Search

An accurate short-term traffic forecasting model serves as an integral part to enhance the efficiency of vehicle rerouting and traffic light control strategies. The information exchange (pheromone) behavior of ants has been applied to forecast traffic conditions in existing pheromone models. These models were developed to forecast congestion on roads with signalized intersections by considering only green and red phases. Motivated by this issue, three short-term traffic forecasting models are proposed: (i) Extended Pheromone Model (EPM), (ii) Extended Pheromone Model with epsilon-Support Vector Regression (ε SVR-EPM), and (iii) Extended Pheromone Model with Artificial Neural Network and Particle Swarm Optimization (ANNPSO-EPM). It is worth noticing that EPM is an algorithmic model whereas the other two are machine learning models. In all proposed models, a new color pheromone concept is proposed with two significant contributions. First, the color pheromone concept is developed to capture stochastic traffic conditions on the roads with non-signalized intersections. Second, the proposed concept is further extended to include all three color phases (red, yellow and green) to forecast dynamic changing traffic behaviors for roads with signalized intersections. The proposed color pheromone concept in EPM, ε SVR-EPM, and ANNPSO-EPM is different from the existing models as it dynamically switches its computation techniques based on traffic light phases. All three proposed models can be realized through a Pheromone-based Multi-Agent System composed of Vehicle Agents and Intersection Agents coordinating locally with one another To promote practicality, Singapore City Hall map is employed in a microscopic simulator of Simulation of Urban Mobility (SUMO), showing that all proposed models outperform the other existing pheromone models. [ABSTRACT FROM AUTHOR]

• A heterogeneous network with signalized and non-signalized intersections is modelled. • A traffic light control problem based on proposed macroscopic model is formulated. • The problem is converted to a mixed integer linear problem for computational benefit. • Simulations are shown to provide guidance for the design of an urban traffic system. In this paper, one type of heterogeneous traffic network, which consists of signalized intersections and non-signalized ones, is analyzed and modelled with a macroscopic model and logic constraints, which involves the evolution of the number of vehicles on each link and the leaving flow dynamics at each intersection. We propose a novel model describing the dynamic behaviors of such a system and the proposed model is validated via road tests in Singapore traffic network and simulations in VISSIM. A piecewise linear model is adopted to describe the traffic flow dynamics at each signalized intersection, while a platooning-like first-in-first-out (FIFO) model is proposed to depict the dynamics at each non-signalized intersection. A traffic light control problem for a heterogeneous traffic network is formulated based on the proposed macroscopic model as a mixed integer programming problem. Simulations indicate that the proposed optimal traffic control scheme could outperform the fixed-time traffic light control strategy and conventional actuated traffic light control scheme. Besides, we demonstrate potentials in developing a systematic planning approach on deciding which traffic intersections require signal control to ensure good traffic control performance. [ABSTRACT FROM AUTHOR]