A SEMI-DYNAMIC TRAFFIC ASSIGNMENT MODEL CASE STUDY: KANAZAWA CITY

In most cities, because daily traffic conditions significantly vary, a static traffic assignment model may not sufficiently represent time-varying congestion phenomena in transportation network analysis. On the other hand, a dynamic traffic assignment model requires heavy computational load and does not have a unique solution in most models. Therefore, a semi-dynamic traffic assignment model is an alternative for describing daily traffic dynamics of large-scale networks. This approach formulates static network equilibrium in each period and also considers flow propagation. Flow propagation describes the flow on a link that is unable to exit in a given period and is propagated to the next period. We calculated flow propagation through sensitivity analysis to reduce the computational expenses on the basis of a four-step method. Moreover, we applied the model to the Kanazawa City urban network in order to demonstrate that the semi-dynamic traffic assignment model can be applied to large-scale networks.