Second Chance: Understanding diversity in broadband access network performance

In recognition of the increasing importance of broadband, several governments have embarked on large-scale efforts to measure broadband services from devices within end-user's homes. Participants for these studies were selected based on features that, a priori, were thought to be relevant to service performance such as geographic region, access technology and subscription level. Every new-year deployment since has followed the same model, ensuring that the number of measurement points remains stable despite the natural churn. In this paper, we start to explore the issue of vantage point selection in residential broadband networks by leveraging the publicly available datasets collected as part of the FCC Broadband America study. We present the first analysis of the variation of performance in edge networks and diversity of individual vantage points. We explore the underlying causes of this diversity through a factor analysis of contextual factors within an ISP such as the geographic location of subscribers. The goal of this analysis is to inform additional deployments in ongoing studies, and guide the design and deployment of future investigations into broadband networks.

[1]  Nick Feamster,et al.  Broadband internet performance: a view from the gateway , 2011, SIGCOMM.

[2]  Donald F. Towsley,et al.  Locating network monitors: complexity, heuristics, and coverage , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[3]  Alejandro López-Ortiz,et al.  On the number of distributed measurement points for network tomography , 2003, IMC '03.

[4]  Rebecca E. Grinter,et al.  Measuring and Mitigating Web Performance Bottlenecks in Broadband Access Networks , 2014 .

[5]  Ritesh Kumar,et al.  Efficient beacon placement for network tomography , 2004, IMC '04.

[6]  Nick Feamster,et al.  Web performance bottlenecks in broadband access networks , 2013, SIGMETRICS '13.

[7]  Ramesh K. Sitaraman,et al.  Video Stream Quality Impacts Viewer Behavior: Inferring Causality Using Quasi-Experimental Designs , 2012, IEEE/ACM Transactions on Networking.

[8]  Fabián E. Bustamante,et al.  Need, Want, Can Afford: Broadband Markets and the Behavior of Users , 2014, Internet Measurement Conference.

[9]  John P. Rula,et al.  Crowdsourcing ISP characterization to the network edge , 2011, W-MUST '11.

[10]  Chadi Barakat,et al.  Reformulating the Monitor Placement Problem: Optimal Network-Wide Sampling , 2006, 2006 40th Annual Conference on Information Sciences and Systems.

[11]  Nick Feamster,et al.  Community contribution award -- Measuring and mitigating web performance bottlenecks in broadband access networks , 2013, Internet Measurement Conference.