Improving software defined networking controller availability using machine learning techniques

Patent metadata

Field	Value
Publication number	US-2023015709-A1
Application number	US-201917756907-A
Country	US
Kind code	A1
Filing date	Dec 5, 2019
Priority date	Dec 5, 2019
Publication date	Jan 19, 2023
Grant date	—

Abstract

A method of managing a controller of a software defined networking (SDN) network is implemented by a computing device in the SDN network. The method includes receiving status information for the controller, receiving usage information for the operating environment, generating at least one failure prediction for the controller based on the received status information, and outputting prediction information for the at least one failure prediction.

First claim

1 . A method of managing a controller of a software defined networking (SDN) network implemented by a computing device in the SDN network, the method comprising:
receiving status information for the controller; receiving usage information for an operating environment; generating at least one failure prediction for the controller based on the received status information, the usage information of the operating environment, historic status information of the controller, and historic usage information of the operating environment; and outputting prediction information for the at least one failure prediction, wherein the prediction information includes a probability of failure over a given time period and a root cause for failure.

2 . The method of claim 1 , further comprising:
sending the prediction information to any one or more of a correction unit, an SDN controller or a data plane node (DPN) to implement a corrective action for the at least one failure prediction.

3 . The method of claim 1 , further comprising:
determining whether the at least one failure prediction exceeds a configured threshold.

4 . The method of claim 1 , wherein the status information for the controller and the usage information for the operating environment is received from a monitor.

5 . The method of claim 1 , wherein the status information for the controller includes internal packet processing queue sizes.

6 . The method of claim 1 , wherein the usage information for the operating environment includes any one or more of memory, processor, and network resource usage by the controller, and memory, processor, and network usage for the computing device.

7 . The method of claim 1 , wherein the at least one failure prediction is generated by a machine learning model trained on historic status information of the controller and historic usage information of the operating environment.

8 . A non-transitory machine-readable storage medium comprising computer program code which, when executed by a computer carries out managing of a controller of a software defined networking (SDN) network implemented by a computing device in the SDN network by performing operations comprising:
receiving status information for the controller; receiving usage information for an operating environment; generating at least one failure prediction for the controller based on the received status information, the usage information of the operating environment, historic status information of the controller, and historic usage information of the operating environment; and outputting prediction information for the at least one failure prediction, wherein the prediction information includes a probability of failure over a given time period and a root cause for failure.

9 . A computing device for managing a controller of a software defined networking (SDN) network implemented by the computing device in the SDN network, the computing device comprising:
a set of processors; and a non-transitory machine-readable medium having stored therein a prediction unit, the set of processors to execute the prediction unit to: receive status information for the controller; receive usage information for an operating environment; generate at least one failure prediction for the controller based on the received status information, the usage information of the operating environment, historic status information of the controller, and historic usage information of the operating environment; and output prediction information for the at least one failure prediction, wherein the prediction information includes a probability of failure over a given time period and a root cause for failure.

10 . (canceled)

11 . The non-transitory machine-readable storage medium of claim 8 , wherein the computer program code further carries out performing of operations comprising:
sending the prediction information to any one or more of a correction unit, an SDN controller or a data plane node (DPN) to implement a corrective action for the at least one failure prediction.

12 . The non-transitory machine-readable storage medium of claim 8 , wherein the computer program code further carries out performing of operations comprising:
determining whether the at least one failure prediction exceeds a configured threshold.

13 . The non-transitory machine-readable storage medium of claim 8 , wherein the status information for the controller and the usage information for the operating environment is received from a monitor.

14 . The non-transitory machine-readable storage medium of claim 8 , wherein the status information for the controller includes internal packet processing queue sizes.

15 . The non-transitory machine-readable storage medium of claim 8 , wherein the usage information for the operating environment includes any one or more of memory, processor, and network resource usage by the controller, and memory, processor, and network usage for the computing device.

16 . The non-transitory machine-readable storage medium of claim 8 , wherein the at least one failure prediction is generated by a machine learning model trained on historic status information of the controller and historic usage information of the operating environment.

17 . The computing device of claim 9 , further to:
send the prediction information to any one or more of a correction unit, an SDN controller or a data plane node (DPN) to implement a corrective action for the at least one failure prediction.

18 . The computing device of claim 9 , further to:
determine whether the at least one failure prediction exceeds a configured threshold.

19 . The computing device of claim 9 , wherein the status information for the controller and the usage information for the operating environment is received from a monitor.

20 . The computing device of claim 9 , wherein the status information for the controller includes internal packet processing queue sizes.

21 . The computing device of claim 9 , wherein the usage information for the operating environment includes any one or more of memory, processor, and network resource usage by the controller, and memory, processor, and network usage for the computing device.

Assignees

• Ericsson Telefon Ab L M

Inventors

• Bisht Ashutosh
• Perumalla Siva Kumar
• Agarwal Aakash
• Bhowmik Tanmoy
• Gopalakrishnan Hema
• Kandagal Hanamantagoud V

Classifications

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• H04L47/127 Primary

  by using congestion prediction · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/08

  Learning methods · CPC title

• H04L41/06 Primary

  Management of faults, events, alarms or notifications · CPC title