Optimal control of signalized intersection using hierarchical fuzzy-real control
Download 1.25 Mb. Pdf ko'rish
|
7. Conclusions and suggestions
In controlling traffic, several traffic flows compete with each other over time and space, but there are often different criteria for traffic flows. Generally, the criterion of delay is the determinant 20 factor in the efficiency of traffic control systems. In this paper, Abshar intersection in Isfahan city was used as the experimental sample. The data membership functions were specified, the rule base was established using SIFRC, and then by presenting a new fuzzy- real strategy to determine the optimal phase time, the performance of the intersection was evaluated. The results indicated the better performance of this method by up to 49% compared to fixed time and 7% relative to pre-timed and fuzzy methods. Since in this paper the performance of the intersection was investigated independently of the network, the number of possible states was limited. Nevertheless, in order to match this intersection with its surrounding intersections, a large number of states should be investigated in order to determine the optimal offset time alongside the optimal phase. In this regard, a possible solution is limiting the number of states in a regulatory way or using optimization algorithms. Therefore, a subject that can be proposed for future research is stating an optimal method to match intersections with each other with the aim of minimizing the delay. Therefore, future research should design a method which can combine the fuzzy- real methods implemented in each intersection with each other using smart algorithms. 21 [1] P. Cramton, R. R. Geddes, and A. Ockenfels, “Set road charges in real time to ease traffic,” Nature, vol. 560, no. 7716, p. 23, Aug. 2018. [2] “Vehicles, Air Pollution, and Human Health,” Union of Concerned Scientists. [Online]. Available: https://www.ucsusa.org/clean-vehicles/vehicles-air-pollution-and-human-health. [Accessed: 05- Aug-2018]. [3] INRIX, “INRIX Global Traffic Scorecard,” INRIX - INRIX. [Online]. Available: http://inrix.com/scorecard/. [Accessed: 05-Aug-2018]. [4] “The hidden cost of congestion,” The Economist, 28-Feb-2018. [5] R. P. Roess, E. S. Prassas, and W. R. McShane, Traffic Engineering, 4 edition. Upper Saddle River, NJ: Prentice Hall, 2010. [6] D. Zhao, Y. Dai, and Z. Zhang, “Computational Intelligence in Urban Traffic Signal Control: A Survey,” IEEE Trans. Syst. Man Cybern. Part C Appl. Rev., vol. 42, no. 4, pp. 485–494, Jul. 2012. [7] S. Touhbi et al., “Adaptive Traffic Signal Control : Exploring Reward Definition For Reinforcement Learning,” Procedia Comput. Sci., vol. 109, pp. 513–520, Jan. 2017. [8] F. V. Webster, Road Research Laboratory, Great Britain, and Department of Scientific and Industrial Research, Traffic signal settings. Middlesex [England]; London, England: Road Research Laboratory, Dept. of Scientific and Industrial Research ; H.M.S.O., 1961. [9] A. J. Miller, “Settings for fixed cycle traffic signals,” presented at the Australian Road Research Board (ARRB) Conference, 2nd, 1964, Melbourne, 1964, vol. 2, pp. 373–386. [10] M. B. Trabia, M. S. Kaseko, and M. Ande, “A two-stage fuzzy logic controller for traffic signals,” Transp. Res. Part C Emerg. Technol., vol. 7, no. 6, pp. 353–367, Dec. 1999. [11] E. Bingham, “Reinforcement learning in neurofuzzy traffic signal control,” Eur. J. Oper. Res., vol. 131, no. 2, pp. 232–241, Jun. 2001. [12] M. Wiering, Multi-agent reinforcement learning for traffic light control. 2000. [13] M. Wiering, J. Vreeken, J. van Veenen, and A. Koopman, “Simulation and optimization of traffic in a city,” in 2004 IEEE Intelligent Vehicles Symposium, 2004, pp. 453–458. [14] A. L. C. Bazzan, “A Distributed Approach for Coordination of Traffic Signal Agents,” Auton. Agents Download 1.25 Mb. Do'stlaringiz bilan baham: |
Ma'lumotlar bazasi mualliflik huquqi bilan himoyalangan ©fayllar.org 2024
ma'muriyatiga murojaat qiling
ma'muriyatiga murojaat qiling