A Multi-Objective Optimization Method for Coordinated Control

Abstract:

In this paper, to overcome the limitations of the weighted combination and single objective optimization methods, we presented a multi-objective optimization and simulation methodology for network-wide traffic signal control. A multi-objective genetic algorithm based on Non-dominated Sorting Genetic Algorithm II was given to solve the model directly to obtain Pareto optimal solution set. The objectives were evaluated by Enhanced Cell Transmission Model used to describe traffic dynamics on signalized urban road network. The results showed that the single objective optimization method made some of the objectives worsen when the objective to be optimized reaching optimal, and that the weighted combination optimization method gained a compromised solution, but the multi-objective optimization method gave consideration to more objectives, making the number of optimal or suboptimal ones is more than that of worse ones.

• Periodical: Applied Mechanics and Materials (Volumes 97-98)
• Pages: 942-946
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.97-98.942
• Online since: September 2011
• Authors: Yun Feng Gao, Hua Hu, Tao Wang, Xiao Guang Yang
• Keywords: Coordinated Control, CTM, Multi-Objective Optimization (MOP), NSGA-II, Pareto Optimal Solution, Simulation, Traffic Control

References

[1] Robertson D. I..TRANSYT: a traffic network study tool[R]. TRL Report LR 253, Road Research Laboratory, Crowthorne. 1969.

[2] S.C. Wong, W.T. Wong, C.M. Leung, C.O. Tong. Group-based optimization of a time-dependent TRANSYT traffic model for area traffic control[J]. Transportation Research Part B, 2002, 36: 291-312.

DOI: 10.1016/s0191-2615(01)00004-2

[3] Jian Chang, Dawei Wu. Multi-objective intersection signal control model[J]. Journal of Dalian University of Technology, 2000, 40(6): 653-656.(In Chinese)

[4] Chengtao Cao, JianminXu. Multi-object traffic signal control method for single intersection[J]. Computer Engineering and Applications, 2010, 46(16): 20-22.(In Chinese)

[5] JianqinZeng, Jiajie Wang, Kun Liu, et. al.. CTM-MOGA Based Crossroad Traffic Signal Control[J]. Journal of university of science and technology of china, 2005, 35(2): 284-290.

[6] Xinsheng Yao, Xia Luo, Jinyou Du. Traffic Signal Control Based on Satisfactory Multi-Optimization[J]. Computer Engineering and Applications, 2006, 35: 9-10+36.(In Chinese)

[7] Yingying Ma, Xiaoguang Yang, YinZeng. Multi-objective Cycle Length Optimization Model and Solution[J]. Journal of Tongji University(Natural Science), 2009, 37(6): 761-765.(In Chinese)

[8] Hua Hu, YunfengGao, XiaoguangYang. Multi-objective Optimization Method of Fixed-time Signal Control of Isolated Intersections[C]. The 2010 IEEE International Symposium on Computational and Information Sciences, 2010: 1281-1284.

DOI: 10.1109/iccis.2010.316

[9] Schmöcker J. D., Ahuja S., Bell M. G.H. Multi-objective signal control of urban junctions – Framework and a London case study[J]. Transportation Research Part C, 2008, 16: 454-470.

DOI: 10.1016/j.trc.2007.09.004

[10] Deb K., Pratap A., Agarwal S., MeyarivanT..A Fast and Elitist Multiobjective Genetic Algorithm: NSGA-II[C]. IEEE Transactions on Evolutionary Computation, 2002, 6(2): 182-197.

DOI: 10.1109/4235.996017

[11] Daganzo C. F..The cell transmission model, Part II: network traffic[J]. Transportation Research part B, 1995, 29(2): 79-93.

DOI: 10.1016/0191-2615(94)00022-r

[12] Flötteröd G., Nagel K..Some practical extensions to the Cell Transmission Model[C]. Proceedings of the 8th International IEEE Conference on Intelligent Transportation Systems, Vienna, Austria, 2005: 172-177.

DOI: 10.1109/itsc.2005.1520042

[13] LI Z. C., CHANG G. L..Modeling arterial signal optimization with enhanced cell transmission formulations[CD]. The 89th Transportation Research Board Annual Meeting, Washington, USA, 2010, #10-2330.