In some embodiments, a data-secure sensor system includes one or more processors configured to receive sensor data (e.g., image data, audio data, etc.) and generate descriptive data based on the sensor data that corresponds to a physical area that corresponds to information about identified objects or activity in physical area, an input/output (I/O) port, and an I/O choke communicatively coupled between the one or more processors and the I/O port, the I/O choke configured to limit a communication bandwidth of the I/O port to a maximum data rate. The one or more processors can be configured to prevent the sensor data from being accessible via any external port of the data-secure camera system, including the I/O port, and allow the descriptive data to be accessible via the I/O port.

The present invention relates to IoT devices existing in a deployed ecosystem. The various computers in the deployed ecosystem are able to respond to requests from a device directly associated with it in a particular hierarchy, or it may seek a response to the request from a high order logic/data source (parent). The logic/data source parent may then repeat the understanding process to either provide the necessary response to the logic/data source child who then replies to the device or it will again ask a parent logic/data sources for the appropriate response. This architecture allows for a single device to make one request to a single known source and potentially get a response back from the entire ecosystem of distributed servers.

The present disclosure illustrates a routing system with learning functions and a routing method thereof. By detecting a raw packet's packet header and an entry port receiving the raw packet, a routing message is queried from a path table by the packet header and the entry port. When there is not the routing message, the raw packet is routed by a kernel and the routing result is recorded in the path table to be the routing message. When there is the routing message, the packet header of the raw packet is replaced with a modified packet header recorded in the routing message, to form a modified packet, and the modified packet is transmitted from the transmission port recorded in the routing message, to achieve the technical effect of improving the routing performance for the packets with the same packet headers and the same entry ports.

In one embodiment, a device receives, via a user interface, an indication of what is considered noise within a time series of a path performance metric. The device selects, based on the indication, a particular denoising filter to be applied to telemetry data obtained from one or more network paths regarding the path performance metric. The device forms model training data by applying the particular denoising filter to telemetry data obtained from one or more network paths regarding the path performance metric. The device trains, using the model training data, a prediction model to predict when a given network path will experience a failure condition.

In one embodiment, a device computes states of a network path associated with an online application by representing time series of telemetry data regarding the network path as discrete values. The device generates state trajectories from the states of the network path computed by the device. The device selects one or more sub-sequences of the state trajectories based on prediction performance metrics that represent how well the one or more sub-sequences are able to predict a failure condition of the network path. The device causes a networking entity to use the one or more sub-sequences of the state trajectories to perform predictive routing for the network path.

The present disclosure provides a method and apparatus for learning a MAC address of a TRILL network. The method comprises: learning, by a routing bridge connected to an end system, a MAC address of the end system; encapsulating the MAC address in a link-state packet, sending the link-state packet to a neighbor routing bridge; after the neighbor routing bridge receives the link-state packet, judging whether the MAC address in the link-state packet is locally present; if not, learning the MAC address in the link-state packet and setting a local confidence to a confidence of the MAC address in the link-state packet; if yes, updating a confidence of a local MAC address to the confidence of the MAC address in the link-state packet, increasing the confidence of the MAC address in the link-state packet by 1, and sending the link-state packet to all neighbor routing bridges except a receiving end.

In one embodiment, a network element in a network receives one or more machine learning models configured to make an inference about the network. The network element requests, according to a predefined peering plan, telemetry attribute data from one or more peer network elements specified by the peering plan. The network element receives the telemetry attribute data from the one or more peer network elements. The network element makes, using the one or more machine learning models, an inference about the network based in part on the received telemetry attribute data.

In one embodiment, a device obtains quality of experience metrics for an online application. The device obtains network metrics for one or more network paths over which traffic for the online application was routed. The device identifies a lack of correlation between the quality of experience metrics for the online application and the network metrics for the one or more network paths over which traffic for the online application was routed. The device disables, based on the lack of correlation, explicit probing of the one or more network paths.

A method and apparatus for analyzing IP data flows for the determination of an alternate routing path for network traffic between a known first network and a destination within an unknown second network on the Internet. An initial path between the first network and the destination exists. The IP address of the destination is determined and looked up in an Internet database. An alternative route to the destination is determined based on information from the Internet database in order to avoid an interconnecting transit network.

In one embodiment, a method comprises causing, by a network controller device, a first access point (AP) device to initiate a reverse sounding operation comprising wireles sly requesting a mobile constrained network device to transmit a null data packet (NDP) at a first transmission interval, wirelessly receiving the NDP at the first transmission interval, and generating a reception report describing reception of the NDP and including beamforming information; causing, by the network controller device, a second AP device to generate a corresponding reception report describing a corresponding wireless detection of the NDP at the first transmission interval; and causing, by the network controller device, the mobile constrained network device to connect to a selected one of the first AP device or the second AP device for an identified data flow based on the respective reception reports from the first and second AP devices.