MODELING THE DYNAMICS OF TRAFFIC FLOWS BASED ON QUEUEING THEORY FOR INTEGRATION INTO INTELLIGENT TRANSPORTATION SYSTEMS

Abstract

The article focuses on the study of traffic flow dynamics modeling in urban environments using queueing theory (QT). The research aims to develop a methodological approach to formalizing dynamic traffic flow processes, enabling their adaptation to modern intelligent transportation systems (ITS). Proposed mathematical models account for the stochastic nature of traffic flows and key performance indicators such as average waiting time, queue length, and throughput. Simulations of various transportation infrastructure scenarios integrating these models into ITS were conducted. The research findings confirm that applying QT under conditions of uneven traffic distribution significantly reduces delays, optimizes routing, and improves the efficiency of road infrastructure utilization. These results pave the way for further enhancements of urban transportation systems by integrating machine learning algorithms and big data analysis, allowing for consideration of the complex behavior of road users. The integration of QT models into ITS contributes to the improved efficiency of transport networks, fostering sustainable development of urban infrastructure. The proposed approaches are universal and can address pressing mobility challenges in contemporary urban agglomerations.