Getting you faster to work: a genetic algorithm approach to the traffic assignment problem

Traffic assignment is a complex optimization problem. In case the road network has many links (thus a high number of alternative routes) and multiple origin-destination pairs, most existing solutions approximate the so-called user equilibrium (a variant of Nash equilibrium). Furthermore, the quality of these solutions (mostly, iterative algorithms) come at the expense of computational performance. In this study, we introduce a methodology to evaluate an approximation of an optimal traffic assignment from the global network's perspective based on genetic algorithms. This approach has been investigated in terms of both network performance (travel time) and convergence speed.