DETERMINISTIC CONTROL LOOP SCHEDULING
    196.
    发明申请

    公开(公告)号:US20170272315A1

    公开(公告)日:2017-09-21

    申请号:US15611836

    申请日:2017-06-02

    CPC classification number: H04L41/0803 H04L41/04

    Abstract: In one embodiment, a scheduling device in a network receives routing metrics regarding a network path between a device controller and a networked device. The scheduling device also receives controller metrics for the device controller. The scheduling device determines time costs associated with the network path and one or more control operations performed by the device controller, based on the routing and controller metrics. The scheduling device generates a communication schedule based on the time costs and instructs the device controller and the networked device to use the communication schedule.

    DETECTING OSCILLATION ANOMALIES IN A MESH NETWORK USING MACHINE LEARNING
    199.
    发明申请
    DETECTING OSCILLATION ANOMALIES IN A MESH NETWORK USING MACHINE LEARNING 审中-公开
    使用机器学习检测网状网络中的振荡异常

    公开(公告)号:US20170078170A1

    公开(公告)日:2017-03-16

    申请号:US14855492

    申请日:2015-09-16

    Abstract: In one embodiment, a device in a network receives metrics regarding a node in the network. The device uses the metrics as input to a machine learning model. The device determines, using the machine learning model and based on the metrics, an indication of abnormality of the node oscillating between using a plurality of different routing parents in the network. The device provides a results notification based on the indication of abnormality of the node oscillating between using the plurality of different routing parents.

    Abstract translation: 在一个实施例中,网络中的设备接收关于网络中的节点的度量。 该设备使用度量作为机器学习模型的输入。 该设备使用机器学习模型并且基于度量来确定节点在使用网络中的多个不同路由父节点之间振荡的异常的指示。 该设备基于在使用多个不同路由父节点之间振荡的节点的异常的指示来提供结果通知。

Patent Agency Ranking