GLASS : Global Learning Anomalous Stream Service

Author(s)
Friis, Erick Y.
Thumbnail
Download1128819877-MIT.pdf (22.14Mb)
Alternative title
Global Learning Anomalous Stream Service
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Katrina LaCurts and Ronald D. Chaney.
Terms of use
MIT theses are protected by copyright. They may be viewed, downloaded, or printed from this source but further reproduction or distribution in any format is prohibited without written permission. http://dspace.mit.edu/handle/1721.1/7582
Metadata
Show full item record
Abstract
I present the Global Learning Anomalous Stream Service (GLASS): a monitoring system for Internet overlay networks that helps identify and investigate unusual behavior. I designed, implemented, and tested GLASS at Akamai Technologies to monitor their internationally distributed content delivery network (CDN) for early signs of special network events. In this thesis, I document my design process, GLASS' architecture and algorithms, and an evaluation of the system based on one year of historic aggregate signals.
Description
This electronic version was submitted by the student author. The certified thesis is available in the Institute Archives and Special Collections.
 
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2019
 
Cataloged from student-submitted PDF version of thesis.
 
Includes bibliographical references (pages 69-70).
 
Date issued
2019
URI
https://hdl.handle.net/1721.1/123139
Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Publisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.
Collections