METHODS AND APPARATUS TO SELECT COMPOSITE LINK COST-OUT THRESHOLDS

• US 20100128629A1
• Filed: 11/21/2008
• Published: 05/27/2010
• Est. Priority Date: 11/21/2008
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Sinha, Rakesh Kumar, Oikonomou, Kostas N.
• Granted Patent: US 7,974,213 B2
• Time in Patent Office: Days
• US Class Current: 370/253
• CPC Class Codes: H04L 41/0681 Configuration of triggering conditions
• CPC Class Codes: H04L 43/0835 One way packet loss
• CPC Class Codes: H04L 43/0882 Utilisation of link capacity

Abstract

Methods and apparatus to select composite link cost-out thresholds are disclosed. A disclosed example method comprises collecting traffic statistics for a communication network, computing, based on the collected traffic statistics, a plurality of flow rates for a composite link of the communication network for respective ones of a plurality of potential fault conditions for the composite link, computing a plurality of remaining capacities of the composite link for respective ones of the plurality of fault conditions, computing a plurality of differences between respective ones of the plurality of flow rates and the plurality of remaining capacities, and selecting a cost-out threshold for the composite link based on the plurality of computed differences.

Claims

1. A method comprising:

collecting traffic statistics for a communication network;

computing, based on the collected traffic statistics, a plurality of flow rates for a composite link of the communication network for respective ones of a plurality of potential fault conditions for the composite link;

computing a plurality of remaining capacities of the composite link for respective ones of the plurality of fault conditions; and

selecting a cost-out threshold for the composite link based on the plurality of computed flow rates and the plurality of computed remaining capacities.

2. A method as defined in claim 1, wherein the composite link comprises first and second communication paths, and wherein a first potential fault condition comprises a first defect in the first communication path and a second potential fault condition comprises a second defect in the second communication path.

3. A method as defined in claim 1, further comprising comparing an operating capacity of the composite link to the cost-out threshold to determine whether to cost-out data from the composite link to another communication path.

4. A method as defined in claim 1, further comprising configuring a router associated with the composite link with the cost-out threshold.

5. A method as defined in claim 1, further comprising:

computing a plurality of differences between respective ones of the plurality of flow rates and the plurality of remaining capacities;

eliminating differences that are less than or equal to zero from the plurality of differences to form a plurality of losses;

computing a first expected loss based on one or more of the plurality of losses having a first associated remaining capacity;

computing a second expected loss based on one or more of the plurality of losses having a second associated remaining capacity, wherein the second remaining capacity is greater than the first remaining capacity; and

computing a third expected loss based on one or more of the plurality of losses having a third associated remaining capacity, wherein the third remaining capacity is greater than the second remaining capacity, and wherein the cost-out threshold is selected based on the first, second and third expected losses.

6. A method as defined in claim 5, further comprising:

computing a first difference between the first and second expected losses;

computing a second difference between the second and third expected losses; and

selecting the first associated remaining capacity as the cost-out threshold when the first difference is less than the second difference.

7. A method as defined in claim 1, further comprising:

computing a first network-wide packet loss for the communication network based on the selected cost-out threshold and the collected traffic statistics;

adjusting the cost-out threshold;

computing a second network-wide packet loss for the communication network based on the adjusted cost-out threshold and the collected traffic statistics; and

comparing the first and second network-wide packet losses to determine whether to select the adjusted cost-out threshold.

8. An apparatus comprising:

a collector to collect traffic statistics for a communication network;

a network modeler to compute, based on the collected traffic statistics, a plurality of flow rates for a composite link of the communication network for respective ones of a plurality of potential fault conditions for the composite link, and to compute a plurality of remaining capacities of the composite link for respective ones of the plurality of fault conditions; and

a threshold chooser to select a cost-out threshold for the composite link based on the plurality of computed flow rates and the plurality of computed remaining capacities.

9. An apparatus as defined in claim 8, wherein the composite link comprises first and second communication paths, and wherein a first potential fault condition comprises a first defect in the first communication path and a second potential fault condition comprises a second defect in the second communication path.

10. An apparatus as defined in claim 8, further comprising:

a router associated with the composite link to compare an operating capacity of the composite link to the cost-out threshold to determine whether to cost-out data from the composite link to another communication path; and

a router configurer to configure the router with the selected cost-out threshold.

11. An apparatus as defined in claim 8, further comprising a first data structure having a plurality of entries for respective ones of the plurality of fault conditions, wherein a first entry of the first data structure comprises a first flow rate, a first remaining capacity and a first loss associated with a first fault condition.

12. An apparatus as defined in claim 11, wherein the threshold chooser is to eliminate from the first data structure a second entry comprising a second loss that is less than or equal to zero.

13. An apparatus as defined in claim 8, wherein the threshold chooser is to:

compute a plurality of differences between respective ones of the plurality of flow rates and the plurality of remaining capacities;

compute a first expected loss based on one or more of the plurality of differences having a first associated remaining capacity;

compute a second expected loss based on one or more of the plurality of differences having a second associated remaining capacity, wherein the second remaining capacity is greater than the first remaining capacity;

compute a third expected loss based on one or more of the plurality of differences having a third associated remaining capacity, wherein the third remaining capacity is greater than the second remaining capacity, and

select the cost-out threshold based on the first, second and third expected losses.

14. An apparatus as defined in claim 13, wherein the threshold chooser is to:

compute a first difference between the first and second expected losses;

compute a second difference between the second and third expected losses; and

select the first associated remaining capacity as the cost-out threshold when the first difference is less than the second difference.

15. An apparatus as defined in claim 8, further comprising a threshold optimizer to:

compute a first network-wide packet loss for the communication network based on the selected cost-out threshold and the collected traffic statistics;

adjust the cost-out threshold;

compute a second network-wide packet loss for the communication network based on the adjusted cost-out threshold and the collected traffic statistics; and

compare the first and second network-wide packet losses to determine whether to select the adjusted cost-out threshold.

16. An article of manufacture storing machine-readable instructions that, when executed, cause a machine to:

collect traffic statistics for a communication network;

compute, based on the collected traffic statistics, a plurality of flow rates for a composite link of the communication network for respective ones of a plurality of potential fault conditions for the composite link;

compute a plurality of remaining capacities of the composite link for respective ones of the plurality of fault conditions;

compute a plurality of differences between respective ones of the plurality of flow rates and the plurality of remaining capacities; and

select a cost-out threshold for the composite link based on the plurality of computed differences.

17. An article of manufacture as defined in claim 16, wherein the composite link comprises first and second communication paths, and wherein a first potential fault condition comprises a first defect in the first communication path and a second potential fault condition comprises a second defect in the second communication path.

18. An article of manufacture as defined in claim 16, wherein the machine-readable instructions, when executed, cause the machine to compare an operating capacity of the composite link to the cost-out threshold to determine whether to cost-out data from the composite link to another communication path.

19. An article of manufacture as defined in claim 16, wherein the machine-readable instructions, when executed, cause the machine to configure a router associated with the composite link with the cost-out threshold.

20. An article of manufacture as defined in claim 16, wherein the machine-readable instructions, when executed, cause the machine to:

eliminate differences that are less than or equal to zero from the plurality of differences to form a plurality of losses;

compute a first expected loss based on one or more of the plurality of losses having a first associated remaining capacity;

compute a second expected loss based on one or more of the plurality of losses having a second associated remaining capacity, wherein the second remaining capacity is greater than the first remaining capacity; and

compute a third expected loss based on one or more of the plurality of losses having a third associated remaining capacity, wherein the third remaining capacity is greater than the second remaining capacity, and wherein the cost-out threshold is selected based on the first, second and third expected losses.

21. An article of manufacture as defined in claim 20, wherein the machine-readable instructions, when executed, cause the machine to:

compute a first difference between the first and second expected losses;

compute a second difference between the second and third expected losses; and

select the first associated remaining capacity as the cost-out threshold when the first difference is less than the second difference.

22. An article of manufacture as defined in claim 16, wherein the machine-readable instructions, when executed, cause the machine to:

compute a first network-wide packet loss for the communication network based on the selected cost-out threshold and the collected traffic statistics;

adjust the cost-out threshold;

compute a second network-wide packet loss for the communication network based on the adjusted cost-out threshold and the collected traffic statistics; and

compare the first and second network-wide packet losses to determine whether to select the adjusted cost-out threshold.