Optimal Scheduling of Road Maintenance Jobs Considering Impact on Traffic Flows
2026-08-14 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors looked at how to plan road maintenance by predicting traffic patterns when roads have less capacity. Normally, figuring out traffic flow after changes takes a lot of computer time because each scenario needs a complex calculation. To speed this up, they trained a simpler model that learns from detailed traffic simulations to guess traffic flows quickly. They tested this method using real traffic data from Newark, New Jersey, and found it works well as a starting point for making maintenance schedules more efficient.
network-level maintenance planningequilibrium traffic assignmenttraffic floworigin-destination demandsurrogate modelsoptimizationroad capacity reductiontraffic simulationdata-driven modelingcase study
Authors
Charitha Nandepu, Lohitha Kalepu, Gabriele Ciavarella, SangWoo Park
Abstract
Network-level maintenance planning requires repeated evaluations of equilibrium traffic flows under road capacity reductions. While equilibrium traffic assignment models are well established, their repeated solution quickly becomes computationally prohibitive and challenging to embed within maintenance scheduling problems. This paper investigates data-driven surrogate models that approximate equilibrium arc flows directly from origin-destination demand, using optimization-based equilibrium solutions as ground truth. A real-world case study based on traffic data from the Newark, New Jersey area demonstrates the effectiveness of the proposed approach as a scalable building block for future maintenance scheduling frameworks.