Mar 2026 14:12
URI:	https://norma.ncirl.ie/id/eprint/9204

Actions (login required)

View Item