This paper describes how decision support for real-time traffic management is a critical component for the success of Intelligent Transportation Systems (ITS). From a theoretical standpoint, microscopic simulation models can potentially be used to evaluate different traffic management strategies in real-time before recommending a course of action. The problem, however, lies in the fact that the strategies would have to be evaluated in real-time, and for large-scale networks and complex simulation models, this might not be feasible from a computational standpoint. To address this, the current study presents two Artificial Intelligence (AI) paradigms, Support Vector Regression (SVR) and Case-Based Reasoning (CBR), as alternatives to using the simulation models as a decision support tool. Specifically, prototype SVR and CBR decision support tools are developed and used to evaluate the likely impacts of implementing diversion strategies in response to incidents on a highway network in Anderson, South Carolina. The authors then evaluated the performance of the two prototypes by comparing their predictions of traffic conditions with those obtained from VISSIM, a microscopic simulation model. While the prototype systems' predictions were found to be comparable to those obtained from simulation, their runtime was only a fraction of the time required by the simulation model. Moreover, the performance of SVR is shown to be superior to that of CBR for most of the cases considered. The results of the study provide motivation for considering the proposed AI paradigms as potential decision support tools for real-time transportation management applications.
Abstract