SVM based intelligent traffic control and simulation for urban expressway and periphery freeway

Abstract

Urban periphery road network is a special type of roadwork pattern that scatters and distributes around the specific zone of metropolitan and in that contains different grade and functional roads of arterial road, urban freeway and expressway. Urban traffic flow and inter-cities flow transform and divert intensively and massively in this zone, also bring traffic jams and incidents frequently. Traffic control is necessary. Coordinated traffic control is a new development where the control problem is to find the combination of control measures that result in the best road performance. The problems of multi-objective coordinated metering and evaluation for local ramp is considered. This paper discusses the optimal coordination of mainline and ramp, a modified ramp latency model is posed using the method of queuing theory, and a ramp control with better mechanism compare to artifical neural network using radical based function-support vector machine algorithm is designed. With in-situ traffic flow data of high-density period, three known and the novel methodologies are compared, and the preliminary simulation-based investigation of the local ramp coordinated metering for urban expressway and related periphery freeway using these methodologies demonstrates the comparative control efficiency and accuracy, especially in the improvement of certain objective.