Resilience-Based Recovery Scheduling of Transportation Network Considering Connected and Autonomous Vehicles

Enhancing the resilience of transportation networks (TNs) relies on effective post-hazard recovery strategies. However, little attention has been paid to the heterogeneous users’ travel behavior in system functionality quantification and the extensive computational burden in metaheuristic solution procedures. A bi-level decision framework is proposed for the resilience-based recovery scheduling of the TN considering the presence of both connected and autonomous vehicles (CAVs) and human-driven vehicles (HDVs). The lower level quantifies the TN’s functionality over time considering different travel behavior of CAV and HDV users. The upper level proposes a novel machine-learning-based optimization approach to solve large-scale network restoration problem. This framework can help better quantify the TN’s functionality and support effective and efficient recovery scheduling of large-scale TN in different mixed traffic scenarios. A real-world traffic network in Southern California is provided to demonstrate the proposed framework.