Patent · US Active

Network configuration for software defined network via machine learning

US10614376B2 · kind B2 · utility

2Cited by
2References
18Claims
0Family size

Assignee

Inventor

Key dates

Filing dateJul 28, 2016
Grant dateApr 7, 2020
Priority date
Expiry dateAug 4, 2036

Classification

  • Technology area (CPC H)Electricity
  • CPC primaryH04L41/40
  • WIPO fieldDigital communication
  • WIPO sectorElectrical engineering

Abstract

A method, computer-readable medium, and apparatus for configuring a software defined network via machine learning are disclosed. For example, a method may generate a first policy for a first service by a first policy model using machine learning for processing first data of the first service, the first service being implement by at least one first virtual component of a software defined network, determine whether the first policy is to be applied to a second service, the second service being implement by at least one second virtual component of the software defined network, apply the first policy to the second service when the first policy is deemed to be applicable to the second service, generate a second policy for the second service, and implement the second policy in the second service, wherein the first service and the second service are provided by a single service provider.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.