Traffic optimization on Islands

This paper focuses on a parallel Genetic Algorithm approach to solve the coordinated route planning problem in road navigation. The optimization problem is solved locally in each car, local solutions are exchanged when communication opportunities arise. Such Island Genetic Algorithms with local sub-populations are known to yield good results in many domains. Here, we leverage their power for road traffic, where limited knowledge and limited communication abilities make a distributed solution particularly desirable. To this end, we specifically tackle the question how to represent the optimization problem and solution instances, and how to exchange them between cars.