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/0000-0003-0688-2043

Document Type

Open Access Dissertation

Degree Name

Doctor of Philosophy (PhD)

Degree Program

Computer Science

Year Degree Awarded

2020

Month Degree Awarded

February

First Advisor

Ramesh K. Sitaraman

Subject Categories

Computer and Systems Architecture | Digital Communications and Networking | Other Computer Engineering

Abstract

Content delivery networks (CDNs) deploy hundreds of thousands of servers around the world to cache and serve trillions of user requests every day for a diverse set of content such as web pages, videos, software downloads and images. In this dissertation, we propose algorithms to provision traffic across cache servers and manage the content they host to achieve performance objectives such as maximizing the cache hit rate, minimizing the bandwidth cost of the network and minimizing the energy consumption of the servers.

Traffic provisioning is the process of determining the set of content domains hosted on the servers. We propose footprint descriptors that effectively capture the popularity characteristics and caching performance of different content classes. We also propose a footprint descriptor calculus that can be used to decide how content should be mixed or partitioned to efficiently provision traffic. To automate traffic provisioning, we propose optimization models to provision traffic such that the cache miss traffic from the network is minimized without overloading the servers. We find that such optimization models produce significant reductions in the cache miss traffic when compared with traffic provisioning algorithms in use today.

Cache management is the process of deciding how content is cached in the servers of a CDN. We propose TTL-based caching algorithms that provably achieve performance targets specified by a CDN operator. We show that the proposed algorithms converge to the target hit rate and target cache size with low error. Finally, we propose cache management algorithms to make the servers energy-efficient using disk shutdown. We find that disk shutdown is well suited for CDN servers and provides energy savings without significantly impacting cache hit rates.

Share

COinS