公开(公告)号：US12170608B2

公开(公告)日：2024-12-17

申请号：US17808066

申请日：2022-06-21

Applicant: Juniper Networks, Inc.

Inventor： Sanjeev Kumar Mishra ,  Sabyasachi Mukhopadhyay ,  Shivaprasad Gali ,  Hsiuyen Tsai

IPC: H04L45/42 ,  H04L41/16 ,  H04L45/02 ,  H04L45/12

Abstract: Techniques are described for predicting future behavior of links in a network and generating dynamic thresholds for link metrics for use in path selection. In one example, a computing system receives historical values of a link metric for links of a network. The computing system executes a machine learning system which processes the historical values of the link metric to generate: (1) a predicted future value of the link metric for each link; and (2) a threshold for the link metric indicating whether the predicted future value for each link is anomalous. The computing system computes a path based on the predicted future values of the link metric and the threshold for the link metric. The computing system provisions the computed path, thereby enabling a network device to forward network traffic along the computed path.

公开(公告)号：US20210409306A1

公开(公告)日：2021-12-30

申请号：US17247891

申请日：2020-12-29

Applicant: Juniper Networks, Inc.

Inventor： Ankur Neog ,  Sanjeev Kumar Mishra ,  Santosh Kottanipral Mathews

IPC: H04L12/721 ,  H04L12/751 ,  H04L12/707 ,  H04L12/703 ,  H04L12/24 ,  G06K9/62 ,  G06N20/00

Abstract: This disclosure describes techniques that include determining the health of one or more routing engines included within a router. In one example, this disclosure describes a method that includes performing, by a first routing engine included within a router, routing operations, wherein the router includes a plurality of routing engines, including the first routing engine and a second routing engine; receiving, by a computing system, data including health indicators associated with the first routing engine; applying, by the computing system, a machine learning model to the data to determine, from the health indicators, a health status of the first routing engine, wherein the machine learning model has been trained to identify the health status from the health indicators; and determining, by the computing system and based on the health status of the first routing engine, whether to switch routing operations to the second routing engine from the first routing engine.

公开(公告)号：US11563671B2

公开(公告)日：2023-01-24

申请号：US17247891

申请日：2020-12-29

Applicant: Juniper Networks, Inc.

Inventor： Ankur Neog ,  Sanjeev Kumar Mishra ,  Santosh Kottanipral Mathews

IPC: H04L45/12 ,  H04L45/02 ,  H04L45/00 ,  G06N20/00 ,  H04L41/0604 ,  G06K9/62 ,  H04L45/28 ,  G06N20/10 ,  G06N5/04 ,  G06F11/30

Abstract: This disclosure describes techniques that include determining the health of one or more routing engines included within a router. In one example, this disclosure describes a method that includes performing, by a first routing engine included within a router, routing operations, wherein the router includes a plurality of routing engines, including the first routing engine and a second routing engine; receiving, by a computing system, data including health indicators associated with the first routing engine; applying, by the computing system, a machine learning model to the data to determine, from the health indicators, a health status of the first routing engine, wherein the machine learning model has been trained to identify the health status from the health indicators; and determining, by the computing system and based on the health status of the first routing engine, whether to switch routing operations to the second routing engine from the first routing engine.

公开(公告)号：US20230412488A1

公开(公告)日：2023-12-21

申请号：US17808066

申请日：2022-06-21

Applicant: Juniper Networks, Inc.

Inventor： Sanjeev Kumar Mishra ,  Sabyasachi Mukhopadhyay ,  Shivaprasad Gali ,  Hsiuyen Tsai

IPC: H04L45/12 ,  H04L45/02

CPC classification number: H04L45/123 ,  H04L45/124 ,  H04L45/08

Abstract: Techniques are described for predicting future behavior of links in a network and generating dynamic thresholds for link metrics for use in path selection. In one example, a computing system receives historical values of a link metric for links of a network. The computing system executes a machine learning system which processes the historical values of the link metric to generate: (1) a predicted future value of the link metric for each link; and (2) a threshold for the link metric indicating whether the predicted future value for each link is anomalous. The computing system computes a path based on the predicted future values of the link metric and the threshold for the link metric. The computing system provisions the computed path, thereby enabling a network device to forward network traffic along the computed path.

公开(公告)号：US20230214304A1

公开(公告)日：2023-07-06

申请号：US17646559

申请日：2021-12-30

Applicant: Juniper Networks, Inc.

Inventor： Sanjeev Kumar Mishra ,  Ankur Neog ,  Ramakrishnan Rajagopalan ,  Ravindran Thangarajah ,  Shamantha Krishna K G

IPC: G06F11/273 ,  G06F11/267 ,  G06F11/27

CPC classification number: G06F11/2733 ,  G06F11/267 ,  G06F11/27

Abstract: In general, a device comprising a processor and a memory may be configured to perform various aspects of the techniques described in this disclosure. The processor may conduct, based on configuration parameters, each of a plurality of simulation iterations within the test environment to collect a corresponding plurality of simulation datasets representative of operating states of the network device. The processor may perform a regression analysis with respect to each of the plurality of configuration parameters and each of the plurality of simulation datasets to generate a light weight model representative of the network device that predicts an operating state of the network device. The processor may output the light weight model for use in a computing resource restricted network device to enable prediction of the operating state of the computing resource restricted network device when configured with the configuration parameters. The memory may store the light weight model.

公开(公告)号：US11797408B2

公开(公告)日：2023-10-24

申请号：US17646559

申请日：2021-12-30

Applicant: Juniper Networks, Inc.

Inventor： Sanjeev Kumar Mishra ,  Ankur Neog ,  Ramakrishnan Rajagopalan ,  Ravindran Thangarajah ,  Shamantha Krishna K G

IPC: G06F11/273 ,  G06F11/27 ,  G06F11/267

CPC classification number: G06F11/2733 ,  G06F11/267 ,  G06F11/27

Abstract: In general, a device comprising a processor and a memory may be configured to perform various aspects of the techniques described in this disclosure. The processor may conduct, based on configuration parameters, each of a plurality of simulation iterations within the test environment to collect a corresponding plurality of simulation datasets representative of operating states of the network device. The processor may perform a regression analysis with respect to each of the plurality of configuration parameters and each of the plurality of simulation datasets to generate a light weight model representative of the network device that predicts an operating state of the network device. The processor may output the light weight model for use in a computing resource restricted network device to enable prediction of the operating state of the computing resource restricted network device when configured with the configuration parameters. The memory may store the light weight model.