A predictability analysis of network traffic

Sang, Aimin; Li, San-Qi

doi:10.1016/s1389-1286(01)00304-8

Cited by 199 publications

(99 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Best mean square error linear predictor: This is the predictor in 1, which provides a minimum on the square error and has been adopted in other papers [3], [5], [4]. While this is the best linear predictor we note that non-linear predictors, for instance wavelet-based [3], which are tailored to the specific case of long-range dependent processes, can provide further improvements in prediction error.…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

On linear prediction of Internet traffic for packet and burst switching networks

Morató

Aracil²,

Díez³

et al.

Proceedings Tenth International Conference on Computer Communications and Networks (Cat. No.01EX495)

View full text Add to dashboard Cite

Abstract-In this paper, we show that prediction algorithms in the least mean square error sense prove better in a burst rather than in a packet switching network. For the latter, further information about the packet arrival distribution within the prediction interval is required. Regarding burst switching, we compare Optical Burst Switching networks with and without linear prediction to conclude that linear prediction provides a significant improvement in end-to-end latency with low bandwidth waste.

show abstract

Section: Resultsmentioning

confidence: 99%

“…For video and network data traffic, linear prediction methods have been considered in the literature as a simple and effective alternative [3], [4], [5]. Let Ò · ½ ´´Ò · ½ µ µ ´Ò µ ´Ø · µ ´Øµ, Ò ¼ ½ AE ½ with Ø Ò .…”

Section: Introductionmentioning

confidence: 99%

On linear prediction of Internet traffic for packet and burst switching networks

Morató

Aracil²,

Díez³

et al.

Proceedings Tenth International Conference on Computer Communications and Networks (Cat. No.01EX495)

View full text Add to dashboard Cite

show abstract

“…Again, the authors concluded that predictions are dependent on the timescale -sub-second prediction performing consistently worse -and on the specific type of the network trace. The work presented in [26] analyzes the predictability of network traffic bit rates using AutoRegressive Moving Average (ARMA) and Markov-Modulated Poisson Process (MMPP) models. Under the assumption that those models are appropriate, authors of [26] developed analytic expressions to describe bounded predictability.…”

Section: State-of-the-artmentioning

confidence: 99%

“…The work presented in [26] analyzes the predictability of network traffic bit rates using AutoRegressive Moving Average (ARMA) and Markov-Modulated Poisson Process (MMPP) models. Under the assumption that those models are appropriate, authors of [26] developed analytic expressions to describe bounded predictability. Traffic aggregation and smoothing proved to monotonically increase the predictability of the network traffic.…”

Section: State-of-the-artmentioning

confidence: 99%

Packet loss reduction during rerouting using network traffic analysis

Tavernier

Papadimitriou²,

Colle

et al. 2011

Telecommun Syst

View full text Add to dashboard Cite

Upon certain network events, such as node or link failures, IP routers need to update their affected routing table entries. During the period between the failure occurrence and the installation of the updated entries (on the line cards), the network traffic is lost when forwarded by routers that are still using old entries. Indeed, current IP routers do not involve network traffic information during this unordered update process. The consequence is more packet losses compared to a process that would order these entries based on local traffic information. In this paper, we model and predict network traffic passing through an IP router and define two dynamic heuristics in order to reduce the packet loss resulting from routing table updates. AutoRegressive Integrated Moving Average (ARIMA) -Generalized AutoRegressive Conditional Heteroskedasticity (GARCH) traffic models are used in combination with heuristics that dynamically sort the routing entries and improve the low-level routing table update process. In a realistic simulation environment, we show that this setup can result into a clear decrease of packet loss, depending on i) the network traffic model, ii) the applied heuristic, and iii) the network traffic aggregation level.

show abstract

“…They used a linear prediction model that is solved through WienerHopf equations. Sang and Li [15] assessed the predictability of traffic by considering how far into the future a traffic rate process can be predicted with bounded error and what the minimum prediction error is over a specified prediction time interval. They used two models, namely the auto-regressive moving average and the Markov-modulated Poisson process and concluded that the applicability of traffic prediction is limited by the deteriorating prediction accuracy with increasing prediction interval.…”

Section: Traffic Predictionmentioning

confidence: 99%

The stability of paths in a dynamic network

Kuipers

Wang

Mieghem

2005

Proceedings of the 2005 ACM Conference on Emerging Network Experiment and Technology - CoNEXT'05

View full text Add to dashboard Cite

Dynamic networks appear in several contexts: QoS routing faces the difficult problem of accurately and efficiently maintaining, distributing and updating network state information, and in wireless ad hoc networking, signal strength fluctuations complicate the choice of stable paths. In this paper we will focus on the stability of paths in a network with dynamically changing link weights. The level of path stability has a direct relation to the number of updates that are necessary to maintain an accurate view of the network state. If a small change in the network state does not affect the shortest path, then such a change need not be distributed throughout the network. We evaluate path stability by adding noise and observing the change in paths.

show abstract

A predictability analysis of network traffic

Cited by 199 publications

References 18 publications

On linear prediction of Internet traffic for packet and burst switching networks

On linear prediction of Internet traffic for packet and burst switching networks

Packet loss reduction during rerouting using network traffic analysis

The stability of paths in a dynamic network

Contact Info

Product

Resources

About