Characterizing performance of residential internet connections using an analysis of measuring broadband America's web browsing test data
Name
938936986-MIT.pdf
Description
Full printable version
Size
8.97 MB
Format
Adobe PDF
Checksum (MD5)
4724aac0b642d5f58105ac3219bca3ef
Author(s)
Gamero-Garrido, Alexander M
Advisor(s)
David D. Clark.
Date Issued
2015
Publisher
Massachusetts Institute of Technology
Abstract
This thesis presents an analysis of F.C.C.-measured web page loading times as observed in 2013 from nodes connected to consumer broadband providers in the Northeastern, Southern and Pacific U.S. We also collected data for multiple months in 2015 from the MIT network. We provide temporal and statistical analyses on total loading times for both datasets. We present four main contributions. First, we find differences in loading times for various websites that are consistent across providers and regions, showing the impact of infrastructure of transit and content providers on loading times and Quality of Experience (QoE.) Second, we find strong evidence of diurnal variation in loading times, highlighting the impact of network and server load on end-user QoE. Third, we show instances of localized congestion that severely impair the performance of some websites when measured from a residential provider. Fourth, we find that web loading times correlate with the size of a website's infrastructure as estimated by the number of IP addresses observed in the data. Finally, we also provide a set of policy recommendations: execution of javascript and other code during the web browsing test to more adequately capture loading times; expanding the list of target websites and collecting trace route data; collection of browsing data from non-residential networks; and public provision of funding for research on Measuring Broadband America's web browsing data. The websites studied in this thesis are: Amazon, CNN, EBay, Facebook, Google, msn, Wikipedia, Yahoo and YouTube.
Description
Thesis: S.M. in Technology and Policy, Massachusetts Institute of Technology, Institute for Data, Systems, and Society, Technology and Policy Program, 2015.
Cataloged from PDF version of thesis.
Includes bibliographical references (pages 71-73).
Subjects
Institute for Data, Systems, and Society.
Engineering Systems Division.
Technology and Policy Program.
MIT Department
Massachusetts Institute of Technology. Engineering Systems Division
Massachusetts Institute of Technology. Institute for Data, Systems, and Society
Technology and Policy Program
Terms of Use
M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.
Persistent DSpace Link
