System and method of using a machine learning algorithm to meet SLA requirements

• US 10,091,070 B2
• Filed: 06/01/2016
• Issued: 10/02/2018
• Est. Priority Date: 06/01/2016
• Status: Expired due to Fees

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Inventors: Chopra, Danish, Narang, Anshu, Bhullar, Inderpreet, Patel, Hemant, Srinivasa, Shashidhar
• Primary Examiner(s): Jiang, Charles C
• Assistant Examiner(s): LIN, WILL W
• Application Number:
  US15/170,040
• Publication Number:
  US 20170353361A1
• Time in Patent Office: 853 Days
• CPC Class Codes: G06F 2009/4557 Distribution of virtual machine instances; Migration and load balancing
• CPC Class Codes: G06F 2009/45591 Monitoring or debugging support
• CPC Class Codes: G06F 9/45558 Hypervisor-specific management and integration aspects
• CPC Class Codes: H04L 41/00 Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
• CPC Class Codes: H04L 41/0896 Bandwidth or capacity management, i.e. automatically increasing or decreasing capacities flow or congestion control using dynamic resource allocation, e.g. in-call renegotiation, H04L47/76
• CPC Class Codes: H04L 41/0897 by horizontal or vertical scaling of resources, or by migrating entities, e.g. virtual resources or entities
• CPC Class Codes: H04L 41/147 for predicting network behaviour
• CPC Class Codes: H04L 41/40 using virtualisation of network functions or resources, e.g. SDN or NFV entities
• 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 43/00 Arrangements for monitoring or testing data switching networks
• CPC Class Codes: H04L 43/16 Threshold monitoring

Abstract

A method includes collecting, at a monitoring and recovery node, a virtual network function key performance index data through multiple channels from a corresponding containerized virtual network function. The method includes maintaining, at the monitoring and recovery node, state information of the corresponding containerized virtual network function and running, at the monitoring and recovery node, a machine learning algorithm that, once trained, learns and predicts whether the corresponding containerized virtual network function requires one of a scaling, a healing or a context switching to sister virtual network function to yield a determination and meet the service level agreement of a network service.

Claims

1. A method comprising:

collecting a virtual network function key performance index data from a corresponding containerized virtual network function;

maintaining state information of the corresponding containerized virtual network function;

running a machine learning algorithm that, once trained, learns and predicts whether the corresponding containerized virtual network function requires one of a scaling, a healing or a context switching to sister virtual network function to yield a determination;

executing the predicted scaling, the predicted healing, or the predicted context switching of the virtual network function in response to the predictions;

wherein the machine learning algorithm comprises;

T(s)=(Σ

(M(v)+R(a)))%T(m)

R(a)=R_vnf/R_total<

=global median resource usage

T(m)=M(v)_max+R(a)_max, where

T(s) is a threshold for the scaling, the healing or the context switching to the sister virtual network function for the corresponding containerized virtual network function;

M(v) is a metric variable;

R(a) comprises an absolute individual resource usage for the corresponding containerized virtual network function out of multiple containerized virtual network functions;

R_vnf comprises a resource usage for a given virtual network function;

R_total comprises a total resource usage for a network service comprising a group of virtual network functions;

T(m) is a threshold maximum; and

Σ

comprises a summation from i=1 to N, wherein N is a number of times the threshold T(s) for the scaling, the healing or the context switching has succeeded.

2. The method of claim 1, wherein the collecting and running steps occur at a monitoring and recovery node.

3. The method of claim 1, further comprising, when the T(s) threshold is met N times, and the determination indicates an action should be taken, providing an instruction to a provisioning node to perform one of the scaling, the healing and the context switching for the corresponding containerized virtual network function.

4. The method of claim 1, wherein the step of collecting the virtual network function key performance index data occurs through multiple channels.

5. The method of claim 4, wherein the multiple channels comprise at least two of IPSLA, NETCONF, and SNMP.

6. The method of claim 3, wherein when the machine learning algorithm predicts that the corresponding containerized virtual network function requires scaling, providing an instruction to the provisioning node to add a new virtual network function instance.

7. The method of claim 6, wherein the provisioning node adds the new virtual network function instance using a new docker container or a virtual machine.

8. A system comprising:

a processor; and

a computer-readable medium, storing instructions which, when executed by the processor, cause the processor to perform operations comprising;

collecting a virtual network function key performance index data from a corresponding containerized virtual network function;

maintaining state information of the corresponding containerized virtual network function;

running a machine learning algorithm that, once trained, learns and predicts whether the corresponding containerized virtual network function requires one of a scaling, a healing or a context switching to sister virtual network function to yield a determination;

executing the predicted scaling, the predicted healing, or the predicted context switching of the virtual network function in response to the predictions;

wherein the machine learning algorithm comprises;

T(s)=(Σ

(M(v)+R(a)))%T(m)

R(a)=R_vnf/R_total<

=global median resource usage

T(m)=M(v)_max+R(a)_max, where

T(s) is a threshold for the scaling, the healing or the context switching to the sister virtual network function for the corresponding containerized virtual network function;

M(v) is a metric variable;

R(a) comprises an absolute individual resource usage for the corresponding containerized virtual network function out of multiple containerized virtual network functions;

R_vnf comprises a resource usage for a given virtual network function;

R_total comprises a total resource usage for a network service comprising a group of virtual network functions;

T(m) is a threshold maximum; and

Σ

comprises a summation from i=1 to N, wherein N is a number of times the threshold T(s) for the scaling, the healing or the context switching has succeeded.

9. The system of claim 8, wherein the collecting and running steps occur at a monitoring and recovery node.

10. The system of claim 8, wherein the computer-readable medium stores instructions which, when executed by the processor, cause the processor to perform further operations comprising, when the T(s) threshold for scaling is met N times, and the determination indicates an action should be taken, providing an instruction to a provisioning node to perform one of the scaling, the healing and the context switching for the corresponding containerized virtual network function.

11. The system of claim 8, wherein the step of collecting the virtual network function key performance index data occurs through multiple channels.

12. The system of claim 11, wherein the multiple channels comprise at least two of IPSLA, NETCONF, and SNMP.

13. The system of claim 10, wherein when the machine learning algorithm predicts that the corresponding containerized virtual network function requires scaling, providing an instruction to the provisioning node to add a new virtual network function instance.

14. The system of claim 13, wherein the provisioning node adds the new virtual network function instance using a new docker container or a virtual machine.

15. A computer-readable storage device storing instructions which, when executed by a processor, cause the processor to perform operations comprising:

collecting a virtual network function key performance index data from a corresponding containerized virtual network function;

maintaining state information of the corresponding containerized virtual network function;

running a machine learning algorithm that, once trained, learns and predicts whether the corresponding containerized virtual network function requires one of a scaling, a healing or a context switching to sister virtual network function to yield a determination,

executing the predicted scaling, the predicted healing, or the predicted context switching of the virtual network function in response to the predictions;

wherein the machine learning algorithm comprises;

T(s)=(Σ

(M(v)+R(a)))% T(m)

R(a)=R_vnf/R_total<

=global median resource usage

T(m)=M(v)_max+R(a)_max, where

T(s) is a threshold for the scaling, the healing or the context switching to the sister virtual network function for the corresponding containerized virtual network function;

M(v) is a metric variable;

R(a) comprises an absolute individual resource usage for the corresponding containerized virtual network function out of multiple containerized virtual network functions;

R_vnf comprises a resource usage for a given virtual network function;

R_total comprises a total resource usage for a network service comprising a group of virtual network functions;

T(m) is a threshold maximum; and

Σ

comprises a summation from i=1 to N, wherein N is a number of times the threshold T(s) for the scaling, the healing or the context switching has succeeded.

16. The computer-readable storage device of claim 15, wherein the collecting and running steps occur at a monitoring and recovery node.

17. The computer-readable storage device of claim 15, wherein the computer-readable device stores additional instructions which, when executed by the processor, cause the processor to perform further operations comprising, when the T(s) threshold for scaling is met N times, and the determination indicates an action should be taken, providing an instruction to a provisioning node to perform one of the scaling, the healing and the context switching for the corresponding containerized virtual network function.

18. The computer-readable storage device of claim 15, wherein the step of collecting the virtual network function key performance index data occurs through multiple channels.

19. The computer-readable storage device of claim 18, wherein the multiple channels comprise at least two of IPSLA, NETCONF, and SNMP.

20. The computer-readable storage device of claim 15, wherein when the machine learning algorithm predicts that the corresponding containerized virtual network function requires scaling, providing an instruction to the provisioning node to add a new virtual network function instance.