Performance Optimization of Serverless Edge Computing for Machine Learning Workloads in Distributed Edge Environments

Sane, Akash Anil (2023) Performance Optimization of Serverless Edge Computing for Machine Learning Workloads in Distributed Edge Environments. Masters thesis, Dublin, National College of Ireland.

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

Abstract

This research focuses on latency and resource optimisation issues in deploying machine learning applications in distributed environments using serverless edge computing. The increasing number of IoT devices requires a strong infrastructure that can effectively handle large amounts of data. The objective of the project is to enhance the scalability and response time of systems by breaking down machine learning applications into smaller, manageable serverless functions. The study leverages the CIFAR-10 and ImageNet200 datasets to assess and improve the system’s performance. It demonstrates significant gains in handling initial startup processes and various workloads. This research enhances the understanding of serverless computing paradigms by providing a novel method that aligns with the latest progress in the field. Essentially, this research presents a framework that greatly simplifies the implementation of machine learning in edge environments, thereby addressing current business needs for responsiveness and efficiency. However, the study does not address long-term sustainability but informs about using a federated learning approach for serverless functions to enhance model accuracy, which uses large datasets, leaving room for future investigation.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Kazmi, Aqeel UNSPECIFIED
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 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:	10 Apr 2025 12:40
Last Modified:	10 Apr 2025 12:40
URI:	https://norma.ncirl.ie/id/eprint/7411

Actions (login required)

View Item