Practical large-scale latency estimation

Szymaniak, Michal; Presotto, David L.; Pierre, Guillaume; Steen, Maarten van

doi:10.1016/j.comnet.2007.11.022

Cited by 39 publications

(29 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead, we map undefined IP addresses to an agnostic /n prefix. Szymaniak et al show that latencies are globally equivalent within the same /24 prefix on the Internet [3]. Based on that, Szymaniak et al suggest to use a /24 cluster division (equivalent to what we call 24-agnostic Clustering in this paper) to reduce the amount of required measurement.…”

Section: Clustering Techniquesmentioning

confidence: 94%

“…All the nodes sharing the same n bits prefix are put in the same cluster. The /24 division proposed by Szymaniak et al [3] is a particular case of such a technique (i.e., 24-agnostic clustering). BGP Clustering: clusters are built according to BGP.…”

Section: Clustering Techniquesmentioning

confidence: 99%

“…Another way is to allow collaboration between probing monitors and to cluster probe targets. Clustering means aggregating a subset of targets into the same hat and considering a measurements towards one of the target as being representative of the whole cluster [2,3,4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

On the Impact of Clustering on Measurement Reduction

2009

View full text Add to dashboard Cite

Abstract. Measuring a path performance according to one or several metrics, such as delay or bandwidth, is becoming more and more popular for applications. However, constantly probing the network is not suitable. To make measurements more scalable, the notion of clustering has emerged. In this paper, we demonstrate that clustering can limit the measurement overhead in such a context without loosing too much accuracy. We first explain that measurement reduction can be observed when vantage points collaborate and use clustering to estimate path performance. We then show, with real traces, how effective is the overhead reduction and what is the impact in term of measurement accuracy.

show abstract

Section: Clustering Techniquesmentioning

confidence: 94%

Section: Clustering Techniquesmentioning

confidence: 99%

See 1 more Smart Citation

On the Impact of Clustering on Measurement Reduction

2009

View full text Add to dashboard Cite

show abstract

“…Ledlie et al [14] analyze the implementation of the Vivaldi algorithm in Azureus, a popular Bit-Torrent client, and Szymaniak et al [30] report on utilizing GNP in the Google content delivery network. We return to the latter paper in Section 7.2.…”

Section: Related Workmentioning

confidence: 99%

“…Second, we study its performance in the context of some specific overlay applications -host clustering and server selection. Third, we performed a a live Internet study comparing the quality of server selection in the Akamai content delivery network [1] using our approach and GNP, which was previously proposed for a similar task [30].…”

Section: Introductionmentioning

confidence: 99%

Dynamic landmark triangles: A simple and efficient mechanism for inter-host latency estimation

Wen

Rabinovich

2011

Computer Networks

View full text Add to dashboard Cite

This paper describes a simple and efficient approach to estimate the network latency between arbitrary Internet hosts. We use three landmark hosts forming a triangle in two-dimensional space to estimate the distance between arbitrary hosts with simple trigonometrical calculations. To improve the accuracy of estimation, we dynamically choose the "best" triangle for a given pair of hosts using a heuristic algorithm. Experiments using several data sets of measured host-pair latencies, as well as a live Internet study, demonstrate the accuracy and efficiency of our approach.

show abstract

Network‐aware service composition in mobile environment

Ding

Chen

Pan

et al. 2016

Concurrency and Computation

View full text Add to dashboard Cite

Summary In the mobile environment, users will use mobile devices to enjoy different services, such as surfing the Internet, shopping online, or paying bills. And the network latency will greatly affect the performance of services, which influences the users using experience at the same time. Many service selection methods have treated network latency as QoS, but they do not consider the issue of user's mobility that resulting inconstantly changing of latency when existing information transmission between the user and services in mobile environment. So it is meaningful to take it into consideration to select globally optimal service to solve the practical problem. In this paper, we consider the user's movement, estimate the network latency by Euclidean distance, and propose a service composition algorithm in mobile environment to provide the best service scheme with the basic idea of dynamic programming. Finally, we make experiments by changing different factors and obtain lower latency compared with the traditional method; reflecting service composition algorithm in mobile environment can better adapt to the user's mobility and uncertain times of interaction between the user and services. Copyright © 2016 John Wiley & Sons, Ltd.

show abstract

Practical large-scale latency estimation

Cited by 39 publications

References 15 publications

On the Impact of Clustering on Measurement Reduction

On the Impact of Clustering on Measurement Reduction

Dynamic landmark triangles: A simple and efficient mechanism for inter-host latency estimation

Network‐aware service composition in mobile environment

Contact Info

Product

Resources

About