Algorithm to make optimal use of network resources during a mass calling event

• US 8,059,799 B1
• Filed: 08/16/2007
• Issued: 11/15/2011
• Est. Priority Date: 08/16/2007
• Status: Active Grant

• Current Assignee: T-Mobile Innovations LLC (Deutsche Telekom AG)
• Original Assignee: Sprint Communications Company LP (Deutsche Telekom AG)
• Inventors: Bloomcamp, Eric, Green, Jeffery O., Huntsman, Russell E., Gorman, Pierce
• Primary Examiner(s): Gauthier; Gerald
• Application Number:
  US11/840,044
• Time in Patent Office: 1,552 Days
• Field of Search: 370/218, 370/230, 370/233, 370/352, 370/356, 370/395.21, 370/235, 370/395.2, 379/112.05, 379/115.01, 379/133, 379/134, 379/221.08, 455/417, 709/224, 726/23
• US Class Current: 379/112.05
• CPC Class Codes: H04L 65/1069 Session establishment or de-establishment
• CPC Class Codes: H04L 65/1104 Session initiation protocol [SIP]
• CPC Class Codes: H04L 65/80 Responding to QoS
• CPC Class Codes: H04M 15/63 based on the content carried by the session initiation protocol [SIP] messages
• CPC Class Codes: H04M 3/367 Traffic or load control

Abstract

Embodiments of the present invention provide methods, systems, and computer-readable media for achieving a higher call completion rate in a system experiencing a mass calling event. The present invention has several practical applications in the technical arts including optimizing use of network resources during a mass calling event. In various embodiments, a network'"'"'s resources are efficiently utilized by way of sampling a network element'"'"'s control processing unit utilization. Additionally, the various embodiments respond by selecting to negatively acknowledging callers in a mass calling event state in order to prevent system components from becoming overloaded. Overloaded network system components lead to such issues as dropped signaling packets, and higher percentages of call failures. Embodiments of the invention are directed to achieving optimal call completion in the case of a mass calling event.

Claims

1. A computerized method to achieve optimal call completion in the case of a mass calling event, the method comprising:

sampling a control processing unit (CPU) utilization;

calculating a negative acknowledgement rate based on the sampled CPU utilization; and

negatively acknowledging a percentage of call attempts based on the calculated negative acknowledgement rate.

2. The method of claim 1, wherein negatively acknowledging a percentage of call attempts to achieve optimal call completion comprises at least one of the following:

aborting a call, sending a preconfigured message to a caller, sending a preconfigured audio file to a caller, sending a SIP nack, and sending a 403 conditioned response to a caller.

3. The method of claim 1, wherein the negative acknowledgement rate is calculated based on an extent to which the CPU utilization exceeds a CPU threshold level.

4. The method of claim 3, wherein the negative acknowledgement rate is calculated according to the following formula:

NackRate=(CPUS ampledRate−

CPUThreshold)/(100−

CPUThreshold), wherein NackRate is the negative acknowledgment rate, CPUSampledRate is the CPU utilization and CPUThreshold is the CPU threshold level.

5. The method of claim 1, further comprising determining a mass calling event.

6. The method of claim 5, wherein determining the mass calling event comprises comparing the CPU utilization against a CPU threshold level.

7. The method of claim 6, wherein determining the mass calling event further comprises determining an average CPU utilization and comparing the average CPU utilization against the CPU threshold level.

8. The method of claim 1, wherein the method further comprises calculating a new negative acknowledgement rate based on at least one of:

a new sampled CPU utilization; and

a previous negative acknowledgement rate reduced by a negative acknowledgment decay rate.

9. The method of claim 8, wherein the method further comprises negatively acknowledging a percentage of call attempts based on the new negative acknowledgment rate.

10. The method of claim 1, further comprising repeatedly determining further negative acknowledgment rates until a further negative acknowledgement rate is below a minimum negative acknowledgement rate.

11. One or more computer-readable media embodying computer-useable instructions for performing a computerized method to negatively acknowledge call attempts in the case of a mass calling event, the method comprising:

determining CPU utilization;

calculating a negative acknowledgement rate;

negatively acknowledging a percentage of call attempts based on the negative acknowledgement rate;

determining a new negative acknowledgement rate; and

negatively acknowledging a percentage of call attempts based on the new negative acknowledgement rate.

12. The one or more computer-readable media of claim 11, wherein negatively acknowledging a caller comprises at least one of the following:

aborting a call, sending a preconfigured message to a caller, sending a preconfigured audio file to a caller, and sending a 403 conditioned response to a caller.

13. The one or more computer-readable media of claim 11, wherein the negative acknowledgement rate is calculated based on an extent to which the CPU utilization exceeds a CPU threshold level.

14. The one or more computer-readable media of claim 11, wherein the negative acknowledgement rate is calculated according to the following formula:

NackRate=(CPUSampledRate−

CPUThreshold)/(100−

CPUThreshold), wherein NackRate is the negative acknowledgment rate, CPUSampledRate is the CPU utilization and CPUThreshold is the CPU threshold level.

15. The one or more computer-readable media of claim 11, further comprising determining a mass calling event.

16. The one or more computer-readable media of claim 15, wherein determining the mass calling event comprises comparing the CPU utilization against a CPU threshold level.

17. The one or more computer-readable media of claim 16, wherein determining the mass calling event comprises determining an average CPU utilization and comparing the average CPU utilization against the CPU threshold level.

18. One or more computer-readable media embodying computer-useable instructions for performing a method of negatively acknowledging call attempts during a mass calling event, the method comprising:

identifying a mass call event; and

repeatedly determining a negative acknowledgment rate based at least in part on a current CPU utilization and negatively acknowledging a percentage of call attempts based on the negative acknowledgement rate until the negative acknowledgement rate falls below a minimum negative acknowledgment rate threshold.

19. The one or more computer-readable media of claim 18, wherein repeatedly determining a negative acknowledgement rate comprises:

determining a first negative acknowledgement rate based on a current CPU utilization;

determining a second negative acknowledgement rate based on a previous negative acknowledgement and a negative acknowledgement decay rate; and

setting the negative acknowledgement rate as the greater of the first and second negative acknowledgement rates.

20. The one or more computer-readable media of claim 19, wherein the first negative acknowledgement rate is calculated according to the following formula:

NackRate=(CPUSampledRate−

CPUThreshold)/(100−

CPUThreshold), wherein NackRate is the first negative acknowledgment rate, CPUSampledRate is the current CPU utilization and CPUThreshold is a CPU threshold level.