Predictive learning machine-based approach to detect traffic outside of service level agreements

• US 9,338,065 B2
• Filed: 01/27/2014
• Issued: 05/10/2016
• Est. Priority Date: 01/06/2014
• Status: Active Grant

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Vasseur, Jean-Philippe, Mermoud, Grgory, Dasgupta, Sukrit
• Primary Examiner(s): Kao, Jutai
• Application Number:
  US14/164,425
• Publication Number:
  US 20150195149A1
• Time in Patent Office: 834 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: H04L 41/12 Discovery or management of network topologies
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/16 using machine learning or artificial intelligence
• 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 41/5019 Ensuring fulfilment of SLA
• CPC Class Codes: H04L 47/2425 for supporting services specification, e.g. SLA

Abstract

In one embodiment, a request to make a prediction regarding one or more service level agreements (SLAs) in a network is received. A network traffic parameter and an SLA requirement associated with the network traffic parameter according to the one or more SLAs are also determined. In addition, a performance metric associated with traffic in the network that corresponds to the determined network traffic parameter is estimated. It may then be predicted whether the SLA requirement would be satisfied based on the estimated performance metric.

Claims

1. A method, comprising:

receiving from a centralized management node a request to make a prediction regarding one or more service level agreements (SLAs) in a network at a router configured to execute a learning machine (LM) algorithm;

establishing a control loop between the centralized management node and the router;

determining, by the router, a network traffic parameter and an SLA requirement associated with the network traffic parameter according to the one or more SLAs;

estimating, by the router, a performance metric associated with a particular communication path in the network that corresponds to the determined network traffic parameter; and

predicting, by the router, whether the SLA requirement would be satisfied based on the estimated performance metric.

2. The method according to claim 1, further comprising:

dynamically adjusting a routing topology of the network when it is predicted that the SLA requirement would not be satisfied.

3. The method according to claim 1, further comprising:

computing one or more alternate communication paths that differ from the particular communication path when it is predicted that the SLA requirement would not be satisfied.

4. The method according to claim 3, further comprising:

defining a schedule according to which the one or more computed alternate communication paths may be utilized.

5. The method according to claim 1, further comprising:

receiving a message indicating the network traffic parameter and the SLA requirement associated with the network traffic parameter.

6. The method according to claim 1, further comprising:

reporting results of the predicting to the centralized management node in the network.

7. The method according to claim 1, further comprising:

determining one or more nodes in the network and their corresponding communication path that corresponds to the determined network traffic parameter.

8. The method according to claim 1, wherein the predicting of whether the SLA requirement would be satisfied further comprises:

determining whether the estimated performance metric satisfies a threshold amount defined by the SLA requirement.

9. The method according to claim 1, further comprising:

establishing one or more of a time at which the predicting is to be performed and a period of time during which the predicting is to be performed.

10. The method according to claim 1, further comprising:

receiving an instruction to adjust a prediction algorithm used to perform the predicting.

11. The method according to claim 1, further comprising:

automatically discovering the particular communication path that corresponds to the determined network traffic parameter.

12. The method according to claim 1, wherein the predicting is performed by the LM algorithm.

13. An apparatus, comprising:

one or more network interfaces that communicate with a network;

a processor coupled to the one or more network interfaces and configured to execute a process which includes a learning machine (LM) algorithm; and

a memory configured to store program instructions which contain the process executable by the processor, the process comprising;

receiving from a centralized management node a request to make a prediction regarding one or more service level agreements (SLAs) in the network;

establishing a control loop with the centralized management node;

determining a network traffic parameter and an SLA requirement associated with the network traffic parameter according to the one or more SLAs;

estimating a performance metric associated with a particular communication path in the network that corresponds to the determined network traffic parameter; and

predicting whether the SLA requirement would be satisfied based on the estimated performance metric.

14. The apparatus according to claim 13, wherein the process further comprises:

dynamically adjusting a routing topology of the network when it is predicted that the SLA requirement would not be satisfied.

15. The apparatus according to claim 13, wherein the process further comprises:

computing one or more alternate communication paths that differ from the particular communication path when it is predicted that the SLA requirement would not be satisfied.

16. The apparatus according to claim 15, wherein the process further comprises:

defining a schedule according to which the one or more computed alternate communication paths may be utilized.

17. The apparatus according to claim 13, wherein the process further comprises:

receiving a message indicating the network traffic parameter and the SLA requirement associated with the network traffic parameter.

18. The apparatus according to claim 13, wherein the process further comprises:

reporting results of the predicting to the centralized management node in the network.

19. The apparatus according to claim 13, wherein the process further comprises:

determining one or more nodes in the network and their corresponding communication path that corresponds to the determined network traffic parameter.

20. The apparatus according to claim 13, wherein the predicting of whether the SLA requirement would be satisfied further comprises:

determining whether the estimated performance metric satisfies a threshold amount defined by the SLA requirement.

21. The apparatus according to claim 13, wherein the process further comprises:

establishing one or more of a time at which the predicting is to be performed and a period of time during which the predicting is to be performed.

22. The apparatus according to claim 13, wherein the process further comprises:

receiving an instruction to adjust a prediction algorithm used to perform the predicting.

23. The apparatus according to claim 13, wherein the process further comprises:

automatically discovering the particular communication path that corresponds to the determined network traffic parameter.

24. The apparatus according to claim 13, wherein the apparatus is a router executing the LM algorithm.

25. A tangible non-transitory computer readable medium storing program instructions that cause a computer to execute a process, the process comprising:

receiving from a centralized management node a request to make a prediction regarding one or more service level agreements (SLAs) in a network at a router configured to execute a learning machine (LM) algorithm;

establishing a control loop between the centralized management node and the router;

determining a network traffic parameter and an SLA requirement associated with the network traffic parameter according to the one or more SLAs;

estimating a performance metric associated with a particular communication path in the network that corresponds to the determined network traffic parameter; and

predicting whether the SLA requirement would be satisfied based on the estimated performance metric.