A Network GEV model for route choice allowing implicit route enumeration

This article introduces an adaptation of the Network GEV model for modelling joint choices, named Joint Network GEV (JNG), and its application to the route choice context, named Link-Based JNG (LBJNG), assuming the choice of a route as the joint choice of all links belonging to that route. The LB-JNG model aims at reproducing the effects of routes overlapping with a theoretical robust framework (since it belongs to the Network GEV, to date the most flexible closedform model in reproducing covariances), allowing at the same time for easy application to real networks through a closed-form probability statement, a proper definition of its parameters and the availability of an implicit route enumeration algorithm for network loading. The article carries out first an overview of the theoretical properties of the JNG model. Then, the LB-JNG adaptation to route choice is described, and its capability to reproduce the effects of routes overlapping is investigated using some test networks, wherein the performances of the proposed model are also compared with those of other route choice models available in the literature. Finally, an implicit route enumeration algorithm for macroscopic static stochastic network loading, based on a double-step generalization of Dial’s STOCH algorithm, is proposed and tested on real size networks.