Using Short Term Traffic Predictors in Traffic Management Centres

Using Short Term Traffic Predictors in Traffic Management Centres


Mark Finer, Mott MacDonald Limited, Tom Van Vuren, Mott MacDonald Limited, Chris Van Hinsbergen, Fileradar


This paper discusses the ERA-NET ROAD Mobility research project "STEP" (Short Term Prediction) which implemented short term prediction within traffic management centres to support traffic management decisions and improve network performance.


Europe’s roads are getting busier and busier. According to EUROSTAT, car ownership is increasing in EU member states and expanding road capacity cannot keep up with this growth. On the other hand, Europe’s trade and industrial activity depend on the accessibility of economic centres, ports and airports. With the modal share still strongly favouring road transport (around 50% of all tonne kilometres and more than 80% of all passenger kilometres in Europe are travelled by road), making best use of our existing road infrastructure is crucial.

An element with considerable potential for making better use of existing road capacity is the prediction, in virtually real time, of short-term future traffic conditions, so that adjustments can be made to controllers such as traffic signals and Variable Message Signs, and information can be provided to drivers to stay away from incident areas and avoid the onset of gridlock. However, one major issue for Traffic Control Centres (TCCs) is that real-time modelling is perceived to be highly specialist, expensive and data hungry.

Despite this, across Europe a number of TCCs already operate systems that are supported by considerable sophistication in terms of prediction tools. These systems are provided by a plethora of suppliers, depend on a variety of data sources, with usually high maintenance cost. They use a range of alternative forecasting algorithms, software and hardware, whilst the user interface is generally bespoke. These barriers limit the national roads authorities from collaborative learning from each other’s mistakes and successes, as the constraints and idiosyncrasies of each individual implementation may be too great to encourage joint innovation.

The ERA-NET ROAD Mobility research project "STEP" implemented short term prediction within traffic management centres to support traffic management decisions and ultimately improve network performance. STEP aimed to establish a better understanding of the operational short term prediction requirements of traffic managers at interurban and urban traffic management centres in Europe. STEP has explored the gaps between the state-of-the-art and requirements of operators in terms of functional application, data requirements, interfacing and the success of existing tools that are used.

Under ERA-NET ROAD programme, the project “STEP” (Short TErm Prediction) has explored issues relating to the implementation of short-term traffic prediction in TCCs. Central to the project were real-life trials conducted in an operational traffic management centre environment, testing the tools against user requirements while learning valuable (practical) lessons during implementation. The project results are aimed to be transferable. The project started in 2011 and its field trial in the regional TCC in Utrecht was completed in Spring 2013. The short-term predictor was operational for five months, and used by staff managing the motorway network in the Netherlands’ congested centre. Separately, a test-bed was similarly developed for the South West of England, although this was not used in operations.

The actual predictor that was tested was developed by Fileradar (which best translates as ‘TrafficRadar’), a new company in the Netherlands. The principal objective was not to test the quality of a single predictor in a real-life situation or to compare between alternative predictors. Instead, the intention was to make a predictor available for actual TCC staff to use in their day-to-day work, to investigate what the obstacles are to its success, and to gain a better understanding of whether we could remove some of these issues.

This paper reports on the results of the STEP project – lessons learnt about the state-of-the-art, operational user requirements in terms of short term prediction, and implementing and deploying predictors for live traffic management operations.


Association for European Transport