US 11,855,872 B2
Methods, systems, and computer readable media for network traffic generation using machine learning
Winston Wencheng Liu, Woodland Hills, CA (US); Dan Mihailescu, Mogosoaia (RO); Razvan Ionut Stan, Agoura Hills, CA (US); and Thomas Ameling, Woodland Hills, CA (US)
Assigned to KEYSIGHT TECHNOLOGIES, INC., Santa Rosa, CA (US)
Filed by Keysight Technologies, Inc., Santa Rosa, CA (US)
Filed on Jul. 6, 2021, as Appl. No. 17/368,439.
Claims priority of application No. a 2021 00386 (RO), filed on Jul. 2, 2021.
Prior Publication US 2023/0006912 A1, Jan. 5, 2023
Prior Publication US 2023/0171177 A9, Jun. 1, 2023
Int. Cl. H04L 43/50 (2022.01); G06N 3/042 (2023.01)
CPC H04L 43/50 (2013.01) [G06N 3/042 (2023.01)] 20 Claims
OG exemplary drawing
 
1. A method for network traffic generation using machine learning, the method comprising:
collecting first traffic from a production data center environment, wherein at least a portion of the first traffic comprises live computer network traffic transiting the production data center environment;
collecting second traffic from an emulated data center testbed device, wherein at least a portion of the second traffic comprises testbed traffic that transits an emulated data center switching fabric of the emulated data center testbed device;
training a traffic generation inference engine using the first traffic and the second traffic; and
generating, using the traffic generation inference engine, test traffic to test or stimulate a network system under test (SUT).