Research and Development of the Atoll Planning System for Effective Management of Modern Mobile Communication Networks in Ukraine
Students Name: Kholiavka Andrii Stepanovych
Qualification Level: master (ESP)
Speciality: Telecommunications and Radio Engineering
Institute: Institute of Telecommunications, Radioelectronics and Electronic Engineering
Mode of Study: full
Academic Year: 2022-2023 н.р.
Language of Defence: ukrainian
Abstract: In view of the increasing volume of data, technological advancements such as 5G, and the growing demand for quality and reliable communication, it is necessary to develop an intelligent planning system that enables traffic forecasting for resource optimization and improved user service quality. The development of the Atoll planning system using artificial intelligence is a step towards creating future mobile communication that meets the growing societal needs and contributes to the further development of the information environment. The master’s thesis is dedicated to the research and development of the Atoll planning system to enhance the efficiency of managing modern mobile communication networks in Ukraine. Specifically, the focus is on the importance of network monitoring and planning, as well as the use of artificial intelligence for mobile network traffic forecasting. The first chapter of the thesis analyses current trends in mobile communication and discusses important aspects of network development, such as the increasing demand for high-speed communication, increased capacity, and the adoption of new technologies. The characteristics of 4G and 5G technologies are studied in detail, including their efficiency and impact on service quality. The second chapter examines the principles and approaches to planning and optimization of mobile communication networks, particularly using the Atoll system. It is found that Atoll is a powerful tool for designing, testing, and managing mobile communication networks. One of the main advantages of Atoll is its ability to model various scenarios and consider diverse factors that affect the network. This enables engineers to solve complex planning tasks, such as determining optimal base station locations, antenna system configuration, and resource management. Another important feature of Atoll is its flexibility and scalability. It can be used for planning and optimization of networks of any size and technology, including 2G, 3G, 4G, and 5G. Furthermore, Atoll supports various mobile communication standards and protocols, making it a versatile tool for many operators. The third chapter of the thesis explores the importance of effective planning of mobile communication networks to ensure quality user service and optimal resource utilization. In this context, the Atoll software plays a significant role as a powerful tool for planning and optimizing mobile communication networks. The research involves analyzing various aspects of network planning, such as coverage, capacity, optimization, and resource management. The initial stage of the research involves studying the main problems that arise during network operation and presenting key approaches to addressing them through efficient mobile network planning. A detailed analysis of the functional capabilities of Atoll is conducted, including its ability to model coverage, equipment configuration, and network development prediction. The research examines various scenarios of Atoll application, including design, testing, and optimization of mobile communication networks. The possibilities of using Atoll for planning radio relay communication lines and monitoring the performance of transport networks for mobile communication systems are also discussed. In the fourth chapter, the peculiarities of monitoring and analyzing traffic in mobile communication networks in the context of the war in Ukraine were investigated. The war has a significant impact on the country’s communication infrastructure, leading to challenges and problems in the functioning of mobile networks. A Long Short-Term Memory (LSTM) neural network model was proposed for predicting mobile network traffic using real input data. Compared to the well-known LSTM model, the proposed model demonstrates advantages that are confirmed by the experimental results. The average nRMSE value of the proposed model is 5.01% lower, and the time required for traffic forecasting is reduced by 36%. Furthermore, this model allows traffic prediction not only for base stations but also at any point in the network where traffic volume data is available. The use of the proposed LSTM neural network model in the Atoll system brings significant advantages for mobile network operators. It helps to avoid packet loss and decreases in internet connection speed. Integrating this model into the Atoll system enables operators to timely react to traffic growth and upgrade the network before congestion occurs, thereby improving network stability and service quality for mobile users. Future improvements for the proposed model include expanding the types of input data, such as weather conditions, major events, and changes in the country’s situation. This will help enhance the accuracy of traffic forecasting and the efficiency of mobile network management.