Skip to main content

Predictive analytics aid Cologne’s congestion management

The City of Cologne, Germany, and IBM have completed a smarter traffic pilot to predict and manage traffic flow and road congestion in the city. The pilot demonstrates how the city of Cologne can anticipate, better manage, and in many cases, avoid traffic jams and trouble spots across the city using analytics technology. Germany’s fourth largest city, Cologne has a population of just over one million, is a retail centre, hub for trade shows and a cultural center with many museums and galleries. The increas
January 17, 2013 Read time: 3 mins
The City of Cologne, Germany, and 62 IBM have completed a smarter traffic pilot to predict and manage traffic flow and road congestion in the city. The pilot demonstrates how the city of Cologne can anticipate, better manage, and in many cases, avoid traffic jams and trouble spots across the city using analytics technology.

Germany’s fourth largest city, Cologne has a population of just over one million, is a retail centre, hub for trade shows and a cultural center with many museums and galleries. The increase in traffic density and congestion has prompted the city to seek out new ways to better manage and optimise traffic flow and increase the capacity if its transportation networks within the constraints of its infrastructure.

The traffic control centre collects real-time data from more than 150 monitoring stations and twenty traffic cameras on the roads, highways and at intersections that are known as traffic hot spots. However, the control centre currently does not have advanced traffic management tools or a way to forecast what traffic will be like in the near future. The advanced transportation management software could help traffic officials identify imminent road congestion and help them plan and respond ahead of time.

IBM transportation experts and researchers worked with the City of Cologne to analyse data from its traffic monitoring stations along the on the left bank of the Rhine for a period of six weeks with the aid of the IBM traffic prediction tool and IBM, intelligent transportation solutions. The detailed results, which compare the accuracy of the traffic prediction tool to the real-time data, revealed the accuracy of short-term forecasting for thirty minutes ahead to be 94 percent for vehicle speed and 87 percent for the volume of traffic.

The city’s traffic engineers and IBM were able to predict traffic volume and flow with over 90 percent accuracy up to 30 minutes in advance. As a result, travelers would be able to better plan ahead and determine whether they should leave at a different time, plan an alternate route or use a different mode of transportation.

“The traffic prediction pilot results are very encouraging,” said Thomas Weil, director of the Cologne traffic control centre. “Having the ability to create actionable insight from the traffic monitoring data gives us an ability to better manage congestion as well as provide citizens with more precise traffic information. Our traffic control centre would be able to optimise current traffic flow while anticipating and planning for potential traffic incidents.”

“As one of the first congestion-prone large cities to do so, Cologne has taken an important step in the right direction with this project,” said Eric-Mark Huitema, IBM smarter transportation leader, Europe. “Intelligent traffic management based on precise forecasting techniques can help cities anticipate and avoid traffic congestion and possibly reduce the volume of traffic, results in a more sustainable transportation network.”

The traffic prediction tool developed by IBM Research is a component of the IBM's intelligent operation centre software, which draws on experience gained from smarter cities projects with cities around the world.

Related Content

  • April 10, 2012
    Flexible, demand-based parking charges ease parking problems
    Innovative parking initiatives on the US Pacific Coast. David Crawford reviews. Californian cities are leading the way in trialling new solutions to their endemic parking problems. According to Donald Shoup, a professor of urban planning at the University of California in Los Angeles, drivers looking for available spots can cause up to 74% of traffic congestion in downtown areas. One solution is variable, demand-responsive pricing of parking.
  • June 20, 2016
    Do buses need subsidies in congestion charging areas
    David Crawford takes a look at the debate surrounding bus subsidies. Subsidies for public transport are a well-known and frequently-used policy tool directed at reducing the high environmental and social costs of peak-period traffic congestion. But at the end of last year the Swedish Centre for Transport Studies published a working paper entitled ‘Should buses still be subsidised in Stockholm?’ This concluded that the subsidy levels currently being applied in Stockholm could be nearly halved by setting bus
  • May 6, 2015
    Countering congestion’s cost
    A new report on the economic costs of traffic congestion predicts the problem will worsen significantly in future. Jon Masters reviews the figures and some suggested solutions. New figures on the rising economic and environmental costs of congestion have been published by the US traffic data specialist Inrix and the UK’s Centre for Economics & Business Research (Cebr). Their report finds the problem much bigger than previously thought.
  • March 24, 2023
    How digital navigation is key to managing congestion
    Satnav – not costly civil engineering projects – might point us towards better management of congested road networks, argues David Metz of University College London