Method of improving the efficiency of distributed data processing In computer systems of cellular operators

The creation of information society in Ukraine is one of the most urgent tasks today. In the Strategy for the Development of the Information Society in Ukraine, the priorities for the formation of the country's modern information infrastructure include the creation of high-speed mobile broadband access networks to Internet resources throughout Ukraine. At the same time, with the development of cellular networks, new and more advanced network architectures for data transmission and management appear. However, there are still a number of unresolved issues and problem areas that need to be addressed accordingly. Therefore, the creation of high-speed networks of the fourth and fifth generations of broadband access to Internet resources and increase of the efficiency of their operation is an urgent and promising task. The purpose of the study is to develop methods to improve the efficiency of distributed data processing in computer systems of cellular operators. Achieving the goal is aimed at improving the quality of customer service of modern cellular networks and meeting the requirements for next generation networks. The paper analyzes the effectiveness of methods, models and technologies of distributed data processing in computer systems of cellular operators and identifies their shortcomings. After that, a method has been developed to optimize the placement of scalable services on the distributed computing resources of the cellular network, which consists in the sequential use of the boundary computing model, a generalized cellular network model and a heuristic solution based on genetic algorithms. The method obtained as a result of this work allows to reduce the level of degradation of the quality of service of end subscribers of the cellular operator's network, in particular, delays of up to 8 ms for a large number of subscribers and, accordingly, a large number of tasks

cellular communication; data transmission; distributed computing; network channels; genetic algorithm