Abstract: In one embodiment, a device obtains quality of experience labels for an online application accessible via a network. The device also obtains telemetry data from the network that is associated with quality of experience labels. The device makes, based on the quality of experience labels and telemetry data, a determination as to whether the online application is similar to a second online application for which a prediction model is already available. The device trains, based on the determination, a prediction model for the online application to predict a quality of experience metric for the online application.

Abstract: The present technology is directed to visualizing a Wi-Fi signal propagation in 3-D based on a building plan defined with implicit geometry. The present technology can extract data from a building plan file where a 3-D space and objects in a building plan are defined with implicit geometry, transform the implicit geometry to explicit geometry for the 3-D space and the objects to translate a positioning of the 3-D space and objects from a local coordinate system to a global coordinate system, calculate a RF propagation pattern in the 3-D space based on a RF propagation model for a plurality of Wi-Fi access points located in the 3-D space, and present a 3-D visualization of the RF propagation pattern in the 3-D space.

Abstract: An apparatus includes a printed circuit board (PCB), an integrated circuit (IC) component connected with a surface of the PCB, and a heat sink. The heat sink includes a base plate disposed directly over the IC component, and a plurality of cooling fins extending transversely from the base plate. The heat sink includes at least one component including a bimetallic material that distorts when heated above a threshold temperature so as to modify a flow of air directed toward and contacting the cooling fins or maintain contact between a surface of the IC component and a facing surface of the base plate.

Abstract: Crest Factor Reduction (CFR) parameters are determined for a dual band Power Amplifier (PA). A first band of the dual band PA is associated with a first Multi-Link Operation (MLO) link and a second band of the dual band PA is associated with a second MLO link. Determining the CFR parameters comprises determining based on a configuration of the first MLO link and the second MLO link. A first portion of the CFR parameters is provided to a first crest factor reduction block. First portion of the CFR parameters comprises a first clipping threshold associated with the first band and first filter coefficients associated with the first band. A second portion of the CFR parameters is provided to a second crest factor reduction block. The second portion of the CFR parameters comprises a second clipping threshold associated with the second band and second filter coefficients associated with the second band.

Abstract: Scaling by using tiered multi-level scheduling may be provided. Connectivity information associated with a plurality of Access Points (APs) may be received by a computing device. A plurality of Connectivity Groups (CGs) may be determined from the plurality of APs based on the connectivity information. Transmissions may be scheduled for the plurality of CGs such that when any of the plurality of CGs sends a transmission, the transmission is substantially unaffected by interference from any others of the plurality of CGs.

Abstract: Connection issue prediction may be provided. A computing device may receive first Channel State Information (CSI) for a first link associated with a client device. The first CSI may be collected when beamforming was trained on a second link associated with the client device. Second CSI may be received for the first link associated with the client device. The second CSI may be collected at a time subsequent to when beamforming was trained on the second link associated with the client device. A correlation between the first CSI and the second CSI may be determined to be below a predetermined threshold. A status of the beamforming performed on the second link associated with the client device may be set to stale in response to determining that the correlation between the first CSI and the second CSI is below the predetermined threshold.

Abstract: In one embodiment, a method for link state flooding between a network node and a receiving node includes determining a current transmit rate that Link State Protocol Data Units (LSPs) are being transmitted from the network node to the receiving node. The method further includes determining an LSP acknowledgment rate that indicates a rate at which a plurality of LSP acknowledgments are received at the network node from the receiving node. The method further includes determining a new transmit rate based on the current transmit rate and the LSP acknowledgment rate. The method further includes transmitting a plurality of LSPs from the network node to the receiving node using the new transmit rate.

Abstract: In one embodiment, a client device enters an area having an overhead mesh of access points, each access point comprising one or more directional transmitters each configured to transmit a beam cone in a substantially downward direction towards a floor of the area. The client device obtains an area-dependent communication schedule for the overhead mesh that is exclusive or partially-exclusive to the client device for the area. The client device sends, during an arbitrary timeslot of the area-dependent communication schedule, a pull request. The client device receives, from a particular access point in the overhead mesh, a packet in response to the pull request.

Abstract: Techniques for analyzing traffic originating from a host device in a wireless network to identify one or more virtual machines (VMs) running on the host device and connected to the network via the host device in bridge mode. When a VM is created in bridge mode behind a host device, the traffic originated by the VM will have the source Media Access Layer (MAC) address of the host device. According to techniques described herein, devices and/or components associated with the network may profile the traffic to identify an address of the VM, such as by analyzing dynamic host configuration protocol (DHCP) packets to determine the Internet Protocol (IP) address of the VM. Once the IP address and the MAC address of the VM is known, the components and/or devices may apply security policies to the VM that may be different than security policies applied to the host device.

Abstract: In one embodiment, a device forms a latent space by applying dimensionality reduction to timeseries snippets of path metrics for a network path via which traffic for an online application is conveyed. The device extracts a plurality of path states from the latent space. The device presents the plurality of path states for display by a user interface. The device associates a set of transitions between the plurality of path states with the online application providing degraded application experience.

Abstract: Techniques and architecture are described for validating and verifying iPXE scripts prior to execution during a booting process. During the booting process of a network device, right after the UEFI/BIOS stage of the booting process, a trusted iPXE script may make a request to a network server for the ownership voucher and owner certificate of the network device. The ownership voucher and owner certificate may then be stored in a trusted platform module (TPM) on the network device. In configurations, the retrieved owner certificate may be validated by the ownership voucher. The owner certificate may be used to validate iPXE scripts. Once validated, the iPXE scripts may be executed and the booting process may be continued to the kernel loading step and the application loading step. During a subsequent booting process of the network device, the ownership voucher and owner certificate may be retrieved from the TPM.

Abstract: A method for communicating in a digital conversation is implemented on a computing device and includes: receiving an interactive contextual emoji from a first digital conversation participant to post in the digital conversation with at least a second digital conversation participant, where the interactive contextual emoji is pre-defined to indicate at least a current availability status associated with the first digital conversation participant, requesting the current availability status from a status application based on at least an indication of the interactive contextual emoji, where the status application maintains the current availability status, receiving the current availability status from the status application, and displaying the interactive contextual emoji in the digital conversation with at least an indication of the current availability status.

Abstract: Techniques for obtaining application network metadata from a service registry so that a network routing policy may be derived for traffic associated with the application are described herein. The techniques may include receiving, at a service registry, network metadata associated with traffic of an application hosted by a scalable application service platform. The techniques may also include obtaining, by a controller of a network and from the service registry, the network metadata associated with the traffic of the application. Based at least in part on the network metadata, the controller may determine a routing policy that is optimized for sending the traffic through the network. Additionally, the controller may send an indication of the routing policy to a node of the network or otherwise provision the network such that the traffic of the application is sent through the network according to the routing policy.

Abstract: Techniques are provided herein for dynamic pressure control of a heat sink. In one example embodiment, an apparatus includes a Ball Grid Array (BGA) device, a heat sink thermally coupled to the BGA device, and a pressure control assembly configured to dynamically control a pressure of the heat sink on the BGA device based on a temperature associated with the BGA device. The pressure control assembly includes a Shape Memory Alloy (SMA) washer configured to apply a first amount of the pressure when the SMA washer is in a first state, and a second amount of the pressure when the SMA washer is in a second state.

Abstract: A method in which a plurality of transmit signals are generated at data rates that are offset from each other by inserting an idle data block into a data stream for one or more transmit signals of the plurality of transmit signals to increase a data rate for the one or more transmit signals, thereby minimizing detectable electromagnetic interference at a particular frequency. The method further includes converting each transmit signal of the plurality of transmit signals to a corresponding optical transmit signal of a plurality of optical transmit signals for transmission via a corresponding channel of a plurality of channels of an optical network device and transmitting the plurality of optical transmit signals via respective ones of the plurality of channels for transmission on respective optical fibers.

Abstract: An apparatus includes a ribbon, an optical waveguide, and an IC. The ribbon includes a first end. The optical waveguide is disposed within the ribbon and terminates at the first end. The IC includes a curved surface. The first end of the ribbon bends to mate with the curved surface such that the optical waveguide is optically coupled to a corresponding waveguide in the IC.

Abstract: A method for providing multicast frames in a Multi-Dwelling Unit (MDU) is provided herein. An Access Point (AP) can receive a join request from a first client device. The AP can generate a Group Master Key (GMK) from the Pre-Shared Key (PSK) associated with a Basic Service Set (BSS) that includes the first client device. The AP can then derive a Group Transient Key (GTK) from the GMK. The AP may then send the GTK to the first client device. Thereinafter, the AP can send multicast frames to the first client device encrypted by the GTK. The first client device can decrypt the multicast frames with the GTK. However, a second client device, that does not share the PSK, may receive the multicast frame but cannot decrypt the multicast frames.

Abstract: Techniques for binding communication flows to unique addresses and/or ports, and configuring networking devices internal to a network to apply policy without the need to further introspect a given stream. Further, by creating mappings of unique addresses and/or ports to flows, the network devices are able to enforce policy without needing to coordinate with an edge node of the network at which the communication session terminates. Further, the techniques may include providing an SDN controller with a mapping between a unique address/port and a network flow, determining flow-specific policy to enforce on the flow, and programming one or more network devices to enforce the flow-specific policy in the network using the unique address/port.

Abstract: Presented herein are techniques for using mobile client density to compensate for variations in path loss between neighboring access points. In one example, a device (e.g., wireless controller) determines one or more mobile client density variation trends in a wireless network location and determines one or more neighbor message power variation trends between at least first and second access points within the wireless network location over a time period. The device generates one or more correlation bias factors using the mobile client density variation trends and the neighbor message power variation trends over the time period. The device determines a path loss between at least the first and second access points using the correlation bias factor.

Abstract: A method, computer system, and computer program product are provided for mitigating network risk. A plurality of risk reports corresponding to a plurality of network devices in a network are processed to determine a multidimensional risk score for the network. The plurality of risk reports are analyzed using a semantic analysis model to identify one or more factors that contribute to the multidimensional risk score. One or more actions are determined using a trained learning model to mitigate one or more dimensions of the multidimensional risk score. The outcomes of applying the one or more actions are presented to a user to indicate an effect of each of the one or more actions on the multidimensional risk score for the network.