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.

For more information on companies in this article

Related Content

  • Citilog has perfect congestion remedy
    March 30, 2022
    Traffic incidents are the biggest contributor to nonrecurring congestion. Combined with natural bottlenecks at tunnels, bridges and highways, incidents ranging from debris on the road to vehicle accidents are every driver’s worst nightmare.
  • Statistical improvement for short-term travel time predictions
    June 2, 2014
    Researchers at Imperial College in London have developed a generic three-stage short-term travel prediction model that promises to give greater accuracy under both normal and abnormal conditions. As travellers do not like the randomness of non-recurrent traffic congestion and delays, it is particularly useful for network managers to know how the ongoing traffic situation will develop when an atypical event occurs.
  • Inrix expands traffic data programme collaboration
    October 12, 2012
    Nearly a year after the I-95 Corridor Coalition, the University of Maryland (UMD) and Inrix announced a three-year expansion of the Vehicle Probe Project (VPP), the coalition and its partners are expanding their collaboration once again. Through a Federal Highway Administration (FHWA) Awards Grant, the coalition will use Inrix traffic information to expand coverage to over 40,000 miles of roads across fourteen states.
  • Traffic management: risky business
    June 15, 2023
    Adding a real-time accident risk layer to the profile of a road network ticks all the crucial boxes: it saves time, fuel, money and, ultimately, lives. Harriet King of Valerann explains the brain power of Lanternn by Valerann’s Core Fusion Engine...