Date of Award

2-19-2020

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Mengjun Xie

Abstract

Edge computing is a solution to the mobile computation offloading problem. Previous works show that virtual machines can be the computation units in edge computing. However, virtual machine-based methods are usually associated with large overheads and long latencies. In this thesis, we explore the possibility of using Docker containers instead of virtual machines in edge computing enabled by lambda architecture. We propose an edge computing platform, called Lambda Edge, which can be used to build edge computing applications and pave the way for further research on lambda-based edge computing. We also provide a sample application built upon the platform. We set up two experiments to compare latency and resource usage of the application between a Lambda Edge deployment and a cloud one. The results show that Lambda Edge provides better latency while resource usage remains the same.

Download

Share

COinS