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.

Mining TCP/IP Traffic for Network Intrusion Detection by Using a Distributed Genetic Algorithm

Abstract: The detection of intrusions over computer networks (i.e., network access by non-authorized users) can be cast to the task of detecting anomalous patterns of network traffic. In this case, models of normal traffic have to be determined and compared against the current network traffic. Data mining systems based on Genetic Algorithms can contribute powerful search techniques for the acquisition of patterns of the network traffic from the large amount of data made available by audit tools. We compare models of network traffic acquired by a system based on a distributed genetic algorithm with the ones acquired by a system based on greedy heuristics. Also we discuss representation change of the network data and its impact over the performances of the traffic models. Network data made available from the Information Exploration Shootout project and the 1998 DARPA Intrusion Detection Evaluation have been chosen as experimental testbed.

The impact of self-similar traffic on network delay

Abstract: The effect of self-similar traffic on the delay of a single queue system is first studied through the use of the measured traffic and models as input process. A model-driven simulation-based method is then proposed for the computation of mean line delay in a network routing design. Both the hybrid-FGN and the FARIMA algorithms have been used to synthesize self-similar sample paths. The comparison results with real-traffic data sets firmly establish the usefulness of our model-driven simulation-based method. We have proposed a practical database method that helps the designer to determine the parameters in network design. This approach may likely play an important role in network design and analysis.

A New Measure for Charcterizing Data Traffic

Abstract: It is generally recognized that data traffic has more diverse characteristics and transmission requirements than voice traffic. In particular, data traffic associated with many interactive data processing applications is often characterized to be extremely bursty, which lends support to the choice of Packet (or message) switching over circuit switching in data network design. We introduce in this paper a new measure called bursty factor for characterizing the burstiness of a data traffic source. Unlike the usual measures of peak-to-average ratio and duty cycle, the new measure introduced is independent of a specific network design and dependent only upon the traffic source characteristics and performance requirements. It can therefore be used to guide the direction of an initial network design.

Scalable Network Traffic Classification Using Distributed Support Vector Machines

Abstract: Internet traffic has increased dramatically in recent years due to the popularization of the Internet and the appearance of wireless Internet mobile devices such as smart-phones and tablets. The explosive growth of Internet traffic has introduced a practical example that demonstrates the concept of Big Data. Accurate identification and classification of large network traffic data plays an important role in network management including capacity planning, network forensics, QoS and intrusion detection. However, the state-of-the-art solutions, which rely on a dedicated server, are not scalable for analyzing high volume network traffic data. In this paper, we implement a distributed Support Vector Machines (SVMs) framework for classifying network traffic using Hadoop, an open-source distributed computing framework for Big Data processing. We design a global parameter store that maintains the global shared parameters between SVM training nodes. The distributed SVMs have been deployed on a 20 node cluster to analyze real network traffic trace. The results demonstrate that with 19 Mapper nodes the system is around 30% faster than Cloud SVM solution and outperforms the standalone SVM with nearly 9 times faster in training process and 15 times in the classifying process. In addition, the distributed SVMs architecture is designed to analyze large scale datasets. Therefore, it can be used not only for processing network traffic dataset, but also other large scale datasets such as Web data.

Overview of fluid-based quick simulation techniques for large packet-switched communication networks

Abstract: We consider a large packet-switched communication network. Traffic in such networks is heavily aggregated especially in the network core. Fluid traffic models have been used for this reason and because the individual packets are very small compared to the volume of aggregated traffic. Fluid models have also been considered for the network components themselves in order to explore the possibility of simulation speed-up. In the event-driven simulation of Kesidis et al of such a `fluid' network, a `ripple effect' was described to explain the substantial degradation in simulation speed-up as the network size grew, especially when work-conserving bandwidth schedulers were present. Thereafter, studies attempted to identify under what network dimensions and designs and under what traffic conditions the ripple effect is minimized. Hybrids of packet/fluid and event/time-driven simulation strategies were considered. This paper gives an overview of the fluid network modeling approach and surveys recent work on such hybrid approaches.© (2001) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.