Optimizing Task Orchestration for Latency Reduction in 5G-Enabled Cloud Environments

Thigala, Siddhartha Reddy (2025) Optimizing Task Orchestration for Latency Reduction in 5G-Enabled Cloud Environments. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (9MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

This research investigates congestion and latency issues in modern 5G networks due to highly bursty traffic emanating from IoT devices, AR/VR applications, and connected vehicles, which in turn require ultra-low-latency processing at MEC nodes. Traditional static scheduling methodologies are inadequate to handle such bursty workloads; thus, congestion and latency excursions happen frequently. To overcome these challenges, the research offers an intelligent task orchestration framework using Approximate Q-Learning (AQL), which will dynamically decide whether tasks need to be executed at the edge or offloaded to the cloud. For realistic simulation of 5G wireless behavior, a custom discrete-event simulator implemented in Python was created, involving signal fading, SINR variation, and bandwidth constraints. The proposed AQL agent is trained using synthetic traffic patterns corresponding to IoT, AR/VR, and vehicular workloads and is evaluated against both random and rule-based scheduling strategies. vehicular traffic patterns and compared against random and rule-based baselines. Results are that the AQL orchestrator reduced latency by 8.7%, from 5,592 ms (random baseline) to 5,103 ms, while 5,452 ms was observed for the rule-based comparator. Statistical analysis via ANOVA showed significance: p < 0.001. In addition, energy consumption increased by 41%, due to the design of the reward program being biased towards lower latency. Overall, the results suggest that light-weight reinforcement learning can successfully manage real-time task orchestration in 5G edge-cloud environments without the need for deep learning infrastructure.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Makki, Ahmed UNSPECIFIED
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 T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	01 Sep 2026 11:43
Last Modified:	01 Sep 2026 11:43
URI:	https://norma.ncirl.ie/id/eprint/9743

Actions (login required)

View Item