With the development of the advanced Intelligent Transportation System (ITS) in modern cities, it is of great significance to upgrade the forecasting methods for travel demand with the impact of ITS. The widespread use of ITS clearly changes the urban travelers’ behavior at present, in which case it is difficult for the conventional four-step travel demand forecasting model to have good performance. In this study, we apply the combined distribution and assignment (CDA) model to forecasting travel demand for modern urban transportation, in which travelers may choose the destination and path simultaneously. Furthermore, we present a new solution algorithm for solving the CDA model. With the network representation method that converts the CDA model into a standard traffic assignment problem (TAP), we develop a new path-based algorithm based on the gradient projection (GP) algorithm to solve the converted CDA model. The new solution algorithm is designed to find a more accurate solution compared with the widely used algorithm, the Evans’ two-stage algorithm. Two road networks, Sioux Falls and Chicago Sketch, are used to verify the performance of the new algorithm. Also, we conduct some experiments on the Sioux Falls network to illustrate several applications of the CDA model in consideration of the influences of ITS.

This paper proposes a path-based algorithm for solving the well-known logit-based stochastic user equilibrium (SUE) problem in transportation planning and management. Based on the gradient projection (GP) method, the new algorithm incorporates a novel multiple-path gradient approach to generate the descent direction in consideration of many paths existing in every single origin-destination (O-D) pair. To apply the path-based algorithm, the SUE problem is reformulated as a variational inequality (VI), and a working path set is predetermined. The numerical experiments are conducted on the Winnipeg network where a large number of paths are provided. The results show the multiple-path gradient projection algorithm outperforms the original GP method. Three different step size strategies, including the fixed step size, self-regulated averaging and self-adaptive Armijo’s strategies, are involved to draw a more general conclusion. Also, the effects of the path number on computational performance are analyzed. The multiple-path gradient projection (MGP) method converges much faster than the GP method when the path set size gets large.