SYSTEM AND METHOD FOR OBSERVING AND CONTROLLING A PROGRAMMABLE NETWORK USING CROSS NETWORK LEARNING

• US 20150142962A1
• Filed: 10/21/2014
• Published: 05/21/2015
• Est. Priority Date: 10/21/2013
• Status: Abandoned Application

• Current Assignee: Nyansa, Inc. (Broadcom, Inc.)
• Original Assignee: Nyansa, Inc. (Broadcom, Inc.)
• Inventors: Srinivas, Anand, Barry, Richard, Ankumah, Abraham, Kan, Daniel
• Application Number:
  US14/520,257
• Publication Number:
  US 20150142962A1
• Time in Patent Office: Days
• US Class Current: 709/224
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 41/046 comprising network management agents or mobile agents therefor
• CPC Class Codes: H04L 41/0816 the condition being an adaptation, e.g. in response to network events
• CPC Class Codes: H04L 41/0823 characterised by the purposes of a change of settings, e.g. optimising configuration for enhancing reliability for optimising operational conditions of wireless networks H04W24/02
• CPC Class Codes: H04L 41/085 Retrieval of network configuration; Tracking network configuration history
• CPC Class Codes: H04L 41/0893 Assignment of logical groups to network elements
• CPC Class Codes: H04L 41/0894 Policy-based network configuration management
• CPC Class Codes: H04L 41/0895 Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
• CPC Class Codes: H04L 41/145 involving simulating, designing, planning or modelling of a network
• 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 41/40 using virtualisation of network functions or resources, e.g. SDN or NFV entities
• CPC Class Codes: H04L 43/04 Processing captured monitoring data, e.g. for logfile generation
• CPC Class Codes: H04L 43/062 related to network traffic
• CPC Class Codes: H04L 43/0829 Packet loss
• CPC Class Codes: H04L 43/0876 Network utilisation, e.g. volume of load or congestion level
• CPC Class Codes: H04L 43/12 Network monitoring probes
• CPC Class Codes: H04L 43/20 the monitoring system or the monitored elements being virtualised, abstracted or software-defined entities, e.g. SDN or NFV

Abstract

A system and method for observing and controlling a programmable network via higher layer attributes is disclosed. According to one embodiment, the system includes a plurality of network systems, and a remote network manager. The remote network manager is configured to connect over the Internet to the plurality of enterprise systems, a plurality of collectors, or combinations thereof. The remote network manager simultaneously and centrally analyzes a network condition of a plurality of network systems, learns a network pattern from a first network system of the plurality of network systems, and predicts a network behavior of a second network system of the plurality of network systems.

Claims

1. A system for monitoring a network comprising:

a plurality of network systems; and

a remote network manager comprising a network interface and configured to connect over the Internet to the plurality of enterprise systems, a plurality of collectors, or combinations thereof; and

wherein the remote network manager simultaneously and centrally analyzes a network condition of a plurality of network systems, learns a network pattern from a first network system of the plurality of network systems, and predicts a network behavior of a second network system of the plurality of network systems.

2. The system of claim 1, wherein the remote network manager is configured to predict performance of an application, a user, or a device based on observed characteristics of the network using network protocol level metrics and metadata.

3. The system of claim 1, wherein the network pattern is a protocol level metric of the network and metadata of network traffic data.

4. The system of claim 1, further comprising a programmable controller that controls at least some of the plurality of network elements, wherein the remote network manager controls the plurality of network elements via the programmable controller.

5. The system of claim 1, further comprising one or more collectors that are disposed in a network system of the plurality of network systems and configured to receive network traffic data from a plurality of network elements in the network system.

6. The system of claim 1, wherein network analysis is performed using metadata.

7. The system of claim 5, wherein the remote network manager or the one or more collectors are further configured to index the network enabling efficient search and retrieval of the metadata and learned network patterns.

8. The system of claim 5, wherein the one or more collectors are further configured to receive statistics about the network, topology information about the network, input from one or more enterprise systems, or combinations thereof.

9. The system of claim 1, wherein the remote network manager is disposed in a cloud and connected to the one or more collectors over the Internet.

10. The system of claim 5, further comprising a programmable network element disposed in the network system, wherein the remote network manager programs the programmable network element to configure the programmable network element to send filtered network traffic data to the one or more collectors.

11. The system of claim 5, further comprising a programmable network element disposed in the network system, wherein the one or more collectors program the programmable network element to configure the programmable network element to send filtered network traffic data to the one or more collectors.

12. The system of claim 10, wherein the remote network manager applies a control loop to determine whether a network control objective is met after programming the programmable network element.

13. The system of claim 1, wherein metadata is time-aligned with data received from one or more enterprise systems.

14. The system of claim 10, wherein the remote network manager affects a network policy by programming a programmable network element or a programmable controller with a control primitive.

15. The system of claim 14, wherein the control primitive includes an access control list (ACL), quality of service (QoS), rate limit settings, or combinations thereof.

16. The system of claim 14, wherein the remote network manager maintains a relationship between a network policy and the control primitive in a database.

17. The system of claim 1, wherein the one or more collectors are programmable, and wherein the remote network manager programs the one or more collectors to collect different type of metadata.

18. The system of claim 1, wherein the remote network manager de-duplicates the metadata received from the one or more collectors.

19. The system of claim 1, wherein the remote network manager calculates a quality of experience of a user, an application, or a device, based on the metadata received from the one or more collectors.

20. A system for monitoring a network comprising:

a plurality of network systems; and

a remote network manager comprising a network interface and configured to connect over the Internet to the plurality of enterprise systems, a plurality of collectors, or combinations thereof; and

wherein the remote network manager simultaneously and centrally analyzes a network condition of a plurality of network systems, learns a network pattern from a first network system of the plurality of network systems, and applies a network policy to a second network system of the plurality of network systems.

21. The system of claim 20, wherein the network policy is controlling one or more of applications, users, or devices of the network.

22. A method for monitoring a network comprising:

providing a plurality of network systems;

providing a remote network manager comprising a network interface and configured to connect over the Internet to the plurality of enterprise systems, a plurality of collectors, or combinations thereof;

simultaneously and centrally analyzing a network condition of a plurality of network systems;

learning a network pattern from a first network system of the plurality of network systems; and

applying a network policy to a second network system of the plurality of network systems.