Short-Term Traffic Prediction Under Non-Recurrent Incident Conditions Integrating Data-Driven Models and Traffic Simulation
- Publication Type:
- Conference Proceeding
- Citation:
- 2020
- Issue Date:
- 2020-01-12
Open Access
Copyright Clearance Process
- Recently Added
- In Progress
- Open Access
This item is open access.
Predicting the traffic condition in urban networks is a priority for all traffic management centers around the world. This becomes very challenging especially when the network is affected by traffic incidents which vary in both time and space. Although data-driven machine learning (ML) modeling can be considered as an ideal tool for short-term traffic predictions, its performance is severely degraded when little historical traffic information is available under non-recurrent incident conditions. This paper addresses this challenge by integrating both data-driven and traffic simulation modeling. Instead of directly predicting the traffic states using limited historical data, we apply data-driven models to reinforce the traffic microsimulation. More explicitly, we employ ML models to predict origin-destination (OD) demand flows based on historical day-to-day demand flows. The traffic simulation uses the freshly reported incident information and the predicted OD demand flows obtained from ML models to forecast the future traffic states under non-recurrent incident conditions. Since accurate OD flows cannot directly measured in large-scale areas, we propose an OD demand rolling-horizon estimation problem to estimate demand flows based on the most recent measured link volumes. Results show that Decision Tree method outperforms other ML models in OD demand flow prediction. Finally, we showcase the capability of the proposed data-driven enforced traffic simulation platform for incident impact analysis in a real –life subnetwork from Sydney, Australia.
Please use this identifier to cite or link to this item: