Enhanced short and longer term network performance prediction capabilities through data-driven analytics and simulation (iMOVE CRC-PATREC, 2018-2019)

Enhanced Network Performance

This project aims to improve the ability of road authorities to predict network performance in the short term using data-driven analytics and to incorporate the impact of Automated Vehicles (AVs) in longer term predictions. The project has two subprojects:

  • Subproject 1:  Develop mathematical and data-driven empirical models (mathematical prediction using machine learning) for short-term traffic prediction as pre-emptive for early warning of network failure. Predictions done on link level as well as area level, aiming to utilising emerging traffic datasets to improve network operations
  • Subproject 2: Simulate the longer term traffic impact of AVs and CAV on Perth’s freeways. Generate scenarios to determine upper and lower bounds, negative and positive impacts of an uncertain future for planning and management. Replicate Stern et al’s dissipation of stop and go traffic waves via control of a single AV. Apply simulation to a larger ring track, 2 lanes with a range of AV penetration rates. Apply alterative driving model on Canning Highway