System and method for predicting updates to network operations

• US 20070121509A1
• Filed: 10/12/2005
• Published: 05/31/2007
• Est. Priority Date: 10/12/2005
• Status: Abandoned Application

• Current Assignee: SBC Knowledge Ventures LP (AT&T, Inc.)
• Original Assignee: SBC Knowledge Ventures LP (AT&T, Inc.)
• Inventors: Chen, Zesen, Taylor, Michael
• Application Number:
  US11/248,410
• Publication Number:
  US 20070121509A1
• Time in Patent Office: Days
• US Class Current: 370/235
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/5003 Managing SLA; Interaction between SLA and QoS
• CPC Class Codes: H04L 41/5009 Determining service level performance parameters or violations of service level contracts, e.g. violations of agreed response time or mean time between failures [MTBF]
• CPC Class Codes: H04L 41/5025 by proactively reacting to service quality change, e.g. by reconfiguration after service quality degradation or upgrade
• CPC Class Codes: H04L 43/55 Testing of service level quality, e.g. simulating service usage

Abstract

A system and method are disclosed for predicting updates to network operations. A system that incorporates teachings of the present disclosure may include, for example, a network management system (NMS) (100) having a memory (104), a communications interface (110), and a controller (102). The controller is programmed to observe (202) packet traffic in a network, and predict (208, 214) a need for updating operations of the network according to the packet traffic and one or more service level agreements (SLAs).

Claims

1. A network management system (NMS), comprising:

a communications interface; and

a controller for controlling operations of the communications interface, and programmed to;

observe packet traffic in a network; and

predict a need for updating operations of the network according to the packet traffic and one or more performance metrics of one or more corresponding service level agreements (SLAs).

2. The NMS of claim 1, wherein the controller is programmed to:

anticipate a shortfall in network resources to support one or more SLAs; and

recommend an adjustment to network resources to remedy the shortfall before its occurrence.

3. The NMS of claim 2, wherein the controller is programmed to recommend the adjustment according to a return on investment model.

4. The NMS of claim 2, wherein the recommendation comprises at least one among a replacement of one or more network resources, a modification to one or more network resources, and an addition of one or more network resources, and wherein a network resource comprises at least one among a network router and a network switch.

5. The NMS of claim 1, wherein the controller is programmed to:

predict a supply and demand model from the observed packet traffic; and

recommend an adjustment to operations according to the supply and demand model.

6. The NMS of claim 5, wherein the controller is programmed to predict from the supply and demand model a price model for one or more services of the network.

7. The NMS of claim 5, wherein the controller is programmed to predict from the supply and demand model an adjustment to services rendered by the network.

8. The NMS of claim 7, wherein the controller is programmed to adjust services according to at least one among a group comprising a discontinuation of one or more existing services, a modification to one or more existing services, and a request for one or more new services.

9. The NMS of claim 7, wherein the controller is programmed to recommend an adjustment to network resources according to the adjustment in services rendered.

10. The NMS of claim 1, wherein the controller is programmed to apply regression analysis on the packet traffic.

11. The NMS of claim 1, wherein the controller is programmed to predict the need for updating network resources of the network according to Bayes'"'"' Theorem.

12. A computer-readable storage medium, comprising computer instructions for:

observing packet traffic in a network;

applying regression analysis to the observed packet traffic;

detecting patterns in the packet traffic;

predicting a need for updating operations of the network according to said patterns and one or more performance metrics of one or more corresponding service level agreements (SLAs).

13. The storage medium of claim 12, comprising computer instructions for:

predicting a number of future SLAs;

anticipating a shortfall in network resources to support the future SLAs; and

recommending an adjustment to network resources to remedy the shortfall before its occurrence according to a return on investment model.

14. The storage medium of claim 12, comprising computer instructions for:

predicting a supply and demand model from the detected patterns; and

recommending at least one among a price model for one or more services of the network, a price model for SLAs, and an adjustment to services rendered by the network.

15. The storage medium of claim 14, comprising computer instructions for adjusting services according to at least one among a group comprising a discontinuation of one or more existing services, a modification to one or more existing services, and a request for one or more new services.

16. The storage medium of claim 14, comprising computer instructions for recommending an adjustment to network resources according to the adjustment in services rendered.

17. The storage medium of claim 12, comprising computer instructions for:

applying Bayes'"'"' Theorem on the packet traffic; and

detecting said patterns in the packet traffic according to Bayes'"'"' Theorem.

18. A method, comprising the steps of:

applying regression analysis to observed packet traffic;

detecting patterns in the packet traffic;

predicting a need for adjusting operations of the network according to said patterns and one or more performance metrics of one or more corresponding SLAs.

19. The method of claim 18, comprising the steps of:

anticipating a shortfall in network resources to support the SLAs; and

reconfiguring the network to remedy the shortfall before its occurrence.

20. The method of claim 19, comprising the step of reconfiguring the network according to at least one among a group of steps comprising:

rerouting of the packet traffic according to the detected patterns;

replacing one or more existing network resources;

modifying one or more existing network resources; and

adding one or more new network resources.