Ant Colony Optimization for Dynamic Traffic Routing
|Project members:||dr. Z. Cong, MSc (Zhe), prof.dr.ir. B. De Schutter (Bart), prof.dr. R. Babuška (Robert)|
|Keywords:||Optimization-based control, Transportation and infrastructure, Intelligent control|
Ant Colony Optimization (ACO), in Swarm Intelligence methods, refers to an optimization technique of mimicking the intelligent collective behavior of groups of ants that may in themselves have only very limited intellectual capabilities. The class of ACO algorithms has proven to be very powerful optimization heuristic of solving combinatorial optimization problems.
In this project, we investigate the use of the ACO algorithm for dynamic traffic routing problems. Because ants and vehicles are similarly individual moving agents in networks, we use ants to assist to (re)direct traffic at junctions in a traffic network corresponding to the evolving traffic conditions as time progresses. However, the standard ACO algorithm is not capable of solving the routing optimization problem aimed at the system optimum, which is very important in traffic system, and therefore a new ACO algorithm is developed to achieve the goal of finding the optimal traffic assignment in the network.