Communication path managing method and communication path managing system

• US 10,277,507 B2
• Filed: 12/28/2016
• Issued: 04/30/2019
• Est. Priority Date: 12/06/2016
• Status: Active Grant

• Current Assignee: Industrial Technology Research Institute
• Original Assignee: Industrial Technology Research Institute
• Inventors: Lo, Chao-Cheng, Wen, Yi-Lun
• Primary Examiner(s): Ho, Duc C
• Application Number:
  US15/392,800
• Publication Number:
  US 20180159768A1
• Time in Patent Office: 853 Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 43/0811 by checking connectivity
• CPC Class Codes: H04L 43/087 Jitter
• CPC Class Codes: H04L 43/0894 Packet rate
• CPC Class Codes: H04L 45/123 Evaluation of link metrics techniques for monitoring network metrics H04L43/08
• CPC Class Codes: H04L 45/70 Routing based on monitoring results

Abstract

A communication path managing method and a communication path managing system are provided. The communication path managing method includes the following steps: A plurality of communication paths connected to a vehicle are provided. A plurality of evaluation items of each of the communication paths are analyzed. A demand situation of the vehicle is identified according to a sensing data of the vehicle. An item importance information is obtained according to the demand situation. At least one of the communication paths is selected according to the evaluation items based on the item importance information.

Claims

1. A communication path managing method, comprising:

providing a plurality of communication paths connected to a vehicle;

analyzing a plurality of evaluation items of each of the communication paths;

identifying a demand situation of the vehicle according to a sensing data of the vehicle;

obtaining an item importance information according to the demand situation; and

selecting at least one of the communication paths for the vehicle according to the evaluation items based on the item importance information.

2. The communication path managing method according to claim 1, wherein the evaluation items include a routing path latency, an available bandwidth, a variance of available bandwidth and a connection keeping ability.

3. The communication path managing method according to claim 1, wherein each of the evaluation items is set a standard threshold, and the communication path managing method further comprising:

classifying each of the communication paths to one of a plurality of groups according to a standard reaching number of each of the communication paths, wherein the standard reaching number is a number of the evaluation items which are better than the standard thresholds respectively, the standard reaching number of each of the communication paths in one of the groups is different from the standard reaching number of each of the communication paths in another one of the groups.

4. The communication path managing method according to claim 3, wherein in the step of classifying each of the communication paths to one of the groups, each of the communication paths is classified via a machine learning classifying algorithm.

5. The communication path managing method according to claim 3, wherein in the step of classifying each of the communication paths to one of the groups, each of the communication paths is classified via a K means algorithm or a Gaussian likelihood algorithm.

6. The communication path managing method according to claim 1, wherein each of the evaluation items is set a standard threshold, and the communication path managing method further comprising:

classifying each of the communication paths to one of a first group, a second group and a third group according to a standard reaching number of each of the communication paths, wherein the standard reaching number is a number of the evaluation items which are better than the standard thresholds respectively, all of the evaluation items of each of the communication paths in the first group are better than the standard thresholds respectively, only part of the evaluation items of each of the communication paths in the second group are better than the standard thresholds respectively, and all of the evaluation items of each of the communication paths in the third group is worse than the standard thresholds.

7. The communication path managing method according to claim 6, wherein in the step of selecting at least one of the communication paths for the vehicle, the at least one of the communication paths is selected according to an order of the first group, the second group and the third group.

8. The communication path managing method according to claim 1, wherein the item importance information indicates part of the evaluation items.

9. The communication path managing method according to claim 1, wherein in the step of identifying the demand situation of the vehicle, the demand situation of the vehicle is identified via a machine learning grouping algorithm.

10. The communication path managing method according to claim 1, wherein in the step of identifying the demand situation of the vehicle, the demand situation of the vehicle is identified via an artificial neural network algorithm (ANN algorithm) or a support vector machines algorithm (SVM algorithm).

11. The communication path managing method according to claim 1, wherein the demand situations include a moving status, a network loading status, an environment status or a cost demand of the vehicle.

12. The communication path managing method according to claim 1, further comprising:

predicting the demand situation of the vehicle according a map information.

13. A communication path managing system, comprising:

a path unit for providing a plurality of communication paths connected to a vehicle;

an evaluating unit for analyzing a plurality of evaluation items of each of the communication paths;

an identifying unit for identifying a demand situation of the vehicle according to a sensing data of the vehicle;

an analyzing unit for obtaining an item importance information according to the demand situation; and

a selecting unit for selecting at least one of the communication paths for the vehicle according to the evaluation items based on the item importance information.

14. The communication path managing system according to claim 13, wherein the evaluation items include a routing path latency, an available bandwidth, a variance of available bandwidth and a connection keeping ability.

15. The communication path managing system according to claim 13, wherein each of the evaluation items is set a standard threshold, and the communication path managing system further comprising:

a classifying unit for classifying each of the communication paths to one of a plurality of groups according to a standard reaching number of each of the communication paths, wherein the standard reaching number is a number of the evaluation items which are better than the standard thresholds respectively, the standard reaching number of each of the communication paths in one of the groups is different from the standard reaching number of each of the communication paths in another one of the groups.

16. The communication path managing system according to claim 15, wherein the classifying unit classifies each of the communication paths via a machine learning classifying algorithm.

17. The communication path managing system according to claim 15, wherein the classifying unit classifies each of the communication paths via a K means algorithm or a Gaussian likelihood algorithm.

18. The communication path managing system according to claim 13, wherein each of the evaluation items is set a standard threshold, and the communication path managing system further comprising:

a classifying unit for classifying each of the communication paths to one of a first group, a second group and a third group according to a standard reaching number of each of the communication paths, wherein the standard reaching number is a number of the evaluation items which are better than the standard thresholds respectively, all of the evaluation items of each of the communication paths in the first group are better than the standard thresholds respectively, only part of the evaluation items of each of the communication paths in the second group are better than the standard thresholds respectively, and all of the evaluation items of each of the communication paths in the third group is worse than the standard thresholds.

19. The communication path managing system according to claim 18, wherein the selecting unit selects the at least one of the communication paths according to an order of the first group, the second group and the third group.

20. The communication path managing system according to claim 13, wherein the item importance information indicates part of the evaluation items.

21. The communication path managing system according to claim 13, wherein the identifying unit identifies the demand situation of the vehicle via a machine learning grouping algorithm.

22. The communication path managing system according to claim 13, wherein the identifying unit identifies the demand situation of the vehicle via an artificial neural network algorithm (ANN algorithm) or a support vector machines algorithm (SVM algorithm).

23. The communication path managing system according to claim 13, wherein the demand situations include a moving status, a network loading status, an environment status or a cost demand of the vehicle.

24. The communication path managing system according to claim 13, further comprising:

a predicting unit for predicting the demand situation of the vehicle according a map information.