Urban Traffic Flow Simulation Using Cellular Automata in Smart City Transportation Networks

Modeling traffic flow in cities is an important part of making transportation networks perform better in smart cities. It means figuring out how traffic will flow, when it will get stuck, and how cars will move to make things safer and more efficient overall. This paper suggests a new way to simulate traffic flow in cities by employing Cellular Automata (CA) in the context of smart city transportation networks. Traffic simulation models that are already out there typically have trouble adequately showing how complicated real-time urban traffic behavior is. Current methodologies might not be able to account for changes in traffic flow, the integration of different modes of transportation, or the effects of new technologies like the Internet of Things (IoT) and self-driving cars. These problems make it harder to manage traffic jams and determine the best routes in cities. This research presents a 2D Cellular Automata Model (2D-CAM) that is meant to better mimic traffic jams at smart city crossings to overcome these problems. In a grid-based system, the model looks at how vehicles interact with each other, the road infrastructure, and traffic signals. By breaking up the city's traffic system into smaller parts, 2D-CAM can simulate traffic flows in real time, which makes it easier to manage congestion in a more flexible and responsive way. Specifically, it achieves traffic density values as low as 170 vehicles/km<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> under high traffic conditions, compared to higher densities observed in other methods. It minimizes average travel time to 33 minutes, demonstrating significant efficiency over traditional models. 2D-CAM maintains a high traffic flow of 560 vehicles/hour, even with increasing vehicle numbers. Furthermore, it reduces congestion levels to 78%. The results show that traffic flow has gotten a lot better, with less congestion and better route planning.

Hali tarjima qilinmagan