Method and structure for vehicular traffic prediction with link interactions

1. An apparatus, comprising:

a receiver to receive data related to traffic on at least a portion of a network; and

a calculator to calculate a traffic prediction for at least a part of said network,

wherein said traffic prediction is calculated by using a deviation from a historical traffic on said network, said deviation being a difference between a historical traffic datum value and a calculated average-case value, and

wherein relationship vectors using such deviations are used to define interrelationships within said network.

2. The apparatus of claim 1 , wherein said network comprises a plurality of interconnected links and a traffic prediction for a link in said network comprises a calculation of a deviation of a historical traffic for said link.

3. The apparatus of claim 2 , wherein said traffic prediction for said link is calculated using a relationship vector that defines other links in said network that affect a traffic amount in said link within a specific time duration.

4. The apparatus of claim 2 , wherein said calculator further calculates said historical traffic for said link as a calibration for traffic in said link.

5. The apparatus of claim 4 , wherein said historical traffic is periodically re-calculated by said calculator.

6. The apparatus of claim 3 , wherein said calculator calculates, for each link in said relationship vector, a traffic deviation from a historical traffic for each said link, and said traffic deviation for said link is expressed as a difference vector for said link, said difference vector comprising a vector of deviations of traffic of each link in said relationship vector.

7. The apparatus of claim 6 , wherein said difference vector is adjusted by an auto-regressive model that modifies said deviations in said difference vector based upon data of previous time intervals for each link in said relationship vector.

8. The apparatus of claim 2 , wherein said prediction comprises a prediction for a first time interval and predictions for subsequent time intervals comprise sequential re-iterations of said prediction for said first interval.

9. The apparatus of claim 1 , wherein said data related to said traffic prediction comprises one or more of:

traffic speed;

traffic density; and

traffic flow.

10. A method of predicting traffic on a network, said method comprising:

receiving data related to at least a portion of said network; and

calculating, using a processor on a computer, a traffic prediction for at least a part of said traffic network by using deviation from a historical traffic on said network, said deviation being a difference between a historical traffic datum value and a calculated average case value, and

wherein relationship vectors using such deviations are used to define interrelationships within said network.

11. The method of claim 10 , wherein said network comprises a plurality of interconnected links and a traffic prediction for a link in said network comprises a calculation of a deviation of a historical traffic for said link.

12. The method of claim 11 , wherein said traffic prediction for said link is calculated using a relationship vector that defines other links in said network that affect a traffic amount in said link within a specific time duration.

13. The method of claim 11 , further comprising calculating said historical traffic for said link as a calibration for traffic in said link.

14. The method of claim 13 , further comprising periodically calculating said historical traffic.

15. The method of claim 12 , further comprising, for each link in said relationship vector, calculating a traffic deviation from a historical traffic for each said link, said traffic deviation for said link being expressed as a difference vector for said link, said difference vector comprising a vector of deviations of traffic of each link in said relationship vector.

16. The method of claim 15 , further comprising adjusting said difference vector using an auto-regressive model that modifies said deviations in said difference vector based upon data of previous time intervals for each link in said relationship vector.

17. The method of claim 11 , wherein said prediction comprises a prediction for a first time interval, said method further comprising re-iterating said prediction of said prediction for said first interval as a prediction for each of a subsequent time intervals for which a future prediction is to be made.

18. The method of claim 10 , wherein said data related to said traffic prediction comprises one or more of:

traffic speed;

traffic density; and

traffic flow.

19. A signal-bearing storage medium tangibly embodying a program of machine-readable instructions executable by a digital processing apparatus to perform a method of predicting traffic on a network, said program comprising:

a receiver module to receive data related to traffic on at least a portion of a network; and

a calculator module to calculate a traffic prediction for at least a part of said network,

wherein said traffic prediction is calculated by using a deviation from a historical traffic on said network, said deviation being a difference between a historical traffic datum value and a calculated average-case value, and

wherein relationship vectors using such deviations are used to define interrelationships within said network.

20. The signal-bearing medium of claim 19 , wherein said network comprises a plurality of interconnected links and a traffic prediction for a link in said network comprises a calculation of a deviation of a historical traffic for said link.