Abstract: A system can determine by which path/tunnel an Internet destination can be best reached for a user with an IP address from a static BGP range. The system looks up the destination address in an egress map. This map can either specify a tunnel that should be used for encapsulation for static BGP, or (when tunnel is not present) cause the system to send out unencapsulated traffic, in which the traffic follows normal BGP routing on a border network.

Abstract: A virtual private drone (VPD) system may include a device manager, one or more stations, one or more drones, and one more computing engines. The device manager keeps a repository of device metadata of all drones and computing engines in each deployment of the drone, and runs as an always-on point of contact on the network, globally reachable by all other drones and computing engines in the system. The station is a control center of the VPD system, and each station obtains its network address during registration with the device manager, and starts to synchronize copies of the device metadata using local communication. The drone includes a flight controller module programmable with a flight plan using a number of navigating points, and/or responding to runtime commands. The computing engine includes hardware and software that perform specialized compute-intensive data processing such as computer vision and artificial intelligence (AI).

Abstract: In one embodiment, a router receives a packet, and determines an intra-flow packet priority level of the packet. The router may then map the intra-flow packet priority level to a weighted random early detection (WRED) marking based on running statistics of intra-flow packet priority levels across received flows, and marks the packet with the mapped WRED marking. By placing the marked packet into an outgoing network queue for transmission, the router may then forward or drop the marked packet based on the network queue, accordingly.

Abstract: Messages are sent from a first network device to a second network device across a network. The network includes a network portion with an expected random packet loss rate. The actual packet loss rate for packets sent across the network is compared to the expected random packet loss rate. A determination is made that the actual packet loss rate is greater than the expected random packet loss rate. Compensation for network congestion is performed in response to the determination that the actual packet loss rate exceeds the expected random packet loss rate.

Abstract: Messages are sent from a first network device to a second network device across a network. The network includes a network portion with an expected random packet loss rate. The actual packet loss rate for packets sent across the network is compared to the expected random packet loss rate. A determination is made that the actual packet loss rate is greater than the expected random packet loss rate. Compensation for network congestion is performed in response to the determination that the actual packet loss rate exceeds the expected random packet loss rate.

Abstract: In one embodiment, a router receives a packet, and determines an intra-flow packet priority level of the packet. The router may then map the intra-flow packet priority level to a weighted random early detection (WRED) marking based on running statistics of intra-flow packet priority levels across received flows, and marks the packet with the mapped WRED marking. By placing the marked packet into an outgoing network queue for transmission, the router may then forward or drop the marked packet based on the network queue, accordingly.

Abstract: In an example embodiment, there is described herein an apparatus comprising an upstream communication interface configured to receive a multicast stream from a source encoded by a first codec, a downstream communication interface, and routing and transcoding logic coupled to the upstream communication interface and downstream communication interface. The routing and transcoding logic is configured to forward the multicast stream encoded by the first codec unchanged to a first downstream subscriber of the multicast stream. The routing and transcoding logic is configured to replicate the multicast steam and transcode the multicast stream to a second codec for a second downstream subscriber, the replicated, transcoded multicast stream is forwarded to the second downstream subscriber.

Abstract: Techniques are provided herein to add multicast media streams to teleconferencing sessions without the unwanted side effects that occur when a speaker's own media is echoed back to the speaker. Multicast and unicast media streams are generated by a network device, e.g., a conference bridge, and distributed to any number of endpoints, e.g., conference endpoints. A media selector is provided that selects the appropriate multicast or unicast media stream for forwarding to an associated network endpoint.

Abstract: A Digital Signal Processor (DSP) cloud architecture for clustering DSP resources across multiple integrated media-services gateways. The control plane components use peer-to-peer overlay connections for DSP resource management. The data plane components use a Virtual Local Area Network (VLAN) for media stream packet processing.

Abstract: Techniques are provided herein to add multicast media streams to teleconferencing sessions without the unwanted side effects that occur when a speaker's own media is echoed back to the speaker. Multicast and unicast media streams are generated by a network device, e.g., a conference bridge, and distributed to any number of endpoints, e.g., conference endpoints. A media selector is provided that selects the appropriate multicast or unicast media stream for forwarding to an associated network endpoint.

Abstract: Techniques are provided for a scalable video multicast framework. In one form, a network device receives information indicating video decoding parameters of an endpoint network device. One or more video streams are received are the network device. A video stream is generated from the one or more video streams for the endpoint network device based on the video decoding. The video stream is transmitted to the endpoint network device. In another form, video decoding parameters from a plurality of endpoint network devices are received at a network device. An incoming video stream is received at the network device that is intended for the plurality of endpoint network devices. One or more outgoing video streams are generated from the incoming video stream for the plurality of endpoint network devices based on a highest video quality indicated by the video decoding parameters.

Abstract: In an example embodiment, there is described herein an apparatus comprising an upstream communication interface configured to receive a multicast stream from a source encoded by a first codec, a downstream communication interface, and routing and transcoding logic coupled to the upstream communication interface and downstream communication interface. The routing and transcoding logic is configured to forward the multicast stream encoded by the first codec unchanged to a first downstream subscriber of the multicast stream. The routing and transcoding logic is configured to replicate the multicast steam and transcode the multicast stream to a second codec for a second downstream subscriber, the replicated, transcoded multicast stream is forwarded to the second downstream subscriber.

Abstract: Embodiments of the present invention combine the flexibility of the computer in segmenting, indexing, and retrieving data with the strengths of people in analyzing scenes. They provide a mechanism that allows a group of analyzers at distributed locations to collaborate in generating pieces of semantic information of a data stream, integrates these pieces into a summary representation that can be used for subsequent computation, and allows related hypotheses and information requests to be presented back to the analyzers. This description is not intended to be a complete description of, or limit the scope of, the invention. Other features, aspects, and objects of the invention can be obtained from a review of the specification, the figures, and the claims.

Abstract: A Digital Signal Processor (DSP) cloud architecture for clustering DSP resources across multiple integrated media-services gateways. The control plane components use peer-to-peer overlay connections for DSP resource management. The data plane components use a Virtual Local Area Network (VLAN) for media stream packet processing.

Abstract: A high-performance queueing method to implement a shared queue for collaborative clusters of servers, where each cluster of servers maintains a local queue, and those queues are networked to form a unified (or shared) queue for all those servers in clusters. Requests in an overcrowded queue are forwarded to some other queues, with a randomized algorithm and a message-exchange algorithm between the networked queues. Requests may be forwarded between clusters multiple times. A request is to be accepted with a higher probability by a cluster if the cluster is visited earlier in the order and if the cluster itself has a higher probability to accept the received request. This technique ensures that the requests are forwarded to a queue that has a shorter length (thus a shorter waiting time for first-in-first-out queues) and is closer to the original cluster with a higher probability.

Abstract: A high-performance queueing method to implement a shared queue for collaborative clusters of servers, where each cluster of servers maintains a local queue, and those queues are networked to form a unified (or shared) queue for all those servers in clusters. Requests in an overcrowded queue are forwarded to some other queues, with a randomized algorithm and a message-exchange algorithm between the networked queues. Requests may be forwarded between clusters multiple times. A request is to be accepted with a higher probability by a cluster if the cluster is visited earlier in the order and if the cluster itself has a higher probability to accept the received request. This technique ensures that the requests are forwarded to a queue that has a shorter length (thus a shorter waiting time for first-in-first-out queues) and is closer to the original cluster with a higher probability.

Abstract: Embodiments of the present invention combine the flexibility of the computer in segmenting, indexing, and retrieving data with the strengths of people in analyzing scenes. They provide a mechanism that allows a group of analyzers at distributed locations to collaborate in generating pieces of semantic information of a data stream, integrates these pieces into a summary representation that can be used for subsequent computation, and allows related hypotheses and information requests to be presented back to the analyzers. This description is not intended to be a complete description of, or limit the scope of, the invention. Other features, aspects, and objects of the invention can be obtained from a review of the specification, the figures, and the claims.