Statistical Characteristics of Active IP One Way Delay Measurements

Holleczek, Peter; Karch, Roland; Kleineisel, Ralf; Kraft, Stephan; Reinwand, Jochen; Venus, Verena

doi:10.1109/icns.2006.106

Cited by 19 publications

(10 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The delay distribution of the generic link ℓ (ie, the delay ground truth) was generated from a Gamma distribution, which was found to be a good fit for real‐world measurements in several measurement studies …”

Section: Simulation Resultsmentioning

confidence: 99%

“…Indeed, real delay distributions tend to be skewed, with a heavier tail compared to the exponential decay of the Gaussian distribution. (17)(18)(19)(20) This is basically due to the fact that regular conditions dominate in well-designed systems, but occasionally longer delays are observed due to overload and other effects, thus producing skewed tail. The pdf of the Pearson Type IV distribution is given by…”

Section: Moment-based Fitting Of the Pearson Type IVmentioning

confidence: 99%

See 1 more Smart Citation

On the estimation of link delay distributions by cumulant‐based moment matching

Coluccia

Ricciato

2017

Internet Technology Letters

View full text Add to dashboard Cite

The statistical distribution of packet delays across individual nodes or links embeds important information for network management. For instance, upward shift of the delay distribution could point to local congestion, node mis‐functioning, or other undesirable events. Since directly measuring delays at individual links is not always possible, a problem that has been studied under the term of network delay tomography is to infer “internal” delays (per link) from “external” measurements (per path). We propose a novel estimation idea based on a combination of 2 tools from formal statistics, namely the cumulant method and the moment matching method. An outstanding feature of this approach is the extremely low implementation cost in terms of local computation and communication overhead. We formalize the estimation framework and develop a method with final closed‐form solutions. The correctness of the analysis framework is validated on synthetic data obtained via simulations.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

Section: Moment-based Fitting Of the Pearson Type IVmentioning

confidence: 99%

On the estimation of link delay distributions by cumulant‐based moment matching

Coluccia

Ricciato

2017

Internet Technology Letters

View full text Add to dashboard Cite

show abstract

“…This observation gives rise to the assumption that the routing delay X measured on such a connection can typically be modeled by underlying probability distributions as shown in [5]. More precisely, the modeling process assumes that X follows a probability density function f (x|θ) with a parameter vector θ.…”

Section: Modeling Of Routing Delaymentioning

confidence: 99%

“…One promising candidate identified in [5] is the Gamma distribution, which is suited well in many network situations [4] and has the following density function:…”

Section: A Single Probability Distributionsmentioning

confidence: 99%

Statistical Analysis of IP Delay Measurements as a Basis for Network Alert Systems

Holleczek

Venus

Naegele-Jackson

2009

2009 IEEE International Conference on Communications

Self Cite

View full text Add to dashboard Cite

Measuring packet delay and packet loss through dedicated test packet streams in computer networks allows for the assessment of Quality of Service on the path the probes traverse. For this reason, active IP performance measurements have been carried out in X-WiN, Germany's National Research and Educational Network, and GÉANT2, its European counterpart, by the WiN-Labor Group of the University of Erlangen-Nuremberg for many years. This paper provides an overview of how network measurements can be interpreted using a variety of statistical concepts in order to gain insight into the state of monitored connections. The focus here is set on the analysis of One-Way Delay (OWD); the approach demonstrates how OWD can be used for the identification of network congestions and can serve as a basis for network alert systems by statistically categorizing changes in the performance metric.

show abstract

“…HADES was developed and deployed as a tool that provides performance measurements and offers IP performance metrics such as oneway delay, one-way delay variation, and packet loss [9]. The main purpose of the experiment was to collect and archive these IP performance metrics over an extended period of time and make the data available to other FEDERICA project partners and experiments that needed reference data as part of their investigations on the behavior of virtualized networks and slice processing.…”

Section: Validation Of Virtual Infrastructure Featuresmentioning

confidence: 99%

Enabling future internet research: the FEDERICA case

Szegedi

Riera²,

Garcia-Espin³

et al. 2011

IEEE Commun. Mag.

View full text Add to dashboard Cite

The Internet, undoubtedly, is the most influential\ud technical invention of the 20th century\ud that affects and constantly changes all aspects\ud of our day-to-day lives nowadays. Although it\ud is hard to predict its long-term consequences,\ud the potential future of the Internet definitely\ud relies on future Internet research. Prior to\ud every development and deployment project, an\ud extensive and comprehensive research study\ud must be performed in order to design, model,\ud analyze, and evaluate all impacts of the new\ud initiative on the existing environment. Taking\ud the ever-growing size of the Internet and the\ud increasing complexity of novel Internet-based\ud applications and services into account, the\ud evaluation and validation of new ideas cannot\ud be effectively carried out over local test beds\ud and small experimental networks. The gap\ud which exists between the small-scale pilots in\ud academic and research test beds and the realsize\ud validations and actual deployments in production\ud networks can be bridged by using\ud virtual infrastructures. FEDERICA is one of\ud the facilities, based on virtualization capabilities\ud in both network and computing resources,\ud which creates custom-made virtual environments\ud and makes them available for Future\ud Internet Researchers. This article provides a\ud comprehensive overview of the state-of-the-art\ud research projects that have been using the virtual\ud infrastructure slices of FEDERICA in\ud order to validate their research concepts, even\ud when they are disruptive to the test bed’s infrastructure,\ud to obtain results in realistic network\ud environments.Postprint (published version

show abstract

Statistical Characteristics of Active IP One Way Delay Measurements

Cited by 19 publications

References 1 publication

On the estimation of link delay distributions by cumulant‐based moment matching

On the estimation of link delay distributions by cumulant‐based moment matching

Statistical Analysis of IP Delay Measurements as a Basis for Network Alert Systems

Enabling future internet research: the FEDERICA case

Contact Info

Product

Resources

About