DEVELOPMENT OF A METHOD FOR STUDYING TRAFFIC OF MULTISERVICE NETWORKS

Abstract

Context. The constant growth in the volume of information, the increase in the speed of information flows in digital communication networks, as before, makes the task of assessing the service stability for traffic flows an urgent one. A simple solution to ensure high service stability is to build a network of sufficient capacity for any traffic that will be thrown at it. To solve the problems of analyzing telecommunication systems, it is necessary to have appropriate models and engineering methods that allow to assess the service stability and predict the characteristics of their operation based on measurement data. In these conditions, the development of new methods for analyzing the traffic of multiservice networks that provide simplicity of calculations and their acceptable accuracy becomes especially relevant.
 Objective. The purpose of this paper is to study the traffic and service stability for users.
 Method. We propose a hybrid method for detecting anomalies in multiservice network traffic that uses algorithms without identification, adaptation and Mamdani fuzzy inference. The peculiarity of multiservice traffic as an object for assessing the existence of anomalies is the presence of stochastic processes in it subject to different distribution laws. For the experimental evaluation of the proposed method and algorithms, we have chosen the Poisson and Pareto distribution laws that define the limiting cases of traffic regularity. The method allows for monitoring and managing faults in a multiservice network in order to determine the causes of their occurrence. The following requirements are imposed on the developed algorithms for detecting anomalies in the traffic on multiservice networks: functioning in real or near real time; maintaining a given service stability; simplicity of implementation. The algorithms belong to the class of adaptive hybrid algorithms for identifying traffic parameters. They are used for both stationary and nonstationary traffic. Traffic is modeled as stochastic processes. Each belongs to the corresponding class, which is determined by the law of distribution of stochastic processes.
 Results. Experimental evaluation of the proposed method and algorithms has shown that they allow us to estimate the trends of these stochastic processes in real time, with high accuracy and while maintaining the service stability.
 Conclusions. The application of the developed method of troubleshooting management in a multiservice environment helps to improve the service stability by timely detecting problems, reducing the time of their elimination and reducing downtime, which, in turn, affects the increase in service reliability.