Diagnostic system, method, and recording medium for signalized transportation networks

• US 9,836,960 B2
• Filed: 08/23/2016
• Issued: 12/05/2017
• Est. Priority Date: 08/28/2015
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Bouillet, Eric P., Hoang, Thanh Lam, Nair, Rahul, Pascale, Alessandra
• Primary Examiner(s): Zanelli, Michael J
• Application Number:
  US15/245,028
• Publication Number:
  US 20170061786A1
• Time in Patent Office: 469 Days
• CPC Class Codes: G08G 1/0125 Traffic data processing
• CPC Class Codes: G08G 1/0145 for active traffic flow control

Abstract

A diagnosis system for an adaptive signal control system in a network, the diagnosis system including a traffic state identification device configured to estimate a traffic state describing a supply-demand mismatch by identifying a relationship between real time data feed from a sensor and a control strategy of said adaptive signal control system and a network transition model device configured to diagnose the supply-demand mismatch and an evolution of the supply-demand mismatch on a network level based on said relationship and infrastructure data of the network.

Claims

1. A diagnosis system for an adaptive signal control system in a network, said system comprising:

a processor; and

a memory, the memory storing instructions to cause the processor to;

estimate a traffic state by identifying a relationship between real time data feed from a plurality of sensors and a control strategy of said adaptive signal control system;

store a probability that a supply-demand mismatch of the traffic state will propagate from a first sensor to a second sensor; and

train the control strategy of the adaptive signal control system to adjust signal control actions to reduce the probability that the supply-demand mismatch will propagate from the first sensor to the second sensor.

2. The diagnosis system according to claim 1, wherein the memory further stores instructions to cause the processor to:

diagnose a location and a severity of supply-demand mismatches;

identify a location of propagation paths and congestion hubs within the network based on the probability that the supply-demand mismatch of the traffic state will propagate from the first sensor to the second sensor;

identify a loss or a gain in a throughput over the propagation paths; and

predict propagation paths in the network at a different location.

3. The diagnosis system according to claim 1, wherein the memory further stores instructions to cause the processor to diagnose the supply-demand mismatch of the traffic state and an evolution of the supply-demand mismatch on a network level based on said relationship and infrastructure data of the network.

4. The diagnosis system according to claim 3, wherein the memory further stores instructions to cause the processor to predict a future evolution of the supply-demand mismatch on the network level based on an identified loss or an identified gain in a throughput over the predetermined path.

5. The diagnosis system according to claim 3, wherein the diagnoses uses a dynamic cascade model to diagnose the supply-demand mismatch and the evolution of the supply-demand mismatch on the network level.

6. The diagnosis system according to claim 1, wherein the memory further stores instructions to cause the processor to identify a loss or a gain in a throughput over a predetermined path based on the diagnosed supply-demand mismatch and an evolution of the supply-demand mismatch.

7. The diagnosis system according to claim 1, wherein the memory further stores instructions to cause the processor to estimate a severity and a location of the traffic state describing the supply-demand mismatch for each sensor of the sensor disposed in the adaptive signal control system.

8. The diagnosis system according to claim 1, wherein the memory further stores instructions to cause the processor to:

store the probability on a training data device configured to store real time feed data; and

learn a parameter set at each sensor of the sensors to increase an efficiency of the control strategy of said adaptive signal control system based on the real time feed data stored in the training data device and the infrastructure data.

9. The diagnosis system according to claim 8, wherein the parameter set at each sensor is learned while the diagnosis system is offline.

10. The diagnosis system according to claim 1, wherein the memory further stores instructions to cause the processor to identify a frequency of the supply-demand mismatch and a frequency of an evolution of the supply-demand mismatch on the network level.

11. The diagnosis system according to claim 1, embodied in a cloud-computing environment.

12. A computer-implemented diagnosis method for an adaptive signal control system of a network, said diagnosis method comprising:

estimating a traffic state by identifying a relationship between real time data feed from a plurality of sensors and a control strategy of said adaptive signal control system;

storing a probability that a supply-demand mismatch of the traffic state will propagate from a first sensor to a second sensor; and

training the control strategy of the adaptive signal control system to adjust signal control actions to reduce the probability that the supply-demand mismatch will propagate from the first sensor to the second sensor.

13. The computer-implemented method of claim 12, further comprising:

diagnosing a location and a severity of supply-demand mismatches;

identifying a location of propagation paths and congestion hubs within the network based on the probability that the supply-demand mismatch of the traffic state will propagate from the first sensor to the second sensor;

identifying a loss or a gain in a throughput over the propagation paths; and

predicting propagation paths in the network at a different location.

14. The computer-implemented method of claim 12, further comprising diagnosing the supply-demand mismatch of the traffic state and an evolution of the supply-demand mismatch on a network level based on said relationship and infrastructure data of the network.

15. The computer-implemented method of claim 12, further comprising identifying a loss or a gain in a throughput over a predetermined path based on the diagnosed supply-demand mismatch and an evolution of the supply-demand mismatch.

16. The computer-implemented method of claim 12, embodied in a cloud-computing environment.

17. A computer program product for a diagnosis program for an adaptive signal control system in a network, the computer program product comprising a computer-readable storage medium having program instructions embodied therewith, the program instructions executable by a computer to cause the computer to perform:

estimating a traffic state by identifying a relationship between real time data feed from a plurality of sensors and a control strategy of said adaptive signal control system;

storing a probability that a supply-demand mismatch of the traffic state will propagate from a first sensor to a second sensor; and

training the control strategy of the adaptive signal control system to adjust signal control actions to reduce the probability that the supply-demand mismatch will propagate from the first sensor to the second sensor.

18. The computer program product of claim 17, further comprising:

diagnosing a location and a severity of supply-demand mismatches;

identifying a location of propagation paths and congestion hubs within the network based on the probability that the supply-demand mismatch of the traffic state will propagate from the first sensor to the second sensor;

identifying a loss or a gain in a throughput over the propagation paths; and

predicting propagation paths in the network at a different location.

19. The computer program product of claim 17, further comprising diagnosing the supply-demand mismatch of the traffic state and an evolution of the supply-demand mismatch on a network level based on said relationship and infrastructure data of the network.

20. The computer program product of claim 17, further comprising identifying a loss or a gain in a throughput over a predetermined path based on the diagnosed supply-demand mismatch and an evolution of the supply-demand mismatch.