Swedish Train operator uses Big Data to ‘avoid train delays that haven’t happened yet’
Stockholmståg, the train operator is using new technology that employs big data to predict train delays before they happen.
The Commuter Prognosis
The a mathematic algorithm, called “The commuter prognosis” was developed in Stockholm, Sweden.
When a train is not on time the algorithm forecasts disruptions in the entire network by using historic big data to prevent the ripple effects that actually causes most delays.
Wilhelm Landerholm the mathematician who has developed the algorithm said: “We have built a prediction model, using big data, that let’s us visualise the entire commuter train system two hours into the future. We can now forecast disruptions in our service and our traffic control center can prevent the ripple effects that actually cause most delays.”
The algorithm has been tested but is not currently being used by traffic controllers.
How it works?
The key to the model is a large amount of historical data. The model works similar to a seismograph, an instrument that measures and records details of earthquakes, such as force and duration, but instead identifies late train arrivals. When this happens, the system uses historical data from previous occurrences to forecast the likely impact on the entire train network.
Real-time public transportation information is already used around the globally, however, traffic control centres still typically assess delays manually to try and prevent further problems in a network. The commuter prognosis system on the other hand will forecast these delay effects instantaneously and provide a prediction of how a single or multiple disturbance might affect the whole train network. The commuter prognosis system could change how traffic control centers operate all over the world world.
The Effects of One Delayed Train Can Quickly Multiply Within a Train Network
“ Imagine that “The commuter prognosis” forecasts that a train will be 10 minutes late to station C in two hours. To deal with this the traffic control center issues a new train from station A that will arrive on time at station C. As soon as the new train has been put in motion the algorithm re-calculates and gives the traffic control center a new forecast for the entire train network within minutes.”
The most important benefit of “The commuter prognosis” is that it provides for a more punctual public transportation.
App in the making
“The commuter prognosis” will be available in a smart phone app based on the original model. The app will integrate with other transportation big data to make commuting easier and will indicate which coaches are more or less crowded.
- A mathematical model interprets big data to forecasts for each train in the train network.
- The commuter prognosis can warn about delays two hours before the departure or arrival actually takes place.
- The the commuter prognosis calculates how the delay affects other trains in the system.
- The purpose of “the commuter prognosis” is to make life easier for traffic control centres and to give passengers a better service.
- In the future the algorithm will be potentially adaptable for more types of public transportations and cities.