Abakumova A. Methods of monitoring and improving the quality of cellular communication network services

Sustainable and balanced development of the communication industry is inextricably linked with an increase in the number of subscribers and services provided. In order to maintain competitiveness, the main efforts of operators are aimed at improving the quality and increasing the service life of subscribers in the network. These circumstances determine the relevance of the study tasks related to the assessment and management of the quality of cellular services, and the development of approaches to their solution. The paper analyzes modern cellular systems in terms of service quality. The shortcomings of modern cellular systems contributed to the analysis of next generation (5G) and the formation of basic requirements. All of the above defined the direction of research - ensuring the quality of services provided by cellular operators through the establishment of relationships between key parameters of the quality of perception and quality of service to mobile network subscribers in real time using machine learning. The key performance indicators (KPI) and quality (KQI) of the cellular network are considered and the hierarchy of their interaction is established. The main uses of the 5G standard have been identified. In view of this, the paper defines the classification of cases of 5G use in relation to KPI. To achieve the task of improving the quality of service provision, a functional relationship between network parameters has been established, i.e. the impact of key performance indicators on a key quality indicator through the use of cubic Hermitian splines (CHS) has been determined. Due to the application of the first developed method of determining the functional relationship between KPI and KQI parameters based on the use of cubic Hermitian splines, it becomes possible to assess the degree of influence of each KPI parameter on the KQI parameter with future average data forecast, which will lead to the implementation of the certain KPI parameter choice for its further improvement or optimization, in order to improve the quality of service provision by the cellular operator. The main technology of artificial intelligence - machine learning – is considered in terms of application in the field of telecommunications. Machine learning is a necessary solution for cellular operators to improve the quality of service and the cellular network as a whole The method of service quality management through machine learning has been improved, which is an effective tool for modeling integrated indicators of communication services quality control, monitoring their condition in terms of final copies of services, finding the causes of degradation and reporting. For the first time, a method has been developed to assess and optimize the network state to improve the quality of service provision to users by cellular operators using the method of services quality management based on the principles of machine learning. A prototype of a 24-hour Chatbot for customer service has been developed, which generates a statement based on the receipt of a request from the subscriber with its subsequent analysis by a system using machine learning. An experimental study and computer modeling of the monitoring and optimization system of the cellular network in the software environment Atoll were conducted on the example of one of the complaints that were recorded by Chatbot, with the calculation of coverage maps, analysis of key quality indicators and optimization of load distribution, in order to present the effectiveness of the proposed methods and models to improve the customer service quality.