Network traffic prediction based on a new time series model

Yin, Hao; Chen, Lin; Berton, Sebastien; Li, Bo; Min, Geyong

doi:10.1002/dac.721

Cited by 25 publications

(15 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Alternative methods for generating traffic matrices can be found in [25], for instance, the gravity model, as well as other online prediction approaches [26].…”

Section: Finding Communitiesmentioning

confidence: 99%

Community‐based traffic preservation in telecommunication networks

Torres-Padrosa

Manzano

Calle

et al. 2013

Int J Communication

View full text Add to dashboard Cite

Large-scale failures in telecommunication networks have been traditionally mitigated by attempting to preserve global connectivity in the network. However, although communication inside communities may be of high relevance, their preservation is a challenging task. To achieve this, we propose a new concept of community that combines not only the topological information of the network but also the traffic-level interaction. This new concept is then used to present six novel community-based strategies that, when working within a limited budget, are able to determine which are the best candidate nodes to protect. The strategies proposed have been tested over four different types of networks and have been compared with other well-known immunization or protection methods. Results show that community-based strategies better preserve the inner community traffic with respect to traditional approaches. Furthermore, in some cases, both global and intra-community traffic preservation is able to be improvedThis work is partly supported by the Spanish Ministerio de Ciencia e Innovacion through project RoGER (Robustness against large-scale failures in interdomain routing, TEC2012-32336), Juan de la Cierva subprogram grant no. JCI-2010-08322, and by the Generalitat de Catalunya through the Research Support Program project SGR-1202 and AGAUR FI-DGR 2012 gran

show abstract

“…Alternative methods for generating traffic matrices can be found in [25], for instance, the gravity model, as well as other online prediction approaches [26].…”

Section: Finding Communitiesmentioning

confidence: 99%

Community‐based traffic preservation in telecommunication networks

Torres-Padrosa

Manzano

Calle

et al. 2013

Int J Communication

View full text Add to dashboard Cite

show abstract

“…Time series analysis [38,39,40,41,42,43] can be used to predict future values in a dynamic system. The theorem proposed by Takens [44] states that a non-linear chaotic dynamic system can be reconstructed from a sequence of observations.…”

Section: Time Series Analysismentioning

confidence: 99%

Predicting expected TCP throughput using genetic algorithm

2016

View full text Add to dashboard Cite

Predicting the expected throughput of TCP is important for several aspects such as e.g. determining handover criteria for future multihomed mobile nodes or determining the expected throughput of a given MPTCP subflow for load-balancing reasons. However, this is challenging due to time varying behavior of the underlying network characteristics. In this paper, we present a genetic-algorithm-based prediction model for estimating TCP throughput values. Our approach tries to find the best matching combination of mathematical functions that approximate a given time series that accounts for the TCP throughput samples using genetic algorithm. Based on collected historical datapoints about measured TCP throughput samples, our algorithm estimates expected throughput over time. We evaluate the quality of the prediction using different selection and diversity strategies for creating new chromosomes. Also, we explore the use of different fitness functions in order to evaluate the goodness of a chromosome. The goal is to show how different tuning on the genetic algorithm may have an impact on the prediction. Using extensive simulations over several TCP throughput traces, we find that the genetic algorithm successfully finds reasonable matching mathematical functions that allow to describe the TCP sampled throughput values with good fidelity. We also explore the effectiveness of predicting time series throughput samples for a given prediction horizon and estimate the prediction error and confidence.

show abstract

“…An evaluation of short-term traffic forecasting algorithms in wireless networks can be found in [8] where several traffic models have been proposed taking into account the periodicity and recent history of network traffic using the IEEE802.11 wireless infrastructure. Several research studies have also been conducted for characterising traffic in wired networks [9,10]. Only a handful of studies can examine wireless traffic loads, and there are even fewer studies into short-term traffic forecasting for wireless networks.…”

Section: Introductionmentioning

confidence: 99%

Traffic modelling and forecasting using genetic algorithms for next-generation cognitive radio applications

Thilakawardana

Moessner

2009

Ann. Telecommun.

View full text Add to dashboard Cite

This article presents a genetic-algorithm-based prediction model for forecasting traffic demands of nextgeneration wireless networks that are expected to be chaotic in nature. The model approximates the best-fit mathematical equation that generates a given time series using a genetic algorithm. It estimates future traffic in wireless networks using the most recent traffic data points collected from the actual network. Such estimations will be beneficial for network operators helping to manage and optimise the limited radio resources efficiently and eventually to facilitate cognitive radio applications. The new model is compared with conventional regressions analysis and exponential smoothing models, and it has been found that the genetic algorithm model successfully recovers the underlying mathematical expression describing chaotic time series in less than 200 generations and the predictions achieved are by far better than those of regression and exponential smoothing models. The model also offers benefits for in cognitive communication systems with their intrinsic learning capabilities and distributed access decisions.

show abstract

Network traffic prediction based on a new time series model

Cited by 25 publications

References 27 publications

Community‐based traffic preservation in telecommunication networks

Community‐based traffic preservation in telecommunication networks

Predicting expected TCP throughput using genetic algorithm

Traffic modelling and forecasting using genetic algorithms for next-generation cognitive radio applications

Contact Info

Product

Resources

About