Multi-intersection traffic light control using infinitesimal perturbation analysis

Abstract We address the traffic light control problem for multiple intersections in tandem by viewing it as a stochastic hybrid system and developing a Stochastic Flow Model (SFM) for it. Using Infinitesimal Perturbation Analysis (IPA), we derive on-line gradient estimates of a cost metric with respect to the controllable green and red cycle lengths. The IPA estimators obtained require counting traffic light switchings and estimating car flow rates only when specific events occur. The estimators are used to iteratively adjust light cycle lengths to improve performance and, in conjunction with a standard gradient-based algorithm, to obtain optimal values which adapt to changing traffic conditions. Simulation results are included to illustrate the approach.

[1]  Daniel Vanderpooten,et al.  Multiobjective and multimodal adaptive traffic light control on single junctions , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[2]  Wilfred W. Recker,et al.  Stochastic adaptive control model for traffic signal systems , 2006 .

[3]  Michael C. Fu,et al.  ONLINE TRAFFIC LIGHT CONTROL THROUGH GRADIENT ESTIMATION USING STOCHASTIC FLUID MODELS , 2005 .

[4]  Christos G. Cassandras,et al.  Perturbation analysis for online control and optimization of stochastic fluid models , 2002, IEEE Trans. Autom. Control..

[5]  Henk Taale.  OPTIMIZING TRAFFIC LIGHT CONTROLLERS BY MEANS OF EVOLUTIONARY ALGORITHMS , 1998 .

[6]  C. Cassandras,et al.  Stochastic hybrid systems , 2006 .

[7]  Sung-Joo Lee,et al.  A Traffic Light Controlling FLC Considering the Traffic Congestion , 2002, AFSS.

[8]  Marco Wiering,et al.  Intelligent Trac Light Control , 2004 .

[9]  B. De Schutter.  Optimal traffic light control for a single intersection , 1999 .

[10]  Yorai Wardi,et al.  A Unified Approach to Infinitesimal Perturbation Analysis in Stochastic Flow Models: The Single-Stage Case , 2010, IEEE Transactions on Automatic Control.

[11]  Christos G. Cassandras,et al.  Introduction to Discrete Event Systems , 1999, The Kluwer International Series on Discrete Event Dynamic Systems.

[12]  Shalabh Bhatnagar,et al.  Reinforcement learning with average cost for adaptive control of traffic lights at intersections , 2011, 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[13]  Nicholas V. Findler,et al.  Distributed Approach to Optimized Control of Street Traffic Signals , 1992 .

[14]  Christos G. Cassandras,et al.  Perturbation analysis of stochastic hybrid systems and applications to resource contention games , 2011 .

[15]  Arne Koopman,et al.  Intelligent Traffic Light Control , 2004 .

[16]  Yetis Sazi Murat,et al.  A FUZZY LOGIC MULTI-PHASED SIGNAL CONTROL MODEL FOR ISOLATED JUNCTIONS , 2005 .

[17]  Christos G. Cassandras,et al.  Resource contention games in multiclass stochastic flow models , 2011 .

[18]  I Alvarez,et al.  Game theory applied to urban traffic control problem , 2010, ICCAS 2010.

[19]  Yangzhou Chen,et al.  Traffic light control method for a single intersection based on hybrid systems , 2003, Proceedings of the 2003 IEEE International Conference on Intelligent Transportation Systems.

[20]  Christos G. Cassandras,et al.  Traffic light control using Infinitesimal Perturbation Analysis , 2012, 2012 IEEE 51st IEEE Conference on Decision and Control (CDC).

[21]  Thomas L. Thorpe.  Vehicle Traffic Light Control Using SARSA , 1997 .

[22]  Christos G. Cassandras,et al.  Perturbation Analysis and Optimization of Stochastic Hybrid Systems , 2010, Eur. J. Control.