Margento RandD

Maribor, Slovenia

Margento RandD

Maribor, Slovenia

Time filter

Source Type

Fras M.,Margento RandD | Mohorko J.,Tehnovitas RandD | Cucej Z.,University of Maribor
Simulation | Year: 2012

In the process of network traffic modeling, for simulation purposes, there is often a need for statistical description of traffic data sources. Usually, the network traffic is measured by capturing packets at a physical level. Normally, the estimation of statistical description of traffic data sources cannot be derived directly from such captured packets traffic. For that reason, we have researched for simpler solutions, which are based on the estimation of statistical processes of traffic data sources from the measured packet network traffic. We have developed the estimation methods, which allow the estimation of suitable probability distribution functions and their parameters of stochastic processes of traffic data sources. Statistical distributions of network traffic processes, such as data lengths process and data inter-arrival time, are important since they can be used for modeling of network traffic in simulation tools. For that reason, the estimation method is firstly developed, which mimics the defragmentation process. This method allows an estimation of distributions of data source network traffic processes and their parameters for captured packet traffic.During further testing, this method shows some limitations, especially for the process of data lengths. For that reason, we have developed a new estimation method with the approach described in this paper in further detail. In the new estimation method, which is called estimation method based on histogram comparison (EMHC), we use the opposite concept where distribution of data lengths is transformed by a developed analytical model to a packet size's histogram. The latter is further compared to a packet size histogram of captured packet traffic. The optimization method is used to find such distribution parameters of the data length process that cause minimal discrepancies between the histogram of captured packets and the estimated packet size histogram. To estimate the discrepancy between two histograms, a well-known π2 test is used, which is modified by a weighting function that considers, beside packet frequencies, the packet lengths as well. The proposed algorithm and method are confirmed through validations and experiments in a simulation tool. © 2012 The Society for Modeling and Simulation International.


Fras M.,Margento RandD | Mohorko J.,Tehnovitas RandD | Cucej Z.,University of Maribor
Computer Networks | Year: 2013

Knowing the estimation of a statistical process's parameters for measured network traffic is very important as it can then be further used for the statistical analyses and modeling of network traffic in simulation tools. It is for this reason that different estimation methods are proposed that allow estimations of the statistical processes of network traffic. One of them is our own histograms comparison (EMHC) based method that can be used to estimate statistical data-length process parameters from measured packet traffic. The main part of EMHC method is Mapping Algorithm with Fragmentation Mimics (MAFM). The MAFM algorithm allows the estimation of a theoretical packet-size histogram for different distributions of the data-length process. In this paper describes in detail the limitations of a developed algorithm, which are correlates with the long-range dependence of data-length distribution. It is shown that a developed MAFM algorithm has limited usability for distribution types which do not posses the finite value of an expected value. In order to improve the robustness for such types of distribution, the new parameter ULS (Upper Limit of Summa) is involved in the original MAFM algorithm. The ULS parameter limits the tail of the distribution. By assuming a finite ULS value, the MAFM algorithm can now be used for all distributions of the data-length process, as well as for distributions without a defined expected value, such as Pareto. The presented analytical results have been confirmed by experiments through the use of the simulation tool. © 2013 Elsevier B.V. All rights reserved.


Fras M.,Margento RandD | Mohorko J.,University of Maribor | Cucej Z.,University of Maribor
Informacije MIDEM | Year: 2010

The Modeling, analysis and simulation of self-similar traffic has become the main goal of much research work around the world, over the last 15 years. In our research we measured many different types of real traffic in different networks and classified it on the basis of analysis in the sense of selfsimilarity and long-range dependence. We used estimated statistical parameters for measured network traffic in order to model this traffic in simulation tool OPNET. We used the following statistical criteria for successful modeling: average bit rate, average packet rate, Hurst parameter, and histograms of statistical network traffic processes. During measurements and simulations we discovered that the shape parameter of Pareto distribution has a great impact on simulated traffic, and also that classical estimation usually leads to significant discrepancies between measured and simulated traffic in the sense of average bit rate and also bursts, which are characteristic of self-similar traffic. So, we developed a novel method for estimating the shape parameter of Pareto distribution which shows successful results regarding the chosen criteria, during the testing process.

Loading Margento RandD collaborators
Loading Margento RandD collaborators