Dismiss
InnovationQ will be updated on Sunday, Oct. 22, from 10am ET - noon. You may experience brief service interruptions during that time.
Browse Prior Art Database

Traffic prediction based on real-time road data

IP.com Disclosure Number: IPCOM000214659D
Publication Date: 2012-Feb-01
Document File: 4 page(s) / 45K

Publishing Venue

The IP.com Prior Art Database

Abstract

This article describes a method to predict the traffic based on historical data and adapt the prediction with real data when the time of the prediction approaches.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 41% of the total text.

Page 01 of 4

Traffic prediction based on real-time road data

Traffic prediction is a strategic component of traffic flow optimization. Current techniques in traffic prediction use historical data to predict the amount of traffic: for example, based on the fact that in the last 3 months on Monday morning a street was very crowded, the prediction is that next Monday the street will be again very crowded. This type of prediction, because of its own nature, cannot account for variations in the historical data due to unpredictable events, like a strike in public transportation, or unexpected car flows due to vacations.

The method we present allows improving the prediction based on historical data, using real time information collected from the street management systems. While there are many alternative to implement this method, like leveraging the Telepass (wireless automated highway billing) system, or the Safety Tutor (speed violation monitoring) system of the Autostrade per l'Italia company or the like, or data supplied by in-car navigation systems, in the description of the method we will focus on the Telepass based solution. The Telepass system allows collecting historical information about the route of a travelling car, and to know in real time when a car starts its route. Merging the historical data with the real-time information that a car is starting its route, allows generating more accurate predictions, where the number of cars and the time they start traveling along a road is accurately known based on data collected by the Telepass system.

More in detail the Telepass system allows identifying a car entering a road, to know where the car completed the road travel and the time it required. While these information are mainly used to bill the car for the usage of the road, they can also be collected to create a history of the car preferred routes and the mean travelling time.

To simplify the presentation of this method, let's assume cars travel along an highway that starts at point A and terminates at point C, with an intermediate entry/exit point known as B. At A cars can enter in the highway, then drive up to B or


C. Cars entering at B can the only drive to C. This can be considered as a single lane of the highway; it is obviously possible to have another lane that allows to drive from C to A, but we consider a single lane for simplicity.

For each car entering at A, using the Telepass system, we can know the probability that it drives up to B or up to C, and the time required to complete the travel. For example for a particular car we know that:


· it drives up to C 90% of the times, taking a time of 60 minutes.


· It drives up to B the remaining 10% of the times, taking a time of 40 minutes.

We can also know the time the car usually enters in the highway, for example we

1


Page 02 of 4

can know that it usually enters the highway at 8 AM.

The system allows to accumulate the above information for every car entering the highway. So we can t...