ABSTRACT
Current data-driven traffic prediction models are usually trained with large datasets, e.g., several months of speeds and flows. Such models provide very good fit for ordinary road conditions, but often fail just when they are most needed: when traffic suffers a sudden and significant disruption, e.g., a road incident. In this work, we describe QTIP: a simulation-based framework for quasi-instantaneous adaptation of prediction models upon traffic disruption. In a nutshell, QTIP performs real-time simulations of the affected road for multiple scenarios, analyzes the results, and suggests a change to an ordinary prediction model accordingly. QTIP constructs the simulated scenarios per properties of the incident, as conveyed by real-time distress signals from In-Vehicle Monitor Systems, which are becoming increasingly prevalent worldwide. We experiment QTIP in a case study of a Danish motorway, and the results show that QTIP can improve traffic prediction in the first critical minutes of road incidents.
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes
1. We are oversimplifying here for the sake of the argument, as there are also “white-box” machine learning approaches, such as Probabilistic Graphical Models (Peled et al., Citation2019).
2. Mastra and Hastrid databases, http://www.vejdirektoratet.dk/http://www.vejdirektoratet.dk/