Model-Based Dynamic Toll Pricing: An Overview

Lombardi, C.; Picado-Santos, Luís; Annaswamy, Anuradha M. · 2021 · OpenAlex-citations

DOI: 10.3390/app11114778

archive: archived pipeline: cataloged verified

Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)

Summary

This review paper examines the current state of research on model-based dynamic toll pricing, a congestion management strategy where tolls vary in real-time based on traffic conditions. The authors aim to synthesize recent literature to identify common methodologies, differences in approach, and emerging trends in price definition, simulation, and technology application. The study is motivated by the growing implementation of dynamic pricing in managed lanes, such as High Occupancy Toll (HOT) facilities, and the need to move beyond simple heuristic strategies toward more sophisticated, model-based schemes. The authors conducted a systematic review of 209 documents retrieved from the Scopus database using the keywords “dynamic,” “toll,” and “pricing.” The analysis focused primarily on studies published between 2008 and 2021, a period marking the maturation of pricing algorithms for HOT operations. The review categorized studies by scope (managed lanes, networks, or general facilities), pricing rule principles, traffic simulation bases, driver behavior models, and recent technology applications. The authors analyzed the structural components of these studies, which typically combine a pricing strategy with a socio-technical simulation model that integrates driver behavior and traffic flow dynamics. The findings reveal that optimization is the dominant method for defining toll prices across the reviewed literature. However, control-based algorithms, such as proportional-integral-derivative (PID) controllers, are notably prevalent in studies focusing on managed lanes. Regarding simulation techniques, there is significant variety; macroscopic traffic models are the most common for simulating traffic flow, while logit models are predominantly used to represent driver behavior. The review also highlights that few studies include models for quantifying externalities, such as emissions or social costs. Additionally, the authors note a rising trend in the application of artificial intelligence paradigms, including reinforcement learning and big data mining, within dynamic toll pricing frameworks. The significance of this work lies in its comprehensive mapping of the methodological landscape for dynamic toll pricing. By identifying the prevalence of optimization and control-based approaches, the paper provides a clear overview of the technical foundations currently shaping the field. The observation that AI and advanced simulation techniques are gaining importance suggests a shift toward more adaptive and data-driven pricing schemes. The review concludes by offering insights into future research perspectives, emphasizing the need for more integrated models that account for externalities and leverage emerging technologies to improve the efficiency and effectiveness of congestion pricing systems.

Provenance

The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.

Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.

Topics

Ranked by relevance to this paper. Hover a topic for its definition.

• work zones