Abstract: In one embodiment, a traffic analysis service receives captured traffic data regarding a Transport Layer Security (TLS) connection between a client and a server. The traffic analysis service applies a first machine learning-based classifier to TLS records from the traffic data, to identify a set of the TLS records that include Hypertext Transfer Protocol (HTTP) header information. The traffic analysis service estimates one or more HTTP transaction labels for the connection by applying a second machine learning-based classifier to the identified set of TLS records that include HTTP header information. The traffic analysis service augments the captured traffic data with the one or more HTTP transaction labels. The traffic analysis service causes performance of a network security function based on the augmented traffic data.

Abstract: In one embodiment, a controller instructs agent processes to monitor for instances of particular types of interactions, each defined by a type of context entity within an interaction instance and one or both of a type of head entity sourcing an interaction instance and a type of tail entity as a destination of an interaction instance. The controller may then receive interaction objects from plurality of agent processes, each containing an identification of a respective interaction instance matching one of particular types of interactions, each respective interaction instance identifying, as components of each respective interaction instance, a particular context entity and one or both of a particular head entity and a particular tail entity.

Abstract: In one embodiment, a network assurance service that monitors a network receives telemetry data regarding monitored characteristics of the network. The service identifies, using a machine learning-based pattern analyzer, a pattern of the monitored characteristics that are associated with failures experienced by one or more networking devices in the network. The service groups networking devices by software version. The service determines probabilities of the pattern being observed concurrently with failures of the grouped network networking devices. A particular probability is associated with a particular group of the networking devices executing a particular software version. The service provides, based on the determined probabilities, data regarding the identified pattern and software versions for display.

Abstract: Telemetry for cloud switches queuing excursion may be provided. A first hysteresis threshold and a second hysteresis threshold for a queue of the network switch may be specified. Next, a queue position relative to the first hysteresis threshold and the second hysteresis threshold may be determined for each incoming packets for the queue. A number of crossings including the queue position passing the first hysteresis threshold and subsequently passing the second hysteresis threshold in a first predetermined time period may be determined. A number of data packets being sent to the queue of the network switch may then be altered based on one or more of the number of crossings, the first hysteresis threshold, and the second hysteresis threshold.

Abstract: Learning-based service migration in mobile edge computing may be provided. First, a service migration policy may be created for a network that includes a plurality of edge clouds configured to provide a service to users. Next, a movement of a user receiving the service from a source edge cloud may be detected. The source edge cloud may be associated with a first area and the detected movement may be from the first area to a second area. Then, the service migration policy may be applied to determine whether to migrate the service for the user from the source edge cloud. In response to determining to migrate the service, a target edge cloud may be identified and the service for the user may be migrated from the source edge cloud to the target edge cloud. The service migration policy may then be updated based on a success of the migration.

Abstract: A solid state drive (SSD) device includes a cage with a top wall and a bottom wall spaced a distance from the top wall so as to define a cage interior between the top and bottom walls. In addition, at least 10% of an area along a side of the cage is open to the cage interior to permit airflow through the side of the cage. At least one printed circuit board (PCB), which includes at least one integrated circuit component, is also provided within the cage interior.

Abstract: In accordance with various embodiments, a method is performed including establishing a first communication session between an application function and a user equipment assigned a first IP address. The method includes determining, by the application function, that the user equipment has changed location. The method includes, in response to determining that the user equipment has changed location, sending, by the application function, a request that the user equipment be assigned a second IP address. The method includes establishing a second communication session between the application function and the user equipment assigned the second IP address.

Abstract: A quality of service framework for applications may be provided. First, a Bandwidth Report (BWR) message may be received from a first sub-system by a second sub-system. The BWR message may correspond to traffic to be received from the first sub-system by the second sub-system. Next, based on the BWR message, the second sub-system may schedule grants for the traffic to be received from the first sub-system. The second sub-system may then receive, from the first sub-system, the traffic. Then the second sub-system may transmit the traffic based on the scheduled grants.

Abstract: In one example, a Network Functions Virtualization Orchestrator (NFVO) obtains a radio service descriptor defining communication parameters for a radio in a virtual Radio Access Network (vRAN). Based on the radio service descriptor, the NFVO determines whether a virtual Distributed Unit (vDU) that is configured in accordance with the communication parameters and a virtual Centralized Unit (vCU) that is configured in accordance with the communication parameters are already instantiated in the vRAN. If it is determined that the vDU or the vCU is not already instantiated, the NFVO automatically instantiates the vDU or the vCU in the vRAN.

Abstract: In one embodiment, a millimeter wave (mmWave) radio resource allocation scheme for vehicle-to-infrastructure (V2I) communications is disclosed, which may illustratively comprise receiving, by a base station, a connection request of a plurality of connection requests from a mobile station of a plurality of mobile stations; determining, by the base station, a resource block allocation scheme that is formulated as a two dimensional rectangular bin for the plurality of mobile stations; allocating, by the base station, one or more resource sub-blocks of the resource block allocation scheme to the mobile station using at least one packing parameter; and controlling, by the base station, the mobile station to communicate with the base station using the one or more resource sub-blocks.

Abstract: In one embodiment, a system includes: a plurality of cloud nodes implemented on computing devices, the plurality of cloud nodes configured to execute computing jobs in a cloud computing environment according to a schedule, a schedule optimizer configured to: use a machine learning model to determine functional intent for job requests according to at least job execution metadata, and generate a schedule recommendation for jobs associated with the job requests, where the schedule recommendation is generated based at least in part on the functional intent; and a job executor configured to provide the schedule recommendation as the schedule to the plurality of cloud nodes, where the schedule optimizer and the job executor are instantiated in memory and executed by processing circuitry on at least one computing device.

Abstract: In one embodiment, a device obtains a machine learning model indicative of how to focus on particular location information from a plurality of radio frequency (RF) elements to provide an accurate location estimate of a wireless client based at least in part on angle-of-arrival information of the wireless client. When the device then obtains location information regarding the wireless client from the plurality of RF elements, it may apply the machine learning model to the location information regarding the wireless client to focus on particular location information of the location information from the plurality of RF elements. The device may then estimate a physical location of the wireless client based on focusing on the particular location information during a locationing computation.

Abstract: A method for selecting either a first malware analysis system or a second malware analysis system to analyze a file is disclosed. The method includes obtaining, at a network security element, a file sent between a first device and a second device, the file having one or more associated attributes; analyzing, at the network security element, the one or more attributes of the file; selecting, based on the analyzing, either the first malware analysis system or the second malware analysis system as a selected malware analysis system for malware analysis of the file; and providing the file to the selected malware analysis system.

Abstract: In one implementation, a media stream is recorded using one or more keys. The one or more keys are also encrypted. The one or more encrypted keys may be stored with the encrypted media session at a cloud storage service. A network device receives a request to record a media stream and accesses at least one stream key for the media stream. The stream key is for encrypting the media stream. The network device encrypts the stream key with a master key. The encrypted stream key is stored in association with the encrypted media stream.

Abstract: In one embodiment, an electronic device maintains one or more tunnel-based overlays for a communication network. The communication network includes two or more physical provider networks. The device maintains a mapping between a particular application and the one or more overlays for the communication network. The device adjusts the mapping between the particular application and the one or more overlays for the communication network. The device causes one or more routers in the communication network to route traffic for the particular application according to the adjusted mapping between the application and the one or more overlays for the communication network.

Abstract: A Unified Data Repository (UDR) proxy obtains first subscriber data from a first UDR of a first network operator, second subscriber data from a second UDR of a second network operator, and third subscriber data from a third UDR of an enterprise. The UDR proxy stores the first subscriber data, the second subscriber data, and the third subscriber data locally. The UDR proxy obtains a request to access a network asset that is accessible through the first network operator. Based on the first subscriber data, the second subscriber data, and the third subscriber data stored locally, the UDR proxy attempts to determine whether the request to access the network asset is authorized to access the network asset. In response to determining that the request to access the network asset is authorized, the UDR proxy permits access to the network asset.

Abstract: Presented herein are methodologies for scaling device management over a sideband management bus (SMBUS). A method includes receiving, at a first expander card, from baseboard management controller (BMC), a management message, addressed to a second expander card that is in communication with the first expander card, forwarding the management message to the second expander card, and sending, by the second expander card, the management message, via the sideband management bus, to a device in communication with the second expander card. The device may be, e.g., a Non-Volatile Memory Express (NVMe) drive. Expander cards can be deployed in a daisy chain, providing scalability. Each expander card can also send commands to connected devices in parallel.

Abstract: An example apparatus for supporting digital pre-distortion (DPD) and full duplex (FDX) in cable network environments is provided and includes a first path for signals being transmitted out of the apparatus, a second path for signals being received into the apparatus, a DPD actuator located on the first path, an amplifier located on the first path, an echo cancellation (EC) actuator located on the second path, and a data interface including a plurality of channels connecting the apparatus to a signal processor. DPD coefficients, EC coefficients and delay parameters are provided over the data interface from the signal processor to the apparatus. The DPD actuator predistorts signals on the first path using the DPD coefficients compensating for distortions introduced by the amplifier, and the EC actuator reduces interferences in signals on the second path using the EC coefficients and the delay parameters, facilitating FDX communication by the apparatus.

Abstract: Embodiments of the present disclosure specify methods and systems for processing a video stream. For example, a video stream may be received at a video processing device. The video stream may comprise video usability syntax elements. The video usability syntax elements may comprise at least a first flag indicative of whether HRD parameters are present for one of fixed frame rate processing or low delay mode processing. The video usability syntax elements may also comprise at least a second flag indicative of whether the video stream comprises field-coded video sequences.

Abstract: In one embodiment, a diagnostic device determines signal strengths of two antennas of a multi-antenna device. When the signal strength of each of the two antennas is unacceptable, the diagnostic device provides a recommendation to adjust each of the two antennas. Alternatively, when the signal strength of a first antenna of the two antennas is unacceptable while the signal strength of a second antenna of the two antennas is acceptable, the diagnostic device provides a recommendation to adjust the first antenna. However, when the signal strength of each of the two antennas is acceptable, but a difference between the signal strength of a first antenna and a second antenna of the two antennas is greater than a threshold, then the diagnostic device determines a weaker antenna with weaker signal strength between the first antenna and the second antenna, and provides a recommendation to adjust the weaker antenna.