A Multiscale Framework for Forecasting Highway Traffic Flow

Lead Research Organisation: University of Southampton
Department Name: Faculty of Engineering & the Environment

Abstract

Traffic jams are an annoying feature of everyday life. They also hamper our economy: the CBI has estimated that delays due to road traffic congestion cost UK businesses up to 20 billion annually. UK road traffic is forecast to grow by 30% in the period 2000-2015, so it seems that the congestion problem can only get worse. There is consequently an intense international effort in using Information and Communication Technologies to manage traffic in order to alleviate congestion --- this broad area is known as Intelligent Transport Systems (ITS). Regular motorway drivers will already be familiar with ITS. Examples include 1. the Controlled Motorways project on the M25 London Orbital (which sets temporary reduced speed limits when the traffic gets heavy); 2. Active Traffic Management on Birmingham's M42 (where the hard-shoulder becomes an ordinary running lane in busy periods); and 3. The `Queue Ahead'warning signs which are now almost ubiquitous on the English motorway network. The investment in this telematics infrastructure has been very significant --- about 100 million pounds for Active Traffic Management alone.Each of the ITS applications described above has at its heart detailed mathematical and computer models that forecast how traffic flows and how queues build up and dissipate. However, these models are far from perfect, and the purpose of this research is to improve the models by working on the fundamental science that underpins them. This a so-called multiscale challenge, since there is a whole hierarchy of models of different levels of detail, ranging from simulation models that model the behaviour of individual drivers, up to macroscopic models that draw an analogy between the flow of traffic and compressible gas. This research will establish methods for finding out which models are good and which ones are bad. Moreover, it will use modern `machine learning' techniques to combine good models so that computer-based traffic forecasting has human-like artificial intelligence.

Publications

10 25 50
 
Description The very wide range of key findings and outputs from this advanced fellowship are described in the original final report submitted through the University of Southampton. Note that this grant is listed in the EPSRC grant portfolio in two parts - EP/E055567/1 which was held at the University of Bristol; and EP/E055567/2, which was the grant designation following my move to Southampton. They are two designations for the same award. To confuse matters, I have now returned to the University of Bristol.

The first key finding of the grant, as promised, was the development of a new methodology which explains spatiotemporal pattern formation in highway traffic models (stop-and-go waves etc.) in terms of dynamical systems ideas.

The second key finding of the grant was the use of individual vehicle loop data on the M42 motorway to develop a new source of trajectory data for car following models of highway traffic.

These two findings corresponded to the first two of four strands of the proposal and in essence were completed in full. The third and fourth strands of the proposal that concerned data fusion and forecasting were completed in part - mainly due to the very high degree of challenge in these tasks (were is still ongoing) and also because of a decision to diversify the fellowship into other areas of traffic modelling and transport analysis that were not originally part of the proposal.
Exploitation Route I am involved in a variety of discussions with national and regional stakeholders about how to use my theories in forecasting models for highway traffic and smart city operating systems.
Sectors Transport