Devising an Ideal Network Slicing Ring Fencing Ratio for Cloud Energy Infrastructure

Iyer, Vinay Sriram (2024) Devising an Ideal Network Slicing Ring Fencing Ratio for Cloud Energy Infrastructure. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (2MB) | Preview
Preview	PDF (Configuration Manual) Download (3MB) | Preview

Abstract

Disparate differences in total energy consumption by heterogeneous architectures often magnify through designed network topologies in cloud energy data centers that contrast sharply against the actualised energy consumption. A preliminary correlation can be drawn by how network operators design high-quality ’Network Slices’ composed of logical ring fences akin to Radio Access Networks(RAN’s) through end-to-end network slicing that reduces the network ’churn’ often associated in large losses of energy consumption in cloud energy infrastructures. However, certain limitations still exist with significant cutoffs in workload resource specific requirements and the actualised energy consumption drawn from ’Network Slices’. This paper proposes an ideal network slicing to ring fencing ratio through an Iterative Heuristic Energy-Aware Non-Convex equation that optimises cloud architectural management through optimal convergence in energy consumption with refined computational execution time. Through subsequent iterative testing against a consistent convergence criterion, the Iterative Heuristic Energy-Aware Non-Convex equation reported an efficiency gain of 91.46% in total energy consumption when benchmarked against a Heuristic AUGMENT Non-Convex Algorithm(Hossain and Ansari. achieved efficiency gain of 63.89%) and Priority Selection Offloading Algorithm (Anajemba et al. achieved efficiency gain of 58.6%). By benchmarking speed in convergence with the overall energy consumption and refined computational execution time, a network-slicing ring-fencing ratio ensures a balance in idealised energy consumption is met between the network architect, operator and client.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Samarawickrama, Yasantha UNSPECIFIED
Uncontrolled Keywords:	Network topologies; energy efficiency; Network Slices ring fences; convergence criterion; execution time
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
Divisions:	School of Computing > Master of Science in Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	15 Jul 2025 11:29
Last Modified:	15 Jul 2025 11:29
URI:	https://norma.ncirl.ie/id/eprint/8105

Actions (login required)

View Item