Generating More Equitable Traffic Signal Timing Plans

Signal timing plans designed under a total delay minimization strategy can induce excessively high delays for low-volume movements and result in an uneven distribution of delay among motorists. A multiobjective optimization approach is considered for the minimization of both overall delay and delay imbalance. The multiobjective method is found to be highly successful. Compared with a pure delay minimization strategy, the multiobjective optimizer is able to produce signal timing plans with similar overall delay that have a considerably more equitable delay distribution. Multi-objective optimization provides the traffic engineer with a choice from an entire range of compromise solutions in the two competing objectives. Large reductions in the delay imbalance can be achieved at the cost of small sacrifices in overall delay. Multiphase signal control, shifting green splits in favor of low-volume movements, and decreasing bandwidth provide more-balanced delays at the cost of increasing overall delay.

[1]  L. Darrell Whitley,et al.  Searching in the Presence of Noise , 1996, PPSN.

[2]  Joyoung Lee,et al.  Application of the Stochastic Optimization Method in Optimizing Traffic Signal Control Settings , 2008 .

[3]  Peter T. Martin,et al.  VisSim-Based Genetic Algorithm Optimization of Signal Timings , 2007 .

[4]  Nathan H. Gartner,et al.  MULTIBAND-96: A Program for Variable-Bandwidth Progression Optimization of Multiarterial Traffic Networks , 1996 .

[5]  Khewal Bhupendra Kesur Advances in Genetic Algorithm Optimization of Traffic Signals , 2009 .

[6]  F A Wagner,et al.  IMPROVED CRITERIA FOR TRAFFIC SIGNALS AT INDIVIDUAL INTERSECTIONS , 1964 .

[7]  J. Fitzpatrick,et al.  Genetic Algorithms in Noisy Environments , 2005, Machine Learning.

[8]  Larry J. Eshelman,et al.  The CHC Adaptive Search Algorithm: How to Have Safe Search When Engaging in Nontraditional Genetic Recombination , 1990, FOGA.

[9]  Kenneth G Courage,et al.  ARTERIAL PROGRESSION--NEW DESIGN APPROACH , 1982 .

[10]  Emilia Rahnemay Kohlman Rabbani,et al.  Marginal Delay: New Measure for Quality of Service at Signalized Intersections , 2002 .

[11]  Xiao Kuan Yang,et al.  Comparison among computer packages in providing timing plans for Iowa arterial in Lawrence, Kansas , 2001 .

[12]  G. F. Newell,et al.  Traffic Signal Synchronization on a One-Way Street , 1967, Transp. Sci..

[13]  Kalyanmoy Deb,et al.  A fast and elitist multiobjective genetic algorithm: NSGA-II , 2002, IEEE Trans. Evol. Comput..

[14]  R. K. Ursem Multi-objective Optimization using Evolutionary Algorithms , 2009 .

[15]  John J. Grefenstette,et al.  Genetic Search with Approximate Function Evaluation , 1985, ICGA.

[16]  Thomas Urbanik,et al.  Enhanced Genetic Algorithm for Signal-Timing Optimization of Oversaturated Intersections , 2000 .

[17]  Volker Nissen,et al.  On the robustness of population-based versus point-based optimization in the presence of noise , 1998, IEEE Trans. Evol. Comput..

[18]  Benjamin W. Wah,et al.  Scheduling of Genetic Algorithms in a Noisy Environment , 1994, Evolutionary Computation.

[19]  Ahmed Al-Kaisy,et al.  Freeway Quality of Service: What Really Matters to Drivers and Passengers? , 2001 .