A Dynamic Traffic Signal Timing Model and Its Algorithm for Junction of Urban Road
As an important part of Intelligent Transportation System, the scientific traffic signal timing of junction can improve the efficiency of urban transport. This paper presents a novel dynamic traffic signal timing model. According to the characteristics of the model, hybrid chaotic quantum evolutionary algorithm is employed to solve it. The proposed model has simple structure, and only requires traffic inflow speed and outflow speed are bounded functions with at most finite number of discontinuity points. The condition is very loose and better meets the requirements of the practical real-time and dynamic signal control of junction. To obtain the optimal solution of the model by hybrid chaotic quantum evolutionary algorithm, the model is converted to an easily solvable form. To simplify calculation, we give the expression of the partial derivative and change rate of the objective function such that the implementation of the algorithm only involves function assignments and arithmetic operations and thus avoids complex operations such as integral and differential. Simulation results show that the algorithm has less remain vehicles than Webster method, higher convergence rate and convergence speed than quantum evolutionary algorithm, genetic algorithms and particle swarm optimization.
KeywordsTraffic signal timing Traffic signal control Evolutionary algorithm Quantum evolutionary algorithm Hybrid chaotic quantum evolutionary algorithm
Unable to display preview. Download preview PDF.
- 1.Webster, F.V., Cobber, B.M.: Traffic Signals. Road Research Technical Paper no. 56, Her Majesty’s Stationery Office, Lodon, U.K. (1966)Google Scholar
- 2.Allsop, R.B.: SIGCAP: a computer program for assessing the traffic capacity of signal-controlled road junctions. Traffic Engineering Control 17(8-9), 338–341 (1976)Google Scholar
- 9.Gu, H.: Wang W, A global optimization simulated annealing algorithm for intersection signal timing. Journal of Southeast University 28(3), 68–72 (1998)Google Scholar
- 10.Wan, W., Chen, F.: Optimal control for isolated intersection signal based on genetic algorithm. Computer Engineering 33(16), 217–219 (2007)Google Scholar
- 11.Gu, R., Cao, L.: Application of immune genetic algorithm optimization in intersection signal timing. Journal of Tongji University (Natural Science Edition) 35(2), 208–212 (2007)Google Scholar
- 12.Zhong, Y., Bao, Z., Chen, Y., Yang, Y.: PSO-based optimization of signal timing and simulation for isolated intersection. Journal of Kunming University of Science and Technology (Science and Technology) 30(1), 82–85 (2005)Google Scholar
- 13.Liu, J.H., Liu, J.W.: A new particle swarm optimization algorithm and real-time control of traffic signal in urban intersection. Systems Engineering 25(7), 83–87 (2007)Google Scholar
- 14.Narayanan, A., Moore, M.: Quantum-inspired genetic algorithms. In: Proc. IEEE Symp. Evolutionary Computation (ICEC 1996), May 1996, pp. 61–66. IEEE Press (1996)Google Scholar
- 15.Cai, Y., Zhang, M., Cai, H.: A hybrid chaotic quantum evolutionary algorithm. In: Proc. 2010 IEEE International Conference on Intelligent Computing and Intelligent Systems (November 2010) (in Press)Google Scholar
- 17.Gao, Y., Lu, K., Shen, Z.: Gradual target elimination quantum genetic algorithm. Signal Processing 25(2), 238–242 (2009)Google Scholar
- 18.Zhang, G., Jin, W., Hu, L.: Quantum evolutionary algorithm for multi-objective optimization problems. In: Proc. IEEE Symp. Intelligent Control (ISIC 2003), October 2003, pp. 703–708. IEEE Press (2003)Google Scholar
- 20.Zhao, Y., Peng, D., Zhang, J., Wu, B.: Quantum evolutionary algorithm for capacitated vehicle routing problem. Systems Engineering-Theory & Practice 29(2), 159–166 (2009)Google Scholar