Mazurenko R. Intelligent traffic control management system of a big city

The dissertation is devoted to solving the important scientific and practical problem of smart traffic management in a big city. The main idea of the work is to create a model of the system, which consists of modules, each of which has several alternative ways of implementation, which gives additional flexibility at the implementation stage. Thus, this work focuses on obtaining practical value from the proposed ideas and takes into account the cost, speed, and ease of implementation in real conditions, which in wartime is especially relevant for the budgets of cities and regions of Ukraine. The proposed approaches make it possible to speed up the learning of the decision-making model, which is controlled by intelligent agents when controlling a complex of traffic lights. Based on the results of the study, the following was developed: – the intelligent model for managing a complex of traffic lights in a big city, which is based on a multi-agent approach of reinforcement learning; – software and technical complex for adaptive control of traffic lights of the city of Kyiv at the street level. Keywords: information system, decision-making model, machine learning, neural network, ontology object, smart city, simulation experiment, traffic flow, traffic management, formalization, artificial intelligence.