Juniper Networks, Inc.

Cisco Technology, Inc.

Monimoy Deb Purkayastha

Madhukar Mulpuri

Patrick Timmons

Kaushik Adesh Agrawal

Ashish Kumar Mishra

Patrick John Melampy

Ajit Krishna Patankar

Narender Singh Pal

Kihwan Han

A device may receive network traffic data that includes network traffic packet sizes, and may transform the network traffic data into transformed data. The device may process the transformed data, with a machine learning model, to generate an embedding, and may obtain a similarity metric for the embedding. The device may create a graph with nodes and edges based on the embedding and the similarity metric, and may process the graph, with a community detection model, to identify network traffic categories for the network traffic data. The device may perform one or more actions based on the network traffic categories.

Utilizing machine learning models for network traffic categorization

Local call information data sets are obtained for each of a plurality of devices engaged in a call, the local call information data sets comprising call attributes and associated metadata. Call signaling is mapped by correlating at least one attribute pertaining to the call in each of the local call information data sets. Global end-to-end call state machine is generated subsequent to mapping of call signaling. The global end-to-end call state machine includes a plurality of global states. Each global state represents a local state of each device along with state transition indicating change in the local state of at least one device.

End-to-end call tracing

A method includes receiving configuration data for configuring network devices; generating remote procedure calls (RPCs) for configuring the network devices, which include provisioning and reverse provisioning RPCs, where each reverse provisioning RPC reverse provisions a particular pseudowire; providing to the network devices the provisioning RPCs; determining a success with respect to each of the provisioning RPCs, where the success indicates that all endpoints of a pseudowire have been successfully configured; providing the reverse provisioning RPCs to the network devices, when it is determined that the success has not been achieved; and storing an indication of success when it is determined that the success has been achieved with respect to the provisioning RPCs.

NETCONF-enabled provisioning in rollback agnostic environment

Growing community of inventors

Bengaluru, India

Monimoy Deb Purkayastha