A Decision Support System for Proactive-Robust Traffic Network Management

Real-time traffic network management systems are envisioned to provide network operators with decision support capabilities to alleviate recurrent and non-recurrent congestion. These capabilities involve predicting the network congestion dynamics and facilitating the development of proactive traffic management schemes that integrate traffic control and demand management strategies. However, traffic networks are subject to numerous sources of stochasticity that make it difficult to accurately predict their operational conditions and generate effective traffic management schemes to cope with these conditions. This paper presents a decision support system for proactive-robust traffic network management, which accounts for uncertainty in the network operational conditions. The objective is to develop robust traffic management schemes such that the network overall performance remains close to optimality under all possible future operational conditions. The modeling framework of the system is presented, which adopts a rolling horizon framework that integrates a meta-heuristic search algorithm and a dynamic traffic assignment simulation-based methodology. The system performance is examined through application to the traffic network of the US-75 corridor in Dallas, TX, USA.