Abstract: Techniques are provided that rotate a device address used to identify a wireless client device on a wireless network. The wireless client device and at least one network infrastructure component identify a plurality of device addresses associated with the wireless client device. In some embodiments, the plurality of device addresses are generated via a corresponding plurality of invocations of a stateful random number generator, such as a cryptographically secure pseudorandom number generator.

Abstract: A method is provided for a radio aware transport network. A network device obtains a first request for a status of one or more radio cells of a radio access network. The network device is configured to transmit radio traffic of the radio access network in a fronthaul packet network and is in communication with a radio controller that manages the one or more radio cells. The network device provides, to the radio controller, a second request for operational data related to the one or more radio cells. The second request is in a format specific to the radio controller. The network device obtains, from the radio controller, the operational data and determining the status of the one or more radio cells based on the operational data.

Abstract: Certain embodiments disclose systems and methods for creating a user private network (UPN) based on 11ay technology. Methods of the present disclosure include creating a personal basic service set (PBSS) having a service device and one or more 11ay devices, the service device configured to wirelessly communicate with the one or more 11ay devices in the PBSS, creating a UPN having an access point located in communicative proximity with the service device, and associating at least one 11ay device of the one or more 11ay devices with the UPN, wherein the at least one 11ay device is configured to establish a wireless connection with the one or more 11ay devices using the service device when within a coverage area of the PBSS, and to establish a wireless connection with the one or more 11ay devices using the access point when outside the coverage area of the PBSS.

Abstract: One embodiment of the present invention sets forth a technique for processing recordings of events. The technique includes applying a machine learning model to a plurality of samples from one or more recordings of the events to generate a plurality of embeddings representing the plurality of samples. The technique also includes generating a plurality of labels that identify speakers associated with the plurality of samples based on metadata comprising timestamps of voice activity during the events and participants associated with the voice activity. The technique further includes storing mappings of the plurality of embeddings to the plurality of labels.

Abstract: Techniques for detecting inactive peers of a tunneled communication session, while allowing for a scalable tunneled protocol that includes split control plane nodes and data plane nodes are described herein. A method according to a technique described herein may include establishing a communication session between a first node and a second node in a network such that control plane traffic of the communication session flows through one or more control nodes and data plane traffic of the communication session flows through one or more data nodes different than the one or more control nodes. The method may also include receiving, at a control node, an indication from a data node that a probe message is to be generated. The probe message may be configured to determine data plane connectivity in the communication session. Additionally, the control node may generate the probe message and send it to the first node.

Abstract: According to certain embodiments, a system includes one or more processors and one or more computer-readable non-transitory storage media comprising instructions that, when executed by the one or more processors, cause one or more components to perform operations including executing a software process of a secondary instance, the secondary instance running in parallel with a primary instance and associated with a plurality of cores including a bootstrap core, registering a non-maskable interrupt for the bootstrap core in the secondary instance, determining whether the secondary instance is in a fault state, wherein, if the secondary instance is in the fault state, halting the plurality of cores associated with the secondary instance, without impact to the primary instance, and recovering the bootstrap core by switching a context of the bootstrap core from the secondary instance to the primary instance via the non-maskable interrupt.

Abstract: Techniques for in-situ passive performance measurement are described. In one embodiment, a method includes receiving a data packet at a first network element, determining whether measurement information is to be collected for the data packet, providing one or more measurement fields for the data packet based on a determination that measurement information is to be collected for the data packet in which at least one measurement field identifies a measurement type, and forwarding the data packet to a second network element. The method further includes determining, by the second network element, the measurement type for the data packet, and performing one or more actions based on the measurement type.

Abstract: Embodiments identify a station that rotates an over the air station address. As address rotation was not originally designed into wireless networks, the rotation can introduce communication challenges for the station. The embodiments derive that traffic referencing two different over the air station addresses are associated with a single common station. This is accomplished by determining a similarity between properties of two sets of traffic. A first set of traffic references the first over the air station address and a second set of traffic references the second over the air station address. If the properties common across the two sets of traffic indicate sufficient similarity, the embodiments determine that both sets of traffic are associated with a single device. Network configuration of the device is then adjusted based on the determination.

Abstract: A method can include receiving, at a workflow controller, a machine learning workflow, the machine learning workflow associated with a first task and a second task. The first task is training a machine learning model and the second task is deploying the model. The method can include segmenting, by the workflow controller, the machine learning workflow into a first sub-workflow associated with the first task and a second sub-workflow associated with the second task, assigning a first workflow agent to the first sub-workflow and assigning a second workflow agent to the second sub-workflow, selecting, by the first workflow agent and based on first resources needed to perform the first task, a first cluster for performing the first task and selecting, by the second workflow agent and based on second resources needed to perform the second task, a second cluster for performing the second task.

Abstract: In one embodiment, a method includes transmitting pulse power on two wire pairs, the pulse power comprising a plurality of high voltage pulses with the high voltage pulses on the wire pairs offset between the wire pairs to provide continuous power, performing low voltage fault detection on each of the wire pairs between the high voltage pulses, and transmitting data on at least one of the wire pairs during transmittal of the high voltage pulses. Data transmittal is suspended during the low voltage fault detection.

Abstract: Techniques for using global virtual network instance (VNI) labels in a multi-domain network to route network data with a multi-tenant network overlay are described herein. A routing device provisioned in a network domain of the multi-domain network may register with a service discovery system of the network domain for use of network configuration data to establish routes through the multi-domain network with network nodes. Each network domain of the multi-domain network may include an application programming interface (API) server for processing API requests to make changes to configurations of a network domain. A border gateway protocol (BGP) large community may be utilized to encode global VNI labels, network addresses, local next hop nodes, and/or additional network information and sent to routing devices provisioned in separate network domains. A service chain may be signaled by global VNI labels to route network traffic through various services prior to reaching a destination endpoint.

Abstract: Techniques, methods, and systems for managing a set of data network nodes in a Network Management System (NMS). In some examples, a method may include receiving, at the network orchestrator, a service invocation for a service transaction associated with a transaction object; storing, by the network orchestrator, service metadata as part of the transaction object; determining whether there is a service metadata conflict associated with the transaction object; and in response to determining that there is the service metadata conflict associated with the transaction object, retrying the service transaction; or in response to determining that there is no service metadata conflict associated with the transaction object, applying the service metadata to one or more nodes of the set of data nodes.

Abstract: Optimizing modify bearer request handling may be provided. A Modify Bearer Request (MBR) may be received by a Serving Gateway (SGW) for a User Equipment (UE). Then a current User Location Information (ULI) may be compared, in the MBR, to a previous ULI. It may then be determined, based on the comparison, determining, if the current ULI and the previous ULI are included in a same Extended-ULI (E-ULI). Next, when the current ULI and the previous ULI are included in the same E-ULI, the MBR may be suppressed from being forwarded to the Packet Data Network (PDN) Gateway (PGW).

Abstract: Load aware load balancing may be provided. Flow duration data associated with a plurality of flows associated with a plurality of servers may be obtained. Then a plurality of queue lengths respectively associated with the plurality of servers may be obtained. Next, a Shortest Expected Delay (SED) score may be determined for each of the plurality of servers based on the flow duration data and the plurality of queue lengths. A flow may then be assigned to a one of the plurality of servers having the lowest SED score.

Abstract: This technology allows time synchronization in passive optical networks (“PON”). A first Ethernet device timestamps and transmits a packet to a second Ethernet device via the PON. The first Ethernet device transmits the packet to a small form-factor pluggable (“SFP”) device within the PON and connected to the first Ethernet device. The SFP device determines a transmission time to a second SFP device and modifies a correction field (“CF”) of the packet by subtracting an ingress time and the transmission time from the CF. The packet is transmitted to the second SFP device, which modifies the CF by the addition of an egress time. The modified CF value represents the real-time transmission delay incurred in the SFP devices. The packet is transmitted to a second Ethernet device to synchronize a clock using the timestamp and the CF value in accordance with the PTP/IEEE-1588 standard.

Abstract: Techniques for identifying network congestion and adapting network performance to relieve the network congestion are described. As described, a network element such as a switch reports network congestion indicators such as link level control frames to a network controller. The network controller uses the network congestion indicators reported from the network elements to identify congestion points, data traffic, and data flows experiencing congestion at a network level. The network controller then determines optimized control parameters for the network in order to reduce or alleviate the congestion at the congestion points.

Abstract: The present technology is generally directed to optimizing a non-3GPP untrusted Wi-Fi to 5G system handover followed by Evolved Packet System (EPS) fallback, more specifically, to delaying removal of the Wi-Fi session resources and creating a voice flow as part of the EPS fallback.

Abstract: A system and method for dynamic enablement of a RLC mode of a Data Radio Bearer (DRB) based on UE radiofrequency (RF) conditions. A threshold value for a network characteristic is provided to a gNodeB. Changes in the network characteristic correlates to changes in RF channel conditions of the UE. The trigger configures the gNodeB to identify when the network characteristic meets the threshold value for selectively controlling operation of the gNodeB at one of a plurality of different operation modes including an initial radio link control (RLC) mode based on the network characteristic. A Protocol Data Unit (PDU) session is established with the gNodeB operating in an initial RLC mode with the possibility to dynamically switch to a different RLC mode based on RF channel conditions.

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: This disclosure describes techniques for improving convergence of Protocol Independent Multicast assert state information in multicast groups. A method includes forwarding, by a router, a PIM join message originating from a destination host and stores distribution tree information based on the join message. The method further includes participating, by the router, in a Protocol Independent Multicast (“PIM”) assert election among a plurality of routers and storing, by the router, PIM assert state information based on an outcome of the PIM assert election. The method further includes acquiring, by the router, routing information base (“RIB”) convergence. The method further includes triggering by the router, or causing, by the router, another router to trigger, a PIM assert among the plurality of routers. The method further includes re-converging, by the router, with PIM assert states among the plurality of routers and storing, by the router, converged PIM assert state information.