An urban traffic simulation system based on multi-agent modeling

The compute simulation technology plays a key role in developing Intelligent Transportation System (ITS). The agent-oriented technology provides the advantage in modeling the system and reflecting the ITS components' interactive and self-managing behavior than the conventional simulation technologies. In this paper, a multi-agent traffic simulation system is presented and implemented in NetLogo platform. In this system, the urban traffic components including the vehicles, road sections, intersections are abstracted to agent models. Each agent has the basic abilities of obtaining knowledge, autonomy, interaction and communication. In the road agent model, the traffic flow forecasting ability is integrated to induce vehicle agents' action and help intersection agent control the traffic signal. Each intersection agent is the abstracted model of the signal controller and the traffic situation of intersection. In each intersection agent model, the signal control function is implemented by analyzing the real-time and predicted traffic flow information from the interaction with related road agents. Simulation result shows that the proposed multi-agent traffic system performs well in reflecting the evolution of dynamic traffic system's behavior. Besides, it shows the advantage in reducing the vehicles' delay time of the road network by the interaction-based signal control function of the intersection agent.

[1]  Meng Ying,et al.  Research of Urban Traffic Flow Forecasting Based on Neural Network , 2009 .

[2]  Corrado Santoro,et al.  The impact of real time information on transport network routing through intelligent agent-based simulation , 2009, 2009 IEEE Toronto International Conference Science and Technology for Humanity (TIC-STH).

[3]  Yongqiang Zhang,et al.  An improved map matching algorithm for intelligent transportation system , 2008, 2008 IEEE International Conference on Industrial Technology.

[4]  B. Basu,et al.  Bayesian Time-Series Model for Short-Term Traffic Flow Forecasting , 2007 .

[5]  Alois Ferscha,et al.  Effect of Proactive Braking on Traffic Flow and Road Throughput , 2009, 2009 13th IEEE/ACM International Symposium on Distributed Simulation and Real Time Applications.

[6]  Masami Goto,et al.  Intra- and Inter-Vehicle Communication Network Using Low-Cost POF Links , 2002 .

[7]  Changshui Zhang,et al.  Short-term traffic flow forecasting based on Markov chain model , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[8]  Yuan Yuan Zhang,et al.  Traffic Flow Forecasting Based on Chaos Neural Network , 2010 .

[9]  M.J. Mahjoob,et al.  Traffic simulation of an urban network system using agent-based modeling , 2011, 2011 IEEE Colloquium on Humanities, Science and Engineering.