Open AccessDevelopment of a model of a subsystem for forecasting changes in data transmission routes in special purpose mobile radio networks
Author(s) -
Andriy Divitskyi,
Serhii V. Salnyk,
Vladyslav Hol,
Pavlo Sydorkin,
Anton Storchak
Publication year - 2021
Publication title -
eastern-european journal of enterprise technologies
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.268
H-Index - 24
eISSN - 1729-4061
pISSN - 1729-3774
DOI - 10.15587/1729-4061.2021.235609
Subject(s) - computer science , identification (biology) , radio access network , transmission (telecommunications) , computer network , process (computing) , quality (philosophy) , quality of service , extrapolation , real time computing , data mining , base station , distributed computing , telecommunications , mobile station , philosophy , mathematical analysis , botany , mathematics , epistemology , biology , operating system
This research addressed the issue of improving the quality of service for the control system of mobile radio networks. The analysis of the forecasting sphere concerning the methods of service quality of mobile radio networks for special purposes, in particular, forecasting the time of congestion of data transmission routes is carried out. It is found that these methods are used in wired and computer networks operating at the network and data link levels. The basic parameters of the protocols of the channel and network layers of mobile radio networks are highlighted. Forecasting methods are analyzed: temporal extrapolation, causality, expert, and the main disadvantages are indicated. A model of a control system for mobile radio networks with a forecasting subsystem is shown. The features of mobile radio networks, which form the requirements for routing methods, are described. A lot of requirements have been put forward for the model of a control system for mobile radio networks. The structure of a model of a control system for mobile radio networks with an improved forecasting subsystem is proposed. On the basis of genetic algorithms, the tasks that arise in the process of identification, training and forecasting in the forecasting subsystem are solved. The operation of the processes consists in building a base of rules aimed at identifying significant dependencies in a time series based on the use of a genetic algorithm. It is based on the use of evolutionary principles to find the optimal solution. Application of the proposed model will allow real-time identification and will significantly improve the quality of service for mobile radio networks. It will increase the speed and volume of data processed during training, improve the quality and reliability of predicting changes in data transmission routes