Method of dynamically adjusting quality of service (QoS) targets

• US 20060212594A1
• Filed: 03/16/2005
• Published: 09/21/2006
• Est. Priority Date: 03/16/2005
• Status: Active Grant

• Current Assignee: Alcatel-Lucent USA, Inc. (Nokia Corporation)
• Original Assignee: Alcatel-Lucent USA, Inc. (Nokia Corporation)
• Inventors: Haner, Mark, Klein, Thierry Etienne, Hinton, Danielle
• Granted Patent: US 9,137,330 B2
• Time in Patent Office: Days
• US Class Current: 709/232
• CPC Class Codes: H04L 47/24 Traffic characterised by specific attributes, e.g. priority or QoS
• CPC Class Codes: H04L 67/61 taking into account QoS or priority requirements

Abstract

In the method of dynamically adjusting quality of service targets, quality of service targets for a first group of applications are reduced based on an overload detection

Claims

1. A method of dynamically adjusting quality of service targets, comprising:

reducing quality of service targets for a first group of applications based on an overload detection.

2. The method of claim 1, wherein the reducing step reduces the quality of service targets for the first group of applications based on an amount of overload detected.

3. The method of claim 1, wherein the reducing step reduces the quality of service targets for the first group of applications in proportion to an amount of overload detected.

4. The method of claim 1, wherein the reducing step reduces the quality of service targets if overload is detected and the detected overload is less than a first overload threshold.

5. The method of claim 1, wherein the reducing step reduces the quality of service targets for the first group of applications to required quality of service values.

6. The method of claim 5, wherein the reducing step reduces the quality of service targets for the first group of applications to required quality of service values if a detected overload is greater than a first threshold, and reduces the quality of service targets for a second group of applications based on an amount of overload detected if the detected overload is less than the first threshold.

7. The method of claim 6, further comprising:

dropping a third group of applications if the detected overload is greater than a second overload threshold, the second overload threshold being greater than the first overload threshold; and

wherein

the reducing step reduces the quality of service targets for the first group of applications to required quality of service values if the detected overload is greater than a first threshold and less than the second threshold.

8. The method of claim 1, wherein the first group of applications have quality of service targets that are greater than respective minimum required quality of service values.

9. The method of claim 8, further comprising:

dropping a second group of applications in a priority class if overload is detected and none of the applications belonging to the priority class have quality of service targets that are greater than respective minimum required quality of service values.

10. The method of claim 1, further comprising:

determining a performance metric for each application; and

detecting overload based on the performance metrics.

11. The method of claim 10, wherein the determining a performance metric for each application step determines each performance metric based on at least one actual performance measurement and a poor performance bound associated with the actual performance measurement such that a lower value of the performance metric indicates better performance.

12. The method of claim 1, wherein the reducing step is performed for a lower priority class of applications that is a lower priority class than a higher priority class of applications.

13. The method of claim 1, wherein the reducing step is performed for the higher priority class of applications after being performed for the lower priority class of applications.

14. The method of claim 12, wherein the applications belong to a priority class based on at least one of service association and user association.

15. The method of claim 14, wherein the higher priority class of application is associated with emergency response services and the lower priority class is associated with municipal services.

16. The method of claim 1, further comprising:

increasing quality of service targets for a second group of applications if an under load is detected.

17. The method of claim 16, wherein the second group of applications each have quality of service targets less than respective preferred quality of service values.

18. The method of claim 16, wherein the increasing step is performed for a higher priority class of applications until respective preferred quality of service values are reached, and then the increasing step is performed for a lower priority class of applications.

19. The method of claim 16, wherein the increasing step increases the quality of service targets by an amount based on an amount of under loading up to respective preferred quality of service targets.

20. A method of dynamically adjusting quality of service targets, comprising:

increasing quality of service targets for a first group of applications based on an amount of under loading detected