Proactive operations, administration, and maintenance systems and methods in networks using data analytics

Patent metadata

Field	Value
Publication number	US-9628340-B2
Application number	US-201414270011-A
Country	US
Kind code	B2
Filing date	May 5, 2014
Priority date	May 5, 2014
Publication date	Apr 18, 2017
Grant date	Apr 18, 2017

Abstract

A computer-implemented method, a system, and a network include receiving network data from a network and non-network sourced data from one or more external sources relative to the network; performing data mining on the network data and the non-network sourced data; developing a predictive analytics model based on the data mining; and performing predictive analytics on the network data and the non-network sourced data using the predictive analytics model to detect likely future failures in the network. The network can include a Software Defined Network (SDN) operating at any of Layers 0, 1, 2 and/or 3.

First claim

What is claimed is:

1. A computer-implemented method, comprising:
receiving network data from a network and non-network sourced data from one or more external sources relative to the network, wherein the non-network sourced data is obtained separately from the network, and wherein the network data is obtained from a Software Defined Network (SDN) controller that consolidates the network data from network elements operating at various Layers and from different equipment vendors;
performing data mining on the network data and the non-network sourced data to identify normal operation and abnormal operation in the network;
developing a predictive analytics model based on the data mining; and
performing predictive analytics on the network data and the non-network sourced data using the predictive analytics model to detect likely future failures in the network based on the normal operation and the abnormal operation in the network and associated trends, patterns, or relationships determined in the predictive analytics model using the network data and the non-network sourced data.

2. The computer-implemented method of claim 1 , wherein the
SDN controller provides the network data via an Application Programming Interface (API).

3. The computer-implemented method of claim 1 , further comprising:
receiving a notification from the predictive analytics that a component in the network is likely to fail; and
performing a proactive maintenance activity on the component.

4. The computer-implemented method of claim 1 , further comprising:
continually updating the data mining and the predictive analytics model based on ongoing occurrences of failures and data associated therewith.

5. The computer-implemented method of claim 1 , wherein the network data and the non-network data are each classified as either analog or digital and either internal to the network or external to the network and prioritized.

6. The computer-implemented method of claim 5 , wherein the network data comprises network Operations, Administration, and Maintenance (OAM) data collected by the network, and the non-network data comprises data collected from external sources relative to the network.

7. A system, comprising:
a network interface, a data store, and a processor, each communicatively coupled; and
memory storing instructions that, when executed, cause the processor to:
receive, via the network interface, network data from a network and non-network sourced data from one or more external sources relative to the network, wherein the non-network sourced data is obtained separately from the network, and wherein the network data is obtained from a Software Defined Network (SDN) controller that consolidates the network data from network elements operating at various Layers and from different equipment vendors;
perform data mining on the network data and the non-network sourced data to identify normal operation and abnormal operation in the network;
develop a predictive analytics model based on the data mining; and
perform predictive analytics on the network data and the non-network sourced data using the predictive analytics model to detect likely future failures in the network based on the normal operation and the abnormal operation in the network and associated trends, patterns, or relationships determined in the predictive analytics model using the network data and the non-network sourced data.

8. The system of claim 7 , wherein the network data is received from the SDN controller via an Application Programming Interface (API).

9. The system of claim 7 , wherein, responsive to a failure prediction by the predictive analytics, a notification is provided when a component in the network is likely to fail to alert an operator for proactive maintenance activity on the component.

10. The system of claim 7 , wherein the memory storing instructions that, when executed, cause the processor to:
continually update the data mining and the predictive analytics model based on ongoing occurrences of failures and data associated therewith.

11. The system of claim 7 , wherein the network data and the non-network data are each classified as either analog or digital and either internal to the network or external to the network and prioritized.

12. The system of claim 11 , wherein the network data comprises network Operations, Administration, and Maintenance (OAM) data collected by the network, and the non-network data comprises data collected from external sources relative to the network.

13. A network, comprising:
a plurality of network elements communicatively coupled and operating at any of Layers 0, 1, 2 and/or 3, wherein two or more of the plurality of network elements are from different equipment vendors; and
a Software Defined Network (SDN) controller communicatively coupled to one or more of the plurality of network elements, wherein the SDN controller consolidates the network data from the plurality of network elements operating at the various Layers and from the different equipment vendors; and
a server communicatively coupled to the SDN controller, wherein the server comprises a processor and memory storing instructions that, when executed, cause the processor to:
receive, via a network interface, network data from a network and non-network sourced data from one or more external sources relative to the network, wherein the non-network sourced data is obtained separately from the network, and wherein the network data is obtained from the SDN controller;
perform data mining on the network data and the non-network sourced data to identify normal operation and abnormal operation in the network;
develop a predictive analytics model based on the data mining;
perform predictive analytics on the network data and the non-network sourced data using the predictive analytics model to detect likely future failures in the network; and
locate spares throughout the network based on the likely future failures.

14. The network of claim 13 , wherein the network data is received from the SDN controller via an Application Programming Interface (API) on the SDN controller.

15. The network of claim 13 , wherein, responsive to a failure prediction by the predictive analytics, a notification is provided when a component in the network is likely to fail to alert an operator for proactive maintenance activity on the component.

16. The network of claim 13 , wherein the memory storing instructions that, when executed, cause the processor to:
continually update the data mining and the predictive analytics model based on ongoing occurrences of failures and data associated therewith.

17. The network of claim 13 , wherein the network data and the non-network data are each classified as either analog or digital and either internal to the network or external to the network and prioritized.

18. The network of claim 17 , wherein the network data comprises network Operations, Administration, and Maintenance (OAM) data collected by the network, and the non-network data comprises data collected from external sources relative to the network.

Assignees

• Blair Loudon Thomas
• Ciena Corp

Inventors

• Blair Loudon Thomas

Classifications

• G06F11/079 Primary

  Root cause analysis, i.e. error or fault diagnosis (in a hardware test environment G06F11/22; in a software test environment G06F11/36) · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N7/005

  Physics · mapped topic

• H04L41/147 Primary

  for predicting network behaviour · CPC title

• H04L41/16

  using machine learning or artificial intelligence · CPC title