.png){kind=icon}
.png){kind=icon}
Return
Review of volume-delay functions integrating traditional models and emerging AI technologies
.png){kind=icon}
PRE
AI
P
H
L
Z
DOI：10.26599/COMMTR.2026.9640003.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Link performance functions (LPFs) underpin the estimation of travel times, delays, and congestion in transportation network models. As multimodal systems become increasingly data rich and feature connected and automated vehicles (CAVs), electric vehicles (EVs), and complex queuing phenomena, traditional LPFs face limitations in accuracy, physical consistency, and real-time adaptability. This review synthesizes the evolution of LPFs to address these modern challenges and bridge theoretical foundations, diverse data sources, and artificial intelligence (AI) techniques. We conduct a systematic literature survey of over 270 peer-reviewed studies, covering (i) classical empirical forms (e.g., the US Bureau of Public Roads (BPR), Davidson), (ii) theory-driven models (fundamental-diagram and fluid-queue approaches), and (iii) AI-augmented frameworks (long short-term memory (LSTM), graph neural network (GNN), transformer, and physics-informed learning). Models are classified by their mathematical assumptions, data requirements, integration with dynamic traffic assignment tools, and support for multimodal flow interactions. We further evaluate each class against emerging criteria: Queuing dynamics, CAV/EV impacts, data fusion complexity, and computational tractability, with the following: (1) We highlight the emergence of hybrid physics-machine learning (ML) models that enforce conservation laws while leveraging large-scale probe and sensor data. (2) We identify critical gaps in AI-related method evaluation, with many studies replying on point-error metrics rather than system-level key performance indicators (KPIs) (e.g., network delay, throughput, queue length, bottleneck durations). (3) We demonstrate that physics-informed neural networks (PINNs) achieve superior predictive accuracy in travel time estimation while maintaining physical consistency, outperforming both traditional LPFs and other data-driven approaches. Overall, by bridging theory, data, and AI, this review maps the LPF landscape, highlights open research directions (e.g., fully differentiable LPFs, uncertainty quantification, real-time adaptation), and provides a roadmap for robust and transparent models for next-generation multimodal transportation networks.
Keywords:
link performance functions
volume-delay functions
physically informed
fluid-queue-based
emerging transportation applications
multimodal systems
artificial intelligence (AI)
Journal
IF:
14.5
Papers:
216
Citations:
915
Organization
Cited Papers