Energy-Efficient Data Optimization for Resource-constrained Edge/Fog Computing Devices

Henry, Divya (2024) Energy-Efficient Data Optimization for Resource-constrained Edge/Fog Computing Devices. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (891kB) | Preview

Abstract

The presence of fog and edge computing devices everywhere have led to the generation of high volumes of data across their nodes resulting in great difficulties while handling and processing such massive volumes of data due to limited computing power at the edge or fog devices. This demands the case for an optimized model for devices in edge/fog computing environments that can achieve optimal data compression and efficient data transfer across the edge/fog nodes by following green cloud computing practices. The proposed method integrates deep compression sensing autoencoder network (DCSANet) for data reduction and accurate reconstruction with deep reinforcement learning (DRL) based joint computing framework (JCF) for intelligent collaboration among fog nodes sharing resources. DCSANet aims at learning how to generate smaller representations of information through dimensionality reduction thereby generating compressed data without sacrificing too much on reconstruction accuracy during the recovery process at the receiving nodes, while still ensuring data fidelity in reproduction. JCF enables smart cooperation between fog nodes to determine best decisions regarding computation offloading along with energy-efficient processing and handling of shared resources for data processing at the fog nodes. The effectiveness of the proposed DRL-based JCF and DCSANet approach will be analyzed by its ability to improve energy efficiency, reduce transmission latencies as well as improve reconstruction accuracy using real-world IoT datasets, thereby showcasing its potential towards providing optimal solutions for efficient data aggregation within resource limited-edge devices while cutting down computational complexities and network bandwidth requirements for a sustainable fog/edge computing environment.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Gupta, Shaguna UNSPECIFIED
Uncontrolled Keywords:	Compressed sensing; deep learning; edge/fog computing; energy efficiency; data aggregation; computation offloading
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 T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Telecommunications > Computer networks > Internet of things 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:	03 Jul 2025 10:50
Last Modified:	03 Jul 2025 10:50
URI:	https://norma.ncirl.ie/id/eprint/8020

Actions (login required)

View Item