Real-Time Traffic Density Estimation Using Various Connected Vehicle Penetration Rates: A New Predictive Approach

Abstract

Traffic density estimation using various Market Penetration Rates (MPRs) of Connected Vehicle (CV) data represents an area in need of continued research and refinement to fully leverage its potential in addressing complex real-world traffic scenarios. This study introduces an innovative approach, the Predictive Approach, employing the Temporal Convolutional Network (TCN) algorithm to estimate traffic density. This method calculates the densities of input approaches at intersections with non-uniform MPRs, using these predictions to estimate the target approach density. Using the Predictive Approach, results showed that improving traffic density predictions can be achieved through factors like accounting for MPR variations between different intersection approaches and considering specific scenarios. Results also highlighted that excluding Signal Phase and Timing (SPaT) data in certain cases can enhance model performance. It offers practical applications in optimizing traffic flow and reducing congestion in smart cities and traffic control centres, particularly when rapid and real-time computations are required. Additionally, it serves as a valuable solution in areas lacking SPaT information and experiencing varying levels of vehicle connectivity, collectively providing versatile tools for efficient traffic management and urban mobility enhancement. These insights have the potential to make real-world traffic management more efficient, responsive, and adaptable, ultimately leading to safer and more effective transportation systems.