Kai Nagel, Martin Pieck, Marcus Rickert, Patrice Simon

Paper #: 00-02-012

Iterating between a router and a traffic micro-simulation is an increasibly accepted method for doing traffic assignment. This paper, after pointing out that the analytical theory of simulation-based assignment to date is insufficient for some practical cases, presents results of simulation studies from a real-world study. Specifically, we look into the issues of uniqueness, variability, and robustness and validation. Regarding uniqueness, despite some cautionary notes from a theoretical point of view, we find no indication of “meta-stable” states for the iterations. Variability however is considerable. By variability we mean the variation of the simulation of a given plan set by just changing the random seed. We show then results from three different micro-simulations under the same iteration scenario in order to test for the robustness of the results under different implementations. We find the results encouraging, also when comparing to reality and with a traditional assignment result.