Abstract: Exemplary methods, apparatuses, and systems maintain network membership information for a host when it is disconnected from a controller. When the host detects a loss of connectivity with the network controller, the host identifies and selects one or more hosts that are members of a control logical network. The control logical network includes hosts configured to run data compute nodes that are members of the overlay network, regardless of whether or not each of the hosts is currently running a data compute node that is a member of the overlay network. The host then sends any broadcast, unknown destination, or multicast (BUM) data packet(s) to the selected one or more hosts.

Abstract: Methods, systems, and devices for wireless communications are described in which sidelink communications between devices may be retransmitted using one or more nodes. A first user equipment (UE) may transmit a broadcast, multicast, or groupcast communication to a set of other UEs using sidelink resources. A node may monitor the communications and store the first UE transmission. UEs of the set of other UEs may transmit feedback reports to the node that indicate one or more missing packets of the first UE transmission. The node may retransmit one or more of the stored packets to the set of other UEs based on the feedback reports. In some cases, the sidelink communications may be encoded using a network coding algorithm, and the node may retransmit network coded packets based on the feedback reports, may transmit newly encoded packets based on the feedback reports, or combinations thereof.

Abstract: This application provides a communications method and a communications apparatus, to reduce storage resources required by an access network device to store a context of a terminal device. The method includes: The access network device gathers terminal devices that have a same attribute in a group, where a context of each terminal device is divided into two parts: a common context and a dedicated context, the common context is shared by all the terminal devices in the group, and the dedicated context is a context specific to the terminal device. The access network device stores one common context for each group and stores a dedicated context of each terminal device in the group, to maintain the context of each terminal device.

Abstract: A method implemented by a network node in a Bit Index Explicit Replication Traffic/Tree Engineering (BIER-TE) domain is used to avoid duplicate packets. The method includes generating an improved bit index forwarding table (BIFT) containing a forwarding entry for a local area network (LAN)-connected adjacency from the network node to a pseudo node; and a secondary BIFT including a forwarding entry for a forward connected adjacency from the pseudo node to each of the pseudo node's next hop nodes except the network node; sending a packet containing a point to multipoint (P2MP) path with a bit position for the LAN-connected adjacency to the pseudo node according to the forwarding entry for the LAN-connected adjacency in the improved BIFT; and sending the packet to each of the pseudo node's next hop nodes on the P2MP path based on the secondary BIFT.

Abstract: This application provides a BIER packet sending method. The method includes: receiving a BIER packet that is encapsulated using an IPv6 protocol and that is sent by a second forwarding device, where the BIER packet includes an IPv6 basic header and a BIER header, a destination address field in the IPv6 basic header is a first IPv6 address of the first forwarding device; determining, based on an identifier corresponding to a first IPv6 address in a forwarding table, to perform BIER forwarding on the BIER packet, where the identifier is used to indicate that the first IPv6 address is a destination address for BIER forwarding. In the technical solution provided in this application, a node may determine, based on the identifier of the first IPv6 address, to perform BIER forwarding on the BIER packet.

Abstract: System and method provide wireless distributed lighting control systems implementing a secure peer-to-peer, self-organizing and self-healing mesh network of actuators and system inputs. The system and method can be designed specifically for indoor and outdoor lighting where actuators include in-fixture, on-fixture and circuit control modules with ON/OFF and full range dimming capabilities, and system inputs include occupancy/vacancy sensors, daylight sensors and switches. A unique messaging protocol facilitates wireless and wired communication between actuators and system inputs, and provides web-based commissioning and monitoring of the lighting control system using a wireless access point accessible from a local network or Internet which can provide an intuitive and easy to use Graphical User Interface (GUI).

Abstract: A controller assigns variable length addresses to addressable elements that are connected to a network. The variable length addresses are determined based on probabilities that packets are addressed to the corresponding addressable element. The controller transmits, to the addressable elements via the network, a routing table indicating the variable length addresses assigned to the addressable elements. Routers or addressable elements receive the routing table and route one or more packets over the network to an addressable element using variable length addresses included in a header of the one or more packets.

Abstract: In an embodiment, a computer-implemented method for highly-scalable, in-network multicasting of statistics data is disclosed. In an embodiment, a method comprises: receiving, from an underlay controller, a match-and-action table that is indexed using one or more multicast (“MC”) group identifiers and includes one or more special MC headers; detecting a packet carrying statistics data; determining whether the packet includes an MC group identifier; in response to determining that the packet includes the MC group identifier: using the MC group identifier, retrieving a special MC header, of the one or more special MC headers, from the match-and-action table; generating an encapsulated packet by encapsulating the packet with the special MC header; and providing the encapsulated packet to an interface controller for transmitting the encapsulated packet to one or more physical switches.

Abstract: A method for execution by a processor of a host having an external interface for connection to at least one other network element of a packet-based data network, the host storing a routing table and implementing a container connected to a bridge, the container being addressable by an internal address on a bridge network associated with the bridge. The method includes obtaining an indication of a request for the container to join a multicast group. In response to the obtaining, a request is sent via the external interface for the host to join the multicast group. The routing table may be modified so as to make the bridge a next hop for future packets obtained from the external interface and destined for the multicast group. The routing table may also be modified so as to make the external interface a next hop for future packets that are obtained from the bridge, whose source address is the internal address of the container and that are destined for the multicast group.

Abstract: A non-transitory computer-readable medium whose contents, when executed by a computing system of an in-home security device, cause the computing system to perform operations to provide security for an in-home network, including receiving home network internet datagrams from a modem at the in-home security device to provide received home network data packets, the received home network internet datagrams being all data packets received by the modem directed to the in-home network from outside, analyzing the received home network internet datagrams using an artificial intelligence service to identify a type of security threat included in the received home network internet datagrams, selecting a security application from among a plurality of security applications included in an in-home network security application suite based on the type of security threat identified in the received home network internet datagrams by the artificial intelligence service to provide a selected security application, using the selecte

Abstract: Embodiments of this application provide a bit-forwarding ingress router, a bit-forwarding router, and an OAM test method, and pertain to the field of multicast networks. A first BFR receives an OAM request packet from a BFIR; the first BFR determines, according to the OAM request packet, that a destination BFR corresponding to the OAM request packet is the first BFR; and the first BFR obtains a first OAM response packet according to an ID of the BFIR, and sends the first OAM response packet to the BFIR. According to the method and the apparatus that are provided in the embodiments of this application, a problem that a BFIR cannot diagnose or handle a transmission fault when the fault occurs during transmission of a multicast packet can be resolved, which helps implement connectivity testing by using an OAM packet and enables testing of multiple BFERs.

Abstract: The present disclosure is intended to enable efficient content forwarding in an HTTP-based web distribution system while maintaining HTTP, which is unicast. In the present disclosure, a unicast-multicast conversion device and a multicast-unicast conversion device that are connected, by using a multicast communication network, with a network between a content server and a terminal that perform web distribution are provided. The unicast-multicast conversion device and the multicast-unicast conversion device execute, in both multicast and unicast, forwarding of a content group into which a plurality of contents are grouped.

Abstract: Hybrid mode multicast routing may be provided. A switching device may receive a first join. Next, in response to receiving the first join, states for a first protocol mode (e.g., (S, G)) that is source aware and state for a second protocol mode (e.g., (*, G)) that is not source aware may be programed. Then a second join may be sent based on the states associated with the second protocol mode (e.g., (*, G)).

Abstract: A system for coordinated management of Internet of Things (IoT) devices to minimize power consumption and network congestion is provided. A mobile device designated as local group management device (LGMD) identifies a group of IoT devices that are configured to access a network. The mobile device receives information regarding an upcoming event involving the group of IoT devices. The mobile device generates usage knowledge specifying the group of IoT devices, a location, and a time associated with the upcoming event. The mobile device receives configuration update data that are generated based on the usage knowledge for scheduling operations of the group IoT devices. The mobile device delivers the configuration update data to the group of IoT devices.

Abstract: Embodiments of the present invention are drawn to electronic systems capable of transmitting a group addressed frame that identifies an MLD according to an MLD MAC address. The group addressed frame can include an ARP request, for example, and can be transmitted by an AP MLD responsive to an individually addressed frame transmitted by a non-AP STA MLD associated with the AP MLD. The AP MLD can provide a proxy ARP service for associated non-AP STA MLDs.

Abstract: This application provides a BIER multicast traffic statistics collection method, a device, and a system. The method includes: A first network device obtains a first BIER packet. The first network device performs traffic statistics collection on the first BIER packet based on multicast flow information, to obtain a traffic statistics collection result of the first BIER packet, where the multicast flow information is used to identify a multicast flow to which the first BIER packet belongs. The first network device sends the multicast flow information and the traffic statistics collection result of the first BIER packet to a controller.

Abstract: Systems and methods provide for enabling multicast-based performance routing and policy controls for software-defined networking in a wide area network deployment including a multicast application-route policy based on sources, groups, receivers, dynamic application-route policy path selection from multicast replicators, and application-route SLA switchover across paths and multicast replicators based on SD-WAN multicast routing architecture; and dynamically selecting SD-WAN multicast replicators based on policies for replication including allowed multicast groups, geographic location, bandwidth indications, system load, and performance, and switching over dynamically across multicast replicators based real-time multicast replicator status updates.

Abstract: Adjusting communication channels used by camera to communicate with a base station are described. In one aspect, characteristics of communication channels can be determined and the operation of the camera can be adjusted to use a communication channel based on a comparison of the characteristics of multiple communication channels.

Abstract: A method for transmitting a message via an access network to a group of terminals is provided. The access network transmits the message to the group of terminals over a broadcast channel. The access network receives a request for retransmission of the message transmitted from a terminal that has not correctly received the message. The access network evaluates a predetermined broadcast retransmission criterion and retransmits the message over a point-to-point link or over a broadcast channel according to the predetermined broadcast retransmission criterion.

Abstract: The present technology is directed to generating a common Border Gateway Protocol (BGP) attribute, for example, BGP-Slice Identifier (ID) for a specific network slice and stitching the network slice across one or more domains to realize end-to-end slicing. The present technology can generate BGP ID for a specific network slice spanning a plurality of domains and map domain-specific attributes associated with sub-slices of the specific network slice in different domains of the plurality of domains to the BGP ID. The present technology can further facilitate distribution of the mapping of the domain-specific attributes to the BGP ID across the plurality of domains for stitching the sub-slices together from the domain-specific attributes based on the BGP ID to stitch the specific network slice across the plurality of domains.

Abstract: An IoT hub comprising one or more servers and databases is configured to automatically assign Internet of Things (IoT) enabled devices to IoT solutions based on a subnet to which the IoT devices are connected. A user interface is configured to enable a user to define subnets within the customer's network environment and assign each subnet to an IoT solution. Upon the user setting up an IoT device's network connection to a network device, such as a router, the IoT device transmits its network information to the IoT hub. The IoT hub can then automatically assign the IoT device to a specific IoT solution without further user input or predict which IoT solution to utilize for that IoT device based on known parameters.

Abstract: A method is provided that includes receiving, from a first cluster, data intended for a second cluster and routing the data to the second cluster, thereby forming an indirect connection between a first cluster and the second cluster. A network usage of the indirect connection may be monitored and in response to determining that the network usage of the indirect connection exceeds a network usage threshold, a respective remote agent of each of the first and second clusters may be instructed to form a direct connection between the first and second clusters. The network usage of the direct connection may be monitored and in response to determining that the network usage of the direct connection is below the network usage threshold, the respective remote agent of each of the first and second clusters may be instructed to remove the direct connection.

Abstract: An electronic device of a content producer generates a chunk of data, associates a location-independent name with the chunk of data, generates a signature for the chunk of data, attaches the signature to the chunk of data, and transmits the chunk of data, with the signature attached, to one or more user devices in response to respective requests. The signature is generated based on the data in the chunk, using a private key of the electronic device. The electronic device also stores information, including a specification of a public key associated with the private key, in a first ledger entry of a blockchain, to provide the one or more user devices with access to the public key. A user device may obtain the public key and use it to verify the chunk of data.

Abstract: The subject technology addresses a need for improving utilization of network bandwidth in a multicast network environment. More specifically, the disclosed technology provides solutions for extending multipathing to tenant multicast traffic in an overlay network, which enables greater bandwidth utilization for multicast traffic. In some aspects, nodes in the overlay network can be connected by virtual or logical links, each of which corresponds to a path, perhaps through many physical links, in the underlying network.

Abstract: Some embodiments provide a method for configuring a set of MFEs to implement a distributed multicast logical router and multiple logical switches to process the multicast data messages. The method sends, from a managed forwarding element (MFE) implementing the distributed multicast logical router, a multicast group query to a set of data compute nodes (DCNs) that are logically connected to one of several logical switches and that execute on the same host machine as the managed forwarding element. The method receives multicast group reports from a subset of the set of DCNs and at least one of the multicast group reports specifies a multicast group of interest. The method distributes, to a set of MFEs executing on other host machines, a summarized multicast group report specifying a set of multicast groups of interest to the first MFE (i.e., multicast groups that the first MFE participates in).

Abstract: Method, devices, programs and system for the realization of an encrypted protocol for the transmission of encrypted data packets, called “Transport Encrypted Protocol” (TEP), intended for communication, characterized by a particular methodology of data encrypted encapsulation according to the blockchain paradigm including the following steps: the establishment of a distributed ledger which generate sender and recipient addresses to establish a communication characterized by the encryption of both the content and the transport channels; the verification of the integrity of the message and the correct correspondence of the address by the receiving node (hash), which decrypts each layer of encapsulation and hence decrypting the message itself; and the submission of an encrypted notification of receipt to the sender node and the subsequent preparation of the receiving node to the next state, either the break in communication or the modification of its status from recipient to sender.

Abstract: Systems and methods are provided for management of network segments that cross geographic regions and/or other types of network divisions in a cloud-based network environment. Gateway may manage traffic across regions using routing metadata that includes a segment identifier. The gateways may also signal their routes across regions based on segment data, and implement the signaled routes using segment-based routing policies. Route selection may be performed using optimization data.

Abstract: A method for facilitating communications between client devices in geographically separated networks is described. First, message monitoring is conducted by each of a plurality of virtual appliances within a local network to detect a message of a first message type. Responsive to failing to locate a Media Access Control (MAC) address of a destination for the message within a prescribed table by a default gateway, one of the plurality of virtual appliances is selected for handling a forwarding of the message to a plurality of remote networks, and the message via the selected virtual appliance is forwarded to a plurality of gateways associated with a plurality of remote networks. Responsive to locating the MAC address of the destination within the table, the virtual appliance previously handling communications with the destination to forward the message to the destination.

Abstract: A method and a user equipment (UE) for wireless communication in a wireless communication system are provided. The method includes receiving serving-cell-configurations of a first serving cell and a second serving cell; receiving a Beam Failure Recovery (BFR) configuration including a configuration list that includes at least one configuration, the BFR configuration being used for at least the first serving cell, the at least one configuration indicating an identifier value of a Downlink Reference Signal (DL RS); performing a measurement by measuring at least one DL RS indicated by the configuration list, the measurement being associated with a measurement metric; selecting one configuration included in the configuration list after detecting beam failure in the first serving cell, the measurement metric of a DL RS indicated by the selected one configuration being greater than a threshold; transmitting a Medium Access Control-Control Element (MAC-CE) including at least one bitmap.

Abstract: Disclosed are a method of controlling a display by a headset with inline control, and related devices. The method includes: detecting whether an headset jack of the display is plugged with the headset; after the headset jack of the display is determined to be plugged with the headset, inputting a detection bias voltage to the headset, and monitoring a feedback signal of the detection bias voltage; in response to detecting a change in the feedback signal of the detection bias voltage, identifying a user's control instruction to the display using the headset according to a control signal sent by the headset; and controlling the display to perform a corresponding display operation according to the control instruction.

Abstract: In one embodiment, a method comprises: establishing, by a network management device, a wireless multicast tree topology for a wireless mesh network, the wireless multicast tree topology comprising a root network device and wireless multicast hubs providing respective wireless multicast areas, the establishing including selecting each wireless multicast hub based on a corresponding location and a corresponding wireless neighbor count; and causing, by the network management device, the root network device to unicast transmit to a selected one or more of the wireless multicast hubs a multicast packet encapsulated within a unicast header, the unicast header causing the selected one or more of the wireless multicast hubs to multicast transmit the multicast packet within a corresponding one or more of the wireless multicast areas.

Abstract: A method for joint optimization of resource allocation includes: obtaining network data volumes of two services; obtaining queue statuses at a time t; computing sub-channel slices; computing a local CPU speed scaling, a user association, a sub-carrier assignment, and a power allocation of service 1; computing a user association, a video quality decision, and a sub-carrier assignment of service 2; obtaining an initial sub-carrier assignment and an initial power allocation; obtaining the user association; obtaining the power allocation and the sub-carrier assignment of service 1; obtaining the video quality decision; obtaining the sub-carrier assignment of service 2; obtaining an optimal data transmission rate and the user association to obtain a data rate allocation; and obtaining an optimal CPU speed scaling, an optimal user association, an optimal sub-carrier assignment, an optimal power allocation, an optimal video quality decision and an optimal sub-channel allocation.

Abstract: In accordance with one or more aspects, a request to run an application is received. The application has an associated tune manifest that identifies one or more resources that the application may use. The tune manifest is compared to a device resource record, and a check is made, based at least in part on the comparing, whether the one or more resources identified in the tune manifest can be satisfied by the device. If the one or more resources identified in the tune manifest can be satisfied by the device, then the application is run; otherwise, a notification of a conflict between the application and the device is presented. Additionally, when the application exits, a device tune state that identifies a content source to which the device was tuned prior to running the application can be retrieved and the device restored to this device tune state.

Abstract: A method includes receiving, at a first edge node, an Internet Protocol (IP) multicast address of a first silent host node. The method further includes receiving, at a second edge node, an IP multicast address of a second silent host node. The IP multicast address of the first silent host node is equal to the IP multicast address of the second silent host node. The method further includes storing the IP multicast address of the first and second silent host node in a shared entry of a routing table. The method further includes receiving, at a third edge node, a packet from a third host node and determining that a destination address of the packet corresponds to the IP multicast address stored in the shared entry of the routing table. The method further includes sending the packet to both the first host node and the second host node.

Abstract: Techniques are disclosed for scaling an IP address in overlay networks without using load balancers. In certain implementations, an overlay IP address can be attached to multiple compute instances via virtual network interface cards (VNICs) associated with the multiple compute instances. Traffic directed to the multi-attached IP address is distributed across the multiple compute instances. In some other implementations, ECMP techniques in overlay networks are used to scale an overlay IP address. In forwarding tables used for routing packets, the IP address being scaled is associated with multiple next hop paths to multiple network virtualization devices (NVDs) associated with the multiple compute instances. When a particular packet directed to the overlay IP address is to be routed, one of the multiple next hop paths is selected for routing the packet. This enables packets directed to the IP address to be distributed across the multiple compute instances.

Abstract: For a managed network including multiple host machines implementing multiple logical networks, some embodiments provide a method that reduces the memory and traffic load required to implement the multiple logical networks. The method generates configuration data for each of multiple host machines including (i) data to configure a host machine to implement a set of logical forwarding elements that belong to a set of routing domains and (ii) identifiers for each routing domain in the set of routing domains. The method then receives data regarding tunnels endpoints operating on each of the host machines and an association with the routing identifiers sent to the host machines. The method then generates a routing domain tunnel endpoint list for each routing domain based on the data received from each of the host machines including a list of the tunnel endpoints associated with the routing domain which the host machines can use to facilitate packet processing.

Abstract: A per-hop postcard technique is disclosed. The per-hop postcard technique is implemented to improve Postcard-based Telemetry (PBT). A per-section postcard technique is also disclosed. The per-section postcard technique is implemented to improve In-situ OAM (IOAM). By utilizing these techniques, suitable on-path telemetry may be obtained for multicast traffic. In addition, these techniques may be used to reconstruct and visualize a multicast tree, to conduct performance monitoring, and to perform trouble shooting.

Abstract: Computer systems and methods, according to various embodiments, allow users with shared access to a shared file or folder to communicate with one another via online chat. In particular embodiments, the system is configured to facilitate a chat session among all users that have shared access to a particular file or folder in response to a particular user selecting a “chat” button (or other suitable chat initiation element) associated with the shared file or folder. After a chat session is complete, the system may archive the chat session for later viewing and use.

Abstract: Provided herein are systems and methods for determining relationships between events occurring in networks. Notifications describing events occurring in networks can be received and processed to determine groups of network event types. A root-cause network can be generated based on the events, with the nodes of the root-cause network representing different event types and the edges of the root-cause network indicating directional, causal relationships between the nodes. A received network event can be processed to determine potential causes of the received network event based on the root-cause network and other events received by the network.

Abstract: Methods and systems are provided for latency-oriented router. An incoming packet is received on a first interface. The type of the incoming packet is determined. Upon the detection that the incoming packet belongs to latency-critical traffic, the incoming packet is duplicated into one or more copies. Subsequently, the duplicated copies are sent to a second interface in a delayed fashion where the duplicated copies are spread over a time period. The duplicated copies are received and processed at the second interface.

Abstract: In embodiments, Internet of Things (IoT) devices may be organized according to an IoT device hierarchy, which may include parent and/or child associations between resources associated with IoT devices and/or with groupings of IoT devices. IoT devices wishing to support an IoT device hierarchy may utilize an extended IoT device resource model which provides for IoT device hierarchy information and interfaces to be provided by supporting IoT devices. A supporting resource may have one or more parent properties and/or child properties which may identify, respectively, parent or child resources which are associated with the resource. In various embodiments, these parent properties and/or child properties may include uniform resource identifiers (URI). A supporting resource may also identify an interface type for a hierarchical access interface, through which one or more descendant resources may be accessed through a single command. Other embodiments may be descried and/or claimed.

Abstract: Methods and systems are provided for latency-oriented router. An incoming packet is received on a first interface. The type of the incoming packet is determined. Upon the detection that the incoming packet belongs to latency-critical traffic, the incoming packet is duplicated into one or more copies. Subsequently, the duplicated copies are sent to a second interface in a delayed fashion where the duplicated copies are spread over a time period. The duplicated copies are received and processed at the second interface.

Abstract: Systems and methods for capturing and distributing a live audio stream of a live event in real-time to a plurality of mobile computing devices are described. The system comprises at least one memory configured to store computer-executable instructions and processing device(s) coupled to the at least one memory and at least one audio input device configured to receive the live audio stream. Upon receipt of the live audio stream, the processing device(s) generate, in real-time, a plurality of discrete audio data packets from the live audio stream, and transmit that respective discrete audio data packet over a first network for receipt by the mobile computing devices. In respect of each one of the discrete audio data packets, a copy of the discrete audio data packet is transmitted for receipt by each one of the mobile computing devices prior to transmitting another one of the discrete audio data packets.

Abstract: A system that can facilitate multicast forwarding via overlay multicast tunnels in a network is provided. The system can operate as a tunnel endpoint and form a first overlay tunnel with a peer tunnel endpoint. During operation, the system can receive a join request for a multicast group via the first overlay tunnel. The system can identify a local port of the system associated with the multicast group indicated by the join request. The system can then include the first overlay tunnel in a set of forwarding tunnels for multicast traffic of the multicast group based on the join request. Subsequently, the system can forward the multicast traffic of the multicast group received from a local port via the set of forwarding tunnels, thereby limiting forwarding of the multicast traffic to tunnel endpoints associated with the multicast group.

Abstract: A network timing view provides enhanced visualization for synch timing in support of mobile (4G/5G deployments) and others requiring sync. It allows network managers to view relevant synch data both textually and graphically displayed on the network map nodes and links in a unified view. The user is able to select the appropriate filter on the network map to show the 1588/SyncE connectivity and relevant nodes that are participating in delivering timing. It allows a user to trace the timing path from any timing device upstream to the clock source. It also allows the user to interactively discover and navigate downstream timing paths from any timing device, similar to exploring a tree hierarchy. The timing topology and path data provided allows a user to investigate the timing network for troubleshooting purposes such as timing alarms and events, sync problems, clock quality levels and clock states.

Abstract: Techniques are disclosed for session-based routing of multipoint Open Systems Interconnection (OSI) Model Layer-2 (L2) frames of an L2 network extended over Layer-3 (L3) networks. In one example, L2 networks connect a source device to an ingress router and receiver devices to egress routers. An L3 network connects the ingress and egress routers. The ingress router receives, from the source device, a multipoint L2 frame destined for the receiver devices. The ingress router forms, for each egress router that is connected to at least one multipoint receiver device, a unicast L3 packet for the L2 frame and forwards the unicast L3 packet to the egress router. Each egress router generates, in response to receiving the unicast L3 packet, the multipoint L2 frame and forwards, to the receiver devices, the multipoint L2 frame.

Abstract: A method of transmitting multicast traffic to workloads of tenants communicating over overlay networks provisioned on top of a physical network includes the steps of: detecting the multicast traffic; determining that the multicast traffic is bound for workloads of a first tenant and workloads of a second tenant; encapsulating one instance of the multicast traffic using a Layer 2 (L2) over Layer 3 (L3) encapsulation protocol to generate encapsulated traffic, wherein the encapsulated traffic includes an identifier of a first backplane network corresponding to the first tenant and an identifier of a second backplane network corresponding to the second tenant in a header portion of each packet of the encapsulated traffic; and transmitting, to a first host computing device, the encapsulated traffic with the identifiers of the first and second overlay networks.

Abstract: Technology related to processing network packets in a subscriber-aware manner is disclosed. In one example, a method includes selecting one or more subscribers to move from a first network processing node to a second network processing node. In response to the selection, subscriber data associated with the one or more subscribers can be programmed at the second network processing node. After the subscriber data associated with the one or more subscribers is programmed on the second network processing node, a software defined network (SDN) switch can be reprogrammed to forward network traffic having network addresses associated with the one or more subscribers to the second network processing node instead of the first network processing node.

Abstract: The invention provides a data communication method, including: sending, by the first electrical node, request information to an electrical node, where the request information is used to request an expected data volume quota of a first VOQ, and the first VOQ stores at least one first data packet to be sent to the electrical node; receiving response information, where the response information includes a target data volume quota; and sending the at least one first data packet to the electrical node via the at least one optical node based on the target data volume quota.

Abstract: A method of training a neural network includes, at a local computing node, receiving remote parameters from a set of one or more remote computing nodes, initiating execution of a forward pass in a local neural network in the local computing node to determine a final output based on the remote parameters, initiating execution of a backward pass in the local neural network to determine updated parameters for the local neural network, and prior to completion of the backward pass, transmitting a subset of the updated parameters to the set of remote computing nodes.