Off-campus UMass Amherst users: To download campus access dissertations, please use the following link to log into our proxy server with your UMass Amherst user name and password.

Non-UMass Amherst users: Please talk to your librarian about requesting this dissertation through interlibrary loan.

Dissertations that have an embargo placed on them will not be available to anyone until the embargo expires.

Author ORCID Identifier

https://orcid.org/0000-0001-5768-291X

Document Type

Open Access Dissertation

Degree Name

Doctor of Philosophy (PhD)

Degree Program

Electrical and Computer Engineering

Year Degree Awarded

2020

Month Degree Awarded

February

First Advisor

Michael Zink

Second Advisor

Lixin Gao

Third Advisor

David Irwin

Fourth Advisor

Klara Nahrstedt

Subject Categories

Computer and Systems Architecture

Abstract

A prodigious increase in video streaming content along with a simultaneous rise in end system capabilities has led to the proliferation of adaptive bit rate video streaming users in the Internet. Today, video streaming services range from Video-on-Demand services like traditional IP TV to more recent technologies such as immersive 3D experiences for live sports events. In order to meet the demands of these services, the multimedia and networking research community continues to strive toward efficiently delivering high quality content across the Internet while also trying to minimize content storage and delivery costs.

The introduction of flexible and adaptable technologies such as compute and storage clouds, Network Function Virtualization and Software Defined Networking continue to fuel content provider revenue. Today, content providers such as Google and Facebook build their own Software-Defined WANs to efficiently serve millions of users worldwide, while NetFlix partners with ISPs such as ATT (using OpenConnect) and cloud providers such as Amazon EC2 to serve their content and manage the delivery of several petabytes of high-quality video content for millions of subscribers at a global scale, respectively. In recent years, the unprecedented growth of video traffic in the Internet has seen several innovative systems such as Software Defined Networks and Information Centric Networks as well as inventive protocols such as QUIC, in an effort to keep up with the effects of this remarkable growth. While most existing systems continue to sub-optimally satisfy user requirements, future video streaming systems will require optimal management of storage and bandwidth resources that are several orders of magnitude larger than what is implemented today. Moreover, Quality-of-Experience metrics are becoming increasingly fine-grained in order to accurately quantify diverse content and consumer needs.

In this dissertation, we design and investigate innovative adaptive bit rate video streaming systems and analyze the implications of recent technologies on traditional streaming approaches using real-world experimentation methods. We provide useful insights for current and future content distribution network administrators to tackle Quality-of-Experience dilemmas and serve high quality video content to several users at a global scale. In order to show how Quality-of-Experience can benefit from core network architectural modifications, we design and evaluate prototypes for video streaming in Information Centric Networks and Software-Defined Networks. We also present a real-world, in-depth analysis of adaptive bitrate video streaming over protocols such as QUIC and MPQUIC to show how end-to-end protocol innovation can contribute to substantial Quality-of-Experience benefits for adaptive bit rate video streaming systems. We investigate a cross-layer approach based on QUIC and observe that application layer-based information can be successfully used to determine transport layer parameters for ABR streaming applications.

DOI

https://doi.org/10.7275/xtv4-j147

Creative Commons License

Creative Commons Attribution 4.0 License
This work is licensed under a Creative Commons Attribution 4.0 License.

Share

COinS