Implications of the topological properties of Internet traffic on traffic engineering

Uhlig, Steve; Bonaventure, O.; Magnin, Vincent; Rapier, Chris; Deri, Luca

doi:10.1145/967900.967974

Cited by 17 publications

(36 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The implications of Section 4 reinforce the findings of [22]. These implications do not mean that modeling Internet traffic on the AS-topology is out of reach.…”

Section: Distance Between Consecutive Time Intervalssupporting

confidence: 59%

“…This indicates that the global traffic distribution is very different from the short-term traffic distribution. As already hinted in [22], the topological traffic distribution observed over large timescales is not representative of the traffic distribution over shorter time intervals. …”

Section: Traffic Similaritymentioning

confidence: 87%

“…Those studies have concluded that a few popular source-destinations (end-hosts or networks) do account for the majority of the traffic. [22] has shown that this picture of traffic over-simplifies reality. In practice, only a subset of the sourcedestination pairs is stable on timescales smaller than hours.…”

Section: Distance Between Individual Time Intervals and Global Traffimentioning

confidence: 99%

“…Modeling traffic dynamics should thus require relatively small changes over time. However, as shown in [22], the traffic on different parts of the AS topology has different dynamics. In Section 6, we will analyze this dynamics of the traffic on AS-level edges.…”

Section: Traffic Distance Between Time Intervalsmentioning

confidence: 99%

“…Previous work has shown that traffic observed by an AS has a tree-like structure rooted at the observing AS and whose leafs are the destination ASs [21,22], and on average edges farther away from the root see less traffic. We thus expect that different edges observed different traffic dynamics.…”

Section: Amount Of Traffic Vs Lifetimementioning

confidence: 99%

See 4 more Smart Citations

Capturing Internet Traffic Dynamics through Graph Distances

Uhlig

Jamakovic³

2009

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Self Cite

View full text Add to dashboard Cite

Abstract. Studies of the Internet have typically focused either on the routing system, i.e. the paths chosen to reach a given destination, or on the evolution of traffic on a physical link. In this paper, we combine routing and traffic, and study for the first time the evolution of the traffic on the Internet topology. We rely on the traffic and routing data of a large transit provider, spanning almost a month. We compute distances between the traffic graph over small and large timescales. We find that the global traffic distribution on the AS graph largely differs from traffic observed at small timescales. However, variations between consecutive time periods are relatively limited, i.e. the topology spanned by the traffic from one time period to the next is small. This difference between local and global traffic distribution is found in the timescales at which traffic dynamics occurs on AS-level links. Small timescales, i.e. less than a few hours, do not account for a significant fraction of the traffic dynamics. Most of the traffic variability is concentrated at timescales of days. Models of Internet traffic on its topology should thus focus on capturing the long-term changes in the global traffic pattern.

show abstract

“…The implications of Section 4 reinforce the findings of [22]. These implications do not mean that modeling Internet traffic on the AS-topology is out of reach.…”

Section: Distance Between Consecutive Time Intervalssupporting

confidence: 59%

Section: Traffic Similaritymentioning

confidence: 87%

Section: Distance Between Individual Time Intervals and Global Traffimentioning

confidence: 99%

Section: Traffic Distance Between Time Intervalsmentioning

confidence: 99%

Section: Amount Of Traffic Vs Lifetimementioning

confidence: 99%

See 3 more Smart Citations

Capturing Internet Traffic Dynamics through Graph Distances

Uhlig

Jamakovic³

2009

Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

A BGP Solver for Hot-Potato Routing Sensitivity Analysis

Quoitin¹,

Tandel²

IFIP International Federation for Information Processing

View full text Add to dashboard Cite

The interactions between the IGP and BGP routing protocols which are running inside an ISP's network are sometimes hard to understand. The problem becomes particularly complex when there are dozens of routers/links and several thousands of destination prefixes. In this paper, we present a publicly available routing solver to evaluate routing what-if scenarios. The solver is able to model the complete network of an ISP and given the external routes learned by this ISP, to compute the paths towards all the destination prefixes. We demonstrate the use of our routing solver, C-BGP, by showing the results of an analysis of the link/router failure sensitivity in a transit network. Based on the analysis' results, we can pinpoint links/routers whose failure has an important impact on the selection of BGP routes. The deployment of protection techniques that are used for optical links, SONET-SDH and MPLS should be considered for these links/routers.

show abstract

Interdomain Ingress Traffic Engineering Through Optimized AS-Path Prepending

Gao

Dovrolis

Zegura

2005

NETWORKING 2005. Networking Technologies, Services, and Protocols; Performance of Computer and Communication Networks; Mobile A

View full text Add to dashboard Cite

Abstract. In INterdomain Ingress Traffic Engineering (INITE), a "target" Autonomous System (AS) aims to control the ingress link at which the traffic of one or more upstream source networks enters that AS. In practice, ISPs often manipulate, mostly in a trial-and-error manner, the length of the AS-Path attribute of upstream routes through a simple technique known as prepending (or padding). In this paper, we focus on prepending and propose a polynomial-time algorithm (referred to as OPV) that determines the optimal padding for an advertised route at each ingress link of the target network. Specifically, given a set of "elephant" source networks and some maximum load constraints on the ingress links of the target AS, OPV determines the minimum padding at each ingress link so that the load constraints are met, when it is feasible to do so. OPV requires as input an AS-Path length estimate from each source network to each ingress link. We describe how to estimate this matrix, leveraging the BGP Looking Glass Servers. To deal with unavoidable inaccuracies in the AS-Path length estimates, and also to compensate for the generally unknown BGP tie-breaking process in upstream networks, we also develop a robust variation (RPV) of the OPV algorithm.

show abstract

Implications of the topological properties of Internet traffic on traffic engineering

Cited by 17 publications

References 25 publications

Capturing Internet Traffic Dynamics through Graph Distances

Capturing Internet Traffic Dynamics through Graph Distances

A BGP Solver for Hot-Potato Routing Sensitivity Analysis

Interdomain Ingress Traffic Engineering Through Optimized AS-Path Prepending

Contact Info

Product

Resources

About