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.

SANTaClass: A Self Adaptive Network Traffic Classification system

Abstract: A critical aspect of network management from an operator's perspective is the ability to understand or classify all traffic that traverses the network. The failure of port based traffic classification technique triggered an interest in discovering signatures based on packet content. However, this approach involves manually reverse engineering all the applications/protocols that need to be identified. This suffers from the problem of scalability; keeping up with the new applications that come up everyday is very challenging and time-consuming. Moreover, traditional approach of developing signatures once and using them in different networks suffers from low coverage. In this work, we present a novel fully automated packet payload content (PPC) based network traffic classification system that addresses the above shortcomings. Our system learns new application signatures in the network where classification is desired. Further more, our system adapts the signatures as the traffic for an application changes. Based on real traces from several service providers, we show that our system is capable of detecting (1) tunneled or wrapped applications, (2) applications that use random ports, and (3) new applications. Moreover, it is robust to routing asymmetry, an important requirement in large ISPs, and has a very high (>99.5%) detection rate. Finally, our system is easy to deploy and setup and performs classification in real-time.

Network link dimensioning : a measurement & modeling based approach

Abstract: Adequate network link dimensioning requires a thorough insight into the interrelationship between: (i) the traffic offered (in terms of the average load, but also its fluctuations), (ii) the desired level of performance, and (iii) the required bandwidth capacity. It is clear that more capacity is needed when the average traffic load becomes higher, the fluctuations become fiercer, or the performance criterion becomesmore stringent. Existing approaches to network link dimensioning are often based on rules of thumb, e.g., `take the average traffic rate at timeswhen the network is relatively busy, and add 30%to cater for fluctuations?. Clearly, such an approach does not explicitly incorporate the fierceness of the traffic rate?s fluctuations, or the desired level of performance. A common approach to estimate the average traffic rate is as follows. A networkmanager regularly polls the so-called Interfaces Group MIB via the Simple NetworkManagement Protocol (SNMP), for instance through a tool such as the Multi-Router Traffic Grapher (MRTG). This yields the average rate of the offered traffic since the last poll. The polling interval generally is in the order of 5minutes. Evidently, the fierceness of fluctuation of the traffic rate within these 5 minute intervals is unknown to the network manager. These fluctuations may, however, be considerably large, and noticeable to users of the network. If, at timescales of say 5 seconds, more traffic is offered to a network link than it can transfer during that interval, traffic may be lost. Such loss is generally known as possibly leading to performance degradation and this may well be noticeable to a network user; for instance, entirewords may be lost in a (voice) conversation. Hence, it is in the interest of network users, and for obvious business reasons also to network operators, to have sufficient bandwidth capacity available to meet the demand at timescales considerably smaller than 5 minutes. In this thesis, we develop an alternative approach to network link dimensioning, which explicitly incorporates the offered traffic in terms of both the average rate as well as its fluctuations at small timescales, and the desired level of performance. This is expressed throughmathematical formulas that give the required bandwidth capacity, given the characteristics of the offered traffic, and the performance criterion.

Towards Time-Parallel Road Traffic Simulation

Abstract: As an alternative to spatial parallelization of simulation models, time-parallel simulation offers the potential for massive parallelism with a high level of independence between the parallel processes. Unfortunately, due to inherent problems, the applicability of time-parallel simulation is restricted. Therefore, it has been proposed recently, to use approximation with time-parallel simulation in order to facilitate its application and to extend the class of models suitable for time-parallel simulation. As a proof-of-concept, this work shows how approximate temporal parallelization can be applied to the simulation of road traffic. Traffic simulation is used extensively in transportation research for various purposes, e.g. analysis of traffic phenomena, traffic forecast, and optimization of traffic flow. Depending on the level of fidelity, a traffic model exhibits a state space of moderate to high complexity. This paper is intended to discuss the basic properties of time-parallel traffic simulation and to examine its feasibility. Experiments with a sequential microscopic traffic simulator, that emulates important aspects of a corresponding time-parallel simulator, suggest this feasibility.