Network traffic simulation

About: Network traffic simulation is a research topic. Over the lifetime, 4535 publications have been published within this topic receiving 74606 citations.

Statistical profile generation for traffic monitoring using real-time UAV based video data

Abstract: The eye-in-the-sky alternative to collecting real-time temporal/spatial data using small unmanned helicopters is proposed to: monitor traffic, evaluate and assess traffic patterns and provide accurate vehicle counts. Collected real-time visual data are converted to traffic statistical profiles and used as continuously updated inputs to existing traffic simulation models improving calibration, accuracy (in terms of variable parameter values) and future traffic predictions. Functionality of simulation models is enhanced, and reliability is improved The proposed approach offers significant advantages over conventional methods where historical and outdated data is used to run poorly calibrated traffic simulation models.

Geo-intelligent traffic manager

Abstract: A traffic manager (30) determines the geographic locations of end points on Internet traffic and routes the traffic in the most efficient manner. A set of analyzers may be disposed to analyze the network, such as the geographic locations of nodes in the network, latency times and speed between nodes, available bandwidth, etc. The traffic manager obtains this intelligence on the network from the analyzers and routes traffic accordingly. The traffic manager considers not only the most direct route but also considers the speed, available bandwidth, and reliability of the routing.

Traffic prediction using FARIMA models

Abstract: Previous traffic measurements have found the coexistence of both long-range and short-range dependence in network traffic. Therefore, models are required to predict traffic that has both long-range and short-range dependence. This paper provides a procedure to model and predict traffic using FARIMA (p,d,q) models. Our experiments illustrate that the FARIMA model is a good model and is capable of capturing the property of actual traffic. We provide guidelines to simplify the FARIMA model fitting procedure and thus to reduce the time of traffic modeling and prediction.

Traffic engineering in multigranularity heterogeneous optical WDM mesh networks through dynamic traffic grooming

Abstract: In this article we investigate the problem of efficiently provisioning connections of different bandwidth granularities in a heterogeneous WDM mesh network through dynamic traffic grooming schemes under traffic engineering principles Due to the huge amount of traffic a WDM backbone network can support and the large geographic area it can cover, constructing and upgrading such an optical WDM network can be costly Hence, it is extremely important for network operators to apply traffic engineering strategies to cost-effectively support different bandwidth granularity services using only the appropriate amount of network resources This requires an optical WDM network to have multigranularity switching capability, and such a network tends to be a multivendor heterogeneous network However, WDM network heterogeneity increases the difficulty and challenge of efficient traffic provisioning In this article we present different TE issues that need to be carefully considered in such an optical WDM network, and propose possible solutions and extensions for the generalized multiprotocol label switching optical network control plane We extend an existing generic graph model to perform efficient traffic grooming and achieve different TE objectives through simple shortest path computation algorithms We show that our approach is very practical and very suitable for traffic engineering in a heterogeneous multigranularity optical WDM mesh network

Fluid simulation of large scale networks: Issues and tradeoffs

Abstract: Traditional discrete-event packet-level approaches to simulating computer networks become computationally infeasible as the number of network nodes or their complexity increases. An alternative approach, in which packet-level traffic sources are replaced by fluid sources, has been proposed to address this challenge. In this paper we compare the amount of computational effort needed to simulate a network using a packet-level approach versus a fluid-based approach. We quantitatively characterize the amount of computational effort needed by each approach using the notion of a simulation’s event rate, and derive expressions for the event rate of a packet and fluid flow at both the input and output sides of a queue. We show that fluid simulation can require less computational effort for simple networks. However, as the network size and complexity grow, the so-called ”ripple effect” can result in fluid simulations becoming more expensive than their packet-level counterparts. This suggests that time-driven (approximate) fluid simulation techniques may be needed to efficiently simulate large scale networks.