Surrogate-Based Optimization of Expensive-to-Evaluate Objective for Optimal Highway Toll Charges in Transportation Network

This article adopts a family of surrogatebased optimization approaches to approximate the response surface for the transportation simulation input– output mapping and search for the optimal toll charges in a transportation network. The computational effort can thus be significantly reduced for the expensive-toevaluate optimization problem. Meanwhile, the random noise that always occurs through simulations can be addressed by this family of approaches. Both one-stage and two-stage surrogate models are tested and compared. A suboptimal exploration strategy and a global exploration strategy are incorporated and validated. A simulationbased dynamic traffic assignment model DynusT (Dynamic Urban Systems in Transportation) is utilized to evaluate the system performance in response to different link-additive toll schemes implemented on a highway in a real road transportation network. With the objective of minimizing the network-wide average travel time, the simulation results show that implementing the optimal toll predicted by the surrogate model can benefit society in multiple ways. The travelers gain from the 2.5% reduction (0.45 minutes) of the average travel time. The total reduction in the time cost during the extended peak hours would be around US$65,000 for all the 570,000 network users assuming a US$15 per hour value of time. Meanwhile, the government benefits from the 20% increase of toll revenue compared to the current situation. Thus, ap*To whom correspondence should be addressed. E-mail: [email protected]. plying the optimized pricing scheme in real world can be an encouraging policy option to enhance the performance of the transportation system in the study region.