Stochastic Vs Deterministic Traffic Simulator. Comparative Study for Its Use Within a Traffic Light Cycles Optimization Architecture

Last year we presented at the CEC2004 conference a novel architecture for traffic light cycles optimization. The heart of this architecture is a Traffic Simulator used as the evaluation tool (fitness function) within the Genetic Algorithm. Initially we allowed the simulator to have a random behavior. Although the results from this sort of simulation were consistent, it was necessary to run a huge amount of simulations before we could get a significant value for the fitness of each individual of the population . So we assumed some simplifications to be able to use a deterministic simulator instead of the stochastic one. In this paper we will confirm that it was the right decision; we will show that there is a strong linear correlation between the results of both simulators. Hence we show that the fitness ranking obtained by the deterministic simulator is as good as the obtained with the stochastic one.

[1]  Nagui M Rouphail,et al.  Direct Signal Timing Optimization: Strategy Development and Results , 2000 .

[2]  D. Giglio,et al.  On applying Petri nets to determine optimal offsets for coordinated traffic light timings , 2002, Proceedings. The IEEE 5th International Conference on Intelligent Transportation Systems.

[3]  D. Chowdhury,et al.  A new cellular automata model for city traffic , 2000 .

[4]  Wann-Ming Wey,et al.  Applications of linear systems controller to a cycle-based traffic signal control , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[5]  Middleton,et al.  Self-organization and a dynamical transition in traffic-flow models. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[6]  J. Neumann,et al.  John von Neumann collected works , 1961 .

[7]  James C. Spall,et al.  A model-free approach to optimal signal light timing for system-wide traffic control , 1994, Proceedings of 1994 33rd IEEE Conference on Decision and Control.

[8]  C. Daganzo.  Requiem for second-order fluid approximations of traffic flow , 1995 .

[9]  Michael Schreckenberg,et al.  A cellular automaton model for freeway traffic , 1992 .

[10]  Javier J. Sánchez Medina,et al.  Genetic algorithms and cellular automata: a new architecture for traffic light cycles optimization , 2004, Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753).

[11]  P. Wagner,et al.  Metastable states in a microscopic model of traffic flow , 1997 .

[12]  You Sik Hong,et al.  Estimation of optimal green time simulation using fuzzy neural network , 1999, FUZZ-IEEE'99. 1999 IEEE International Fuzzy Systems. Conference Proceedings (Cat. No.99CH36315).

[13]  A Schadschneider,et al.  Optimizing traffic lights in a cellular automaton model for city traffic. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[14]  YouSik Hong,et al.  The optimization of traffic signal light using artificial intelligence , 2001, 10th IEEE International Conference on Fuzzy Systems. (Cat. No.01CH37297).