DETECTING NETWORK FAILURE USING A MACHINE LEARNING MODEL

    公开(公告)号:US20250007771A1

    公开(公告)日:2025-01-02

    申请号:US18343360

    申请日:2023-06-28

    Abstract: A network management system includes a memory configured to store a machine learning model and processing circuitry in communication with the memory. The processing circuitry is configured to receive network data from a plurality of network devices of an internal network managed by the network management system. The internal network may be connected to an external network isolated from the network management system. Additionally, the processing circuitry is configured apply the machine learning model to detect, based on the network data, a network failure within the external network and perform a corrective action to remediate the network failure within the external network.

    WIDE AREA NETWORK LINK BANDWIDTH MONITORING

    公开(公告)号:US20250007803A1

    公开(公告)日:2025-01-02

    申请号:US18346009

    申请日:2023-06-30

    Abstract: A network management system instructs a first network device to obtain one or more parameters related to a Wireless Area Network (WAN) link between the first network device and a second network device. The network management system executes a machine learning system configured to apply, to the one or more parameters related to the WAN link, a machine learning model trained with parameters of links to predict bandwidths of the links, to predict a maximum bandwidth of the WAN link. The network management system outputs an indication of the predicted maximum bandwidth of the WAN link.

    NETWORK DEVICE UPGRADE BASED GROUP PRIORITY
    3.
    发明公开

    公开(公告)号:US20240007350A1

    公开(公告)日:2024-01-04

    申请号:US18066626

    申请日:2022-12-15

    CPC classification number: H04L41/082 H04L41/0894 H04L43/062

    Abstract: Techniques are disclosed for identifying sets of network devices to which to deploy a software upgrade based on an importance to the network of each network device. For example, a network system obtains information identifying a number of instances of an application associated with network traffic forwarded by each network device of a plurality of network devices. The instances of the application are executed by client devices serviced by each network device in forwarding the network traffic. The network system assigns each network device to different upgrade groups based on the number of instances of the application, each upgrade group associated with a different relative priority. The network system deploys a software upgrade to each network device according to a priority of the respective upgrade group relative to a priority of the other upgrade groups.

    Network device upgrade based group priority

    公开(公告)号:US12107726B2

    公开(公告)日:2024-10-01

    申请号:US18066626

    申请日:2022-12-15

    CPC classification number: H04L41/082 H04L41/0894 H04L43/062

    Abstract: Techniques are disclosed for identifying sets of network devices to which to deploy a software upgrade based on an importance to the network of each network device. For example, a network system obtains information identifying a number of instances of an application associated with network traffic forwarded by each network device of a plurality of network devices. The instances of the application are executed by client devices serviced by each network device in forwarding the network traffic. The network system assigns each network device to different upgrade groups based on the number of instances of the application, each upgrade group associated with a different relative priority. The network system deploys a software upgrade to each network device according to a priority of the respective upgrade group relative to a priority of the other upgrade groups.

    NETWORK DEVICE UPGRADE BASED GROUP PRIORITY
    5.
    发明公开

    公开(公告)号:US20240356803A1

    公开(公告)日:2024-10-24

    申请号:US18759463

    申请日:2024-06-28

    CPC classification number: H04L41/082 H04L41/0894 H04L43/062

    Abstract: Techniques are disclosed for identifying sets of network devices to which to deploy a software upgrade based on an importance to the network of each network device. For example, a network system obtains information identifying a number of instances of an application associated with network traffic forwarded by each network device of a plurality of network devices. The instances of the application are executed by client devices serviced by each network device in forwarding the network traffic. The network system assigns each network device to different upgrade groups based on the number of instances of the application, each upgrade group associated with a different relative priority. The network system deploys a software upgrade to each network device according to a priority of the respective upgrade group relative to a priority of the other upgrade groups.

    Network device upgrade based group priority

    公开(公告)号:US12058000B2

    公开(公告)日:2024-08-06

    申请号:US18066626

    申请日:2022-12-15

    CPC classification number: H04L41/082 H04L41/0894 H04L43/062

    Abstract: Techniques are disclosed for identifying sets of network devices to which to deploy a software upgrade based on an importance to the network of each network device. For example, a network system obtains information identifying a number of instances of an application associated with network traffic forwarded by each network device of a plurality of network devices. The instances of the application are executed by client devices serviced by each network device in forwarding the network traffic. The network system assigns each network device to different upgrade groups based on the number of instances of the application, each upgrade group associated with a different relative priority. The network system deploys a software upgrade to each network device according to a priority of the respective upgrade group relative to a priority of the other upgrade groups.

    SOFTWARE IMAGE SCORE FOR RECOMMENDING SOFTWARE IMAGES

    公开(公告)号:US20240004628A1

    公开(公告)日:2024-01-04

    申请号:US18147430

    申请日:2022-12-28

    CPC classification number: G06F8/63 G06F16/24578 H04L67/30

    Abstract: Techniques are disclosed for recommending particular versions of a software image for installation on a network device. In one example, a cloud-based Wide-Area Network (WAN) assurance system determines, for a first entity, entities having similar entity profiles as an entity profile of the first entity. The system obtains historical information, such as historical performance information, for network devices of the entities having similar entity profiles as the entity profile of the first entity. The system computes, based on the historical information, software image scores for software images used by the network devices. The system outputs, for display, an indication specifying a recommended software image to install on a first network device of the first entity, the recommended software image selected based on the software image scores for the software images used by the network devices.

Patent Agency Ranking