Detecting transient vs. perpetual network behavioral patterns using machine learning

    公开(公告)号:US10547518B2

    公开(公告)日:2020-01-28

    申请号:US15880600

    申请日:2018-01-26

    Abstract: In one embodiment, a network assurance service that monitors a network detects a pattern of network measurements from the network that are associated with a particular network problem. The network assurance service tracks characteristics of the detected pattern over time. The network assurance service uses the tracked characteristics of the detected pattern over time as input to a machine learning-based pattern analyzer. The pattern analyzer is configured to determine whether the detected pattern is a perpetual or transient pattern in the network, and the pattern analyzer is further configured to detect anomalies in the characteristics of the pattern. The network assurance service initiates a change to the network based on an output of the machine learning-based pattern analyzer.

    Proactive roaming handshakes based on mobility graphs

    公开(公告)号:US10285108B1

    公开(公告)日:2019-05-07

    申请号:US15782197

    申请日:2017-10-12

    Abstract: In one embodiment, a service maintains a mobility path graph that represents roaming transitions between wireless access points in a network by one or more client devices in the network. The service identifies, using the mobility path graph, one of the wireless access points in the network to which a particular client device is predicted to roam. The service performs, in advance of the particular client device initiating roaming to the one or more wireless access points, one or more roaming handshakes on behalf of the particular client device and with respect to the wireless access point to which the particular client device is predicted to roam. The service sends handshake data from the performed one or more roaming handshakes to the identified access point to which the particular client device is predicted to roam.

    PROACTIVE ROAMING HANDSHAKES BASED ON MOBILITY GRAPHS

    公开(公告)号:US20190116539A1

    公开(公告)日:2019-04-18

    申请号:US15782197

    申请日:2017-10-12

    Abstract: In one embodiment, a service maintains a mobility path graph that represents roaming transitions between wireless access points in a network by one or more client devices in the network. The service identifies, using the mobility path graph, one of the wireless access points in the network to which a particular client device is predicted to roam. The service performs, in advance of the particular client device initiating roaming to the one or more wireless access points, one or more roaming handshakes on behalf of the particular client device and with respect to the wireless access point to which the particular client device is predicted to roam. The service sends handshake data from the performed one or more roaming handshakes to the identified access point to which the particular client device is predicted to roam.

    ACTIVELY LEARNING POPS TO PROBE AND PROBING FREQUENCY TO MAXIMIZE APPLICATION EXPERIENCE PREDICTIONS

    公开(公告)号:US20230327971A1

    公开(公告)日:2023-10-12

    申请号:US17714483

    申请日:2022-04-06

    CPC classification number: H04L43/12 H04L47/2475

    Abstract: In one embodiment, a device computes, for each of a set of points of presence (PoPs) via which traffic for an online application can be sent from a location, application experience metrics predicted for the application over time. The device assigns, for each of the set of PoPs, weights to different time periods, based on measures of uncertainty associated with the predicted application experience metrics. The device generates, based on the weights assigned to the different time periods for each of the set of PoPs, schedules for probing network paths connecting the location to the online application via those PoPs. The device causes the network paths to be probed in accordance with their schedules. Results of this probing are used to select a particular PoP from among the set of PoPs via which traffic for the online application should be sent from the location during a certain time period.

Patent Agency Ranking