DISTRIBUTED ARCHITECTURE FOR MACHINE LEARNING BASED COMPUTATION USING A DECISION CONTROL POINT

• US 20140222730A1
• Filed: 07/30/2013
• Published: 08/07/2014
• Est. Priority Date: 02/05/2013
• 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
• Granted Patent: US 9,443,204 B2
• Time in Patent Office: Days
• US Class Current: 706/12
• CPC Class Codes: G06F 11/3433 for load management allocation of a server based on load conditions G06F9/505; load rebalancing G06F9/5083; redistributing the load in a network by a load balancer H04L67/1029
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 67/1029 using data related to the state of servers by a load balancer

Abstract

In one embodiment, a request is received from a requesting node in a network to assist in distributing a task of the requesting node. Upon receiving the message, a capability to perform the task of one or more helping nodes in the network is evaluated, and a helping node of the one or more helping nodes is selected to perform the task based on the evaluated capability of the selected helping node. The distribution of the task is then authorized from the requesting node to the selected helping node.

Claims

1. A method, comprising:

receiving a request from a requesting node in a network to assist in distributing a task of the requesting node;

evaluating a capability to perform the task of one or more helping nodes in the network;

selecting a helping node of the one or more helping nodes to perform the task based on the evaluated capability of the selected helping node; and

authorizing the distribution of the task from the requesting node to the selected helping node.

2. The method according to claim 1, wherein the evaluating of the capability to perform the task comprises:

evaluating historical data relating to a particular helping node.

3. The method according to claim 2, wherein the historical data includes one or more of:

information relating to a previous task performed by the particular helping node, an indication of success or failure of the previous task, and a degree of confidence associated with the particular helping node.

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

storing the historical data in a local database; and

when evaluating the historical data relating to the particular helping node, accessing the historical data from the local database.

5. The method according to claim 1, wherein the evaluating of the capability to perform the task comprises:

evaluating information specified in the received request.

6. The method according to claim 5, wherein the information specified in the received request includes one or more of:

a period of time during which the task is to be performed, an indication of type of the task, a resource necessary to perform the task, and a network performance metric.

7. The method according to claim 1, wherein the evaluating of the capability to perform the task comprises:

evaluating a network-based parameter relating to the network or a particular helping node.

8. The method according to claim 1, wherein the evaluating of the capability to perform the task is performed by a Learning Machine-based algorithm.

9. The method according to claim 1, wherein the authorizing of the distribution of the task comprises:

sending a message to the requesting node indicating an identity of the selected helping node.

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

receiving a message from the selected helping node indicating a completion of the task.

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

storing information related to the completed task in a local database.

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

predicting an amount of time for the selected helping node to complete the task;

comparing the predicted amount of time to an actual amount of time for the selected helping node to complete the task; and

determining a degree of confidence associated with the selected helping node based on the comparison.

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; and

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

receiving a request from a requesting node in the network to assist in distributing a task of the requesting node;

evaluating a capability to perform the task of one or more helping nodes in the network;

selecting a helping node of the one or more helping nodes to perform the task based on the evaluated capability of the selected helping node; and

authorizing the distribution of the task from the requesting node to the selected helping node.

14. The apparatus according to claim 13, wherein the evaluating of the capability to perform the task comprises:

evaluating historical data relating to a particular helping node.

15. The apparatus according to claim 14, wherein the historical data includes one or more of:

information relating to a previous task performed by the particular helping node, an indication of success or failure of the previous task, and a degree of confidence associated with the particular helping node.

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

storing the historical data in a local database; and

when evaluating the historical data relating to the particular helping node, accessing the historical data from the local database.

17. The apparatus according to claim 13, wherein the evaluating of the capability to perform the task comprises:

evaluating information specified in the received request.

18. The apparatus according to claim 17, wherein the information specified in the received request includes one or more of:

a period of time during which the task is to be performed, an indication of type of the task, a resource necessary to perform the task, and a network performance metric.

19. The apparatus according to claim 13, wherein the evaluating of the capability to perform the task comprises:

evaluating a network-based parameter relating to the network or a particular helping node.

20. The apparatus according to claim 13, wherein the evaluating of the capability to perform the task is performed by a Learning Machine-based algorithm.

21. The apparatus according to claim 13, wherein the authorizing of the distribution of the task comprises:

sending a message to the requesting node indicating an identity of the selected helping node.

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

receiving a message from the selected helping node indicating a completion of the task.

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

storing information related to the completed task in a local database.

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

predicting an amount of time for the selected helping node to complete the task;

comparing the predicted amount of time to an actual amount of time for the selected helping node to complete the task; and

determining a degree of confidence associated with the selected helping node based on the comparison.

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

receiving a request from a requesting node in a network to assist in distributing a task of the requesting node;

evaluating a capability to perform the task of one or more helping nodes in the network;

selecting a helping node of the one or more helping nodes to perform the task based on the evaluated capability of the selected helping node; and

authorizing the distribution of the task from the requesting node to the selected helping node.