Reference:
Malakhov S.V., Yakupov D.O..
Investigation of stochastic models of packet generation in computer networks
// Software systems and computational methods. – 2024. – ¹ 2.
– P. 53-72.
Read the article
Abstract: Stochastic packet generation models are models that are used to generate traffic in computer networks with certain characteristics. These models can be used to simulate network activity and test network performance. Standard data transmission on the network is packet generation with delays, in which packets are sent at certain intervals. Various stochastic models can be used to generate delayed packets, including uniform distribution, exponential distribution, and Erlang distribution. In this work, an experimental setup was assembled and a client-server application was developed to conduct research and analyze the performance of the data transmission channel. An algorithm has been proposed that allows to restore the moment characteristics of a random value of the interval between packets for further use of queuing models. The analysis of the distribution laws on the performance of the experimental network sample was performed and estimates of the efficiency of channel use and the average packet generation time in network segments, as well as histograms of delays according to the distribution laws, were obtained. An experimental setup was created, and a client-server application was developed to analyze the performance of the data transmission channel. An algorithm for restoring the moment characteristics of the time intervals between packets is proposed. The analysis of the distribution laws on network performance was carried out, estimates of the efficiency of channel use and the average packet generation time in network segments were obtained, as well as histograms of delays according to the distribution laws. The generation of packets with delays according to stochastic distribution laws (uniform, exponential, Erlang) is of great importance in modeling and analyzing the operation of network systems. Also, the generation of packets with delays according to the above-mentioned distribution laws allows testing and debugging of network applications and devices in conditions close to real ones. This allows to identify possible problems and improve the operation of network systems. As a result of the experiment, an algorithm was proposed that allows to restore the moment characteristics of a random value of the interval between packets for further use of queuing models. Also, the analysis of the influence of distribution laws on the performance of the experimental network sample was performed and estimates of the efficiency of channel use and the average packet generation time in network segments, as well as histograms of delays according to distribution laws, were obtained.
Keywords: generating packages, data transmission, traffic analysis, client-server application, delays, packet switching, Erlang distribution, exponential distribution, uniform distribution, Stochastic models
References:
Zhukova, G.N. (2015). A Map of Skewness and Kurtosis Coefficients in Teaching Probability Theory and Mathematical Statistics. Concept, 8, 1-4.
Dmitriev, E.I., & Medvedev, A.V. (2011). P-Exponential Random Number Generator. Actual Problems of Aviation and Astronautics, 7, 316-317.
Erlang distribution. (Accessed March 6, 2023). Retrieved from http://algolist.ru/maths/matstat/erlang/index.php#:~:text=%D0%A0%BC
How to use Wireshark for traffic analysis. (Accessed March 6, 2023). Retrieved from https://losst.pro/kak-polzovatsya-wireshark-dlya-analiza-trafika
Yakupov, D.O. (2023). Application for generating packets in computer networks using stochastic distribution models. Retrieved from https://elibrary.ru/item.asp?id=50133060
Tarasov, V.N., Bakhareva, N.F., Gorelov, G.A., & Malakhov, S.V. (2014). Analysis of incoming traffic at the level of three moments of time interval distributions. Information Technology, 9