01154610

Component

This article proposes to solve the oversaturated network traffic signal coordination problem using the Ant Colony Optimization (ACO) algorithm. The traffic network used is a discrete time model which uses the green times at all the intersections throughout the period of oversaturation as the decision variables. The Ant Colony Optimization algorithm takes the green times as variables and generates an intelligent timing plan which takes care of dissipation of queues and removal of blockages as opposed to just the minimization of cost in the case of undersaturation. The network is then solved for different cases of ACO using different number of ants and trials. The results are then compared with Simple Genetic Algorithms (SGA) for similar cases and statistical analysis is done to determine the better algorithm. Further, a master-slave parallelism is suggested for ACO to reduce the execution time allowing the opportunity to implement the algorithm on real-time signal control systems.

01147878

10-2669

English

18p

2010

Transportation Research Board 89th Annual Meeting

DVD

Figures (4) ; References (19) ; Tables (1)

Algorithms; Genetic algorithms; Green interval (Traffic signal cycle); Optimization; Traffic oversaturation; Traffic signal controllers; Traffic signal timing

Ant colony optimization

Data and Information Technology; Highways

Transportation Research Board Annual Meeting 2010 Paper #10-2669

BTRIS, TRIS, TRB

Jan 25 2010 11:17AM