Capacitated Network Traffic Assignment using Lagrange Neural Networks

Abstract

In this study, we utilize a neural network methodology to obtain user equilibrium for network traffic assignment problems with capacity constraints. The optimization problem associated with network traffic assignment is first transformed into a Lagrange problem. By considering the gradient method, a system of differential equations is obtained. Subsequently, the system of differential equations is solved using the Runge-Kutta method. The effectiveness of the proposed neural network approach is demonstrated through a numerical example.