The method of assessing and improving the user experience of subscribers in software-configured networks based on the use of machine learning

Abstract

Evolutionary processes, which primarily affected computer technologies, led to the appearance of several types of computer networks, representing a set of computer devices combined into one system. The main purpose of such a system is user access to shared resources and the ability to exchange data between subscribers during work. Such networks are called software-configurable networks - SDN. SDN networks have long been the basis for building carrier-class telecommunication networks. However, they have a certain number of shortcomings that must be eliminated. The object of the study is the process of evaluating and improving the user experience of subscribers in software-configured networks. The subject of the study is a method of evaluating and improving the user experience of subscribers in software-configured networks based on the use of machine learning. The purpose of the work is to develop a model and a corresponding method for assessing the quality of the user experience of subscribers of SDN networks. As a result of the research, for the first time, a method of evaluating and improving the user experience of subscribers of SDN networks was developed based on the use of machine learning. The method consists in sequentially conducting an automated survey of users, measuring indicators of subscriber service quality, selecting and building a regression model from a set of defined models, and managing the user experience according to the measured parameters of SDN subscriber service quality. The developed method, in contrast to the known ones, makes it possible to improve the quality of the user experience in real time. Conclusions. The research of existing mechanisms for managing the user experience of subscribers and the analysis of regression models for the possibility of using them to establish the relationship between network parameters and user experience allowed to develop a generalized model for evaluating and improving the user experience of subscribers of SDN networks, based on the use of machine learning, and to develop an algorithm works of the method. The developed method makes it possible to build accurate models of the relationship of QoE and QoS parameters and increases the quality of the user experience of subscribers of SDN networks by up to 10%.