Abstract: In one embodiment, a supervisory device in a network forms a virtual access point (VAP) for a node in the network. A set of access points (APs) in the network are mapped to the VAP as part of a VAP mapping and the node treats the APs in the VAP mapping as a single AP for purposes of communicating with the network. The supervisory device receives measurements from the APs in the VAP mapping regarding communications associated with the node. The supervisory device identifies a movement of the node based on the received measurements from the APs in the VAP mapping. The supervisory device adjusts the set of APs in the VAP mapping based on the identified movement of the node.

Abstract: Methods and apparatus for use in reducing signal latency in a mobile network with use of localized Unified Data Management (UDM) entities are described. For example, the technique may employ a plurality of localized UDMs, where each localized UDM is associated with a unique location area. A localized UDM provides for storage of, in a localized Unified Data Repository (UDR), subscriber profile data associated with a subscriber of user equipment (UE). The subscriber profile data stored in the localized UDR may be a replica or copy of at least a subset of subscriber profile data for the subscriber stored in a UDR of a “centralized” UDM. Query access to the localized UDR may be provided for network functions (NFs) or subscriber/UEs. The replica or copy of subscriber profile data may be stored in the localized UDR for those subscribers having use in the location area.

Abstract: A method comprises collecting, by a computing device located at an edge of a network, data items corresponding to information transmitted by endpoints using the network, generating, by the computing device, a probabilistic hierarchy using the data items, generating, by the computing device using the probabilistic hierarchy and natural language data, a similarity metric, generating, by the computing device using the probabilistic hierarchy, the natural language data, and the similarity metric, an ontology, detecting, by the computing device using the ontology, an anomaly, and in response to detecting the anomaly, sending a notification.

Abstract: Various systems and methods for bypassing one or more non-capable nodes. For example, one method involves a capable node determining that an adjacent node is non-capable, where capable nodes are configured to implement a data plane capability and non-capable nodes are not. The method then involves identifying a downstream node that is capable. The downstream node is on a shortest path. The method also involves generating information that identifies a tunnel to the downstream node.

Abstract: In one aspect, a system for identifying a root cause of a performance issue in a monitored entity is disclosed. The system can detect a performance issue with the monitored entity running in a monitored environment of networked entities; receive a plurality of datatypes and associated data for each entity, the plurality of datatypes include metrics, events, logs, snapshots, and configurations; provide a dashboard user interface to display the datatypes and associated data for each entity as user selectable items; receive user input through the dashboard user interface that indicate a selection of two of the datatypes for performing correlation analysis; perform the correlation analysis using the received user selection of the two of the datatypes; identify a candidate root cause of the performance issue based on the correlation analysis; and display the identified candidate root cause through the dashboard user interface.

Abstract: In one embodiment, a device in a network determines that traffic sent via a first label switched path should be sent via a new label switched path. The device sends the traffic along the new label switched path using a label stack that indicates one or more adjacency segments or interface binding labels. A particular node along the new label switched path is configured to forward the traffic via a particular interface of the node based on a corresponding interface binding label or adjacency segment indicated by the traffic. The device completes a switchover from the first path to the new path.

Abstract: In one embodiment, a device in a network maintains a plurality of applications executed by the device. The device associates the plurality of applications with a node in the network. The device schedules a time period during which a particular one of the applications is authorized to access the node associated with the applications. The device relays data packets between the node and the particular application during the scheduled time period.

Abstract: A method is described that includes receiving at a network element a transmission control protocol (“TCP”) packet with TCP options set on a link between a controller and a destination node. If the network element comprises a transit node, the method includes comparing a bandwidth value indicated in a TCP options field of the received TCP packet with an outgoing link bandwidth of the network element. If the bandwidth value indicated in the TCP options field is greater than the outgoing link bandwidth of the network element, the method includes updating the bandwidth value in the TCP options field to be equal to the outgoing link bandwidth of the network element, and forwarding the packet to a next network element. If the bandwidth value indicated in the TCP options field is not greater than the outgoing link bandwidth, the bandwidth value in the TCP options field is not changed.

Abstract: In one embodiment, a network comprises a first forwarding domain using a first data plane forwarding protocol and a second forwarding domain using a second data plane forwarding protocol different than the first data forwarding plane forwarding protocol. The first forwarding domain includes a first path node and a particular border node. The second forwarding domain includes a second path node and the particular border node. The particular border node performs Segment Routing or other protocol interworking between the different data plane forwarding domains, such as for transporting packets through a different forwarding domain or translating a packet to use a different data forwarding protocol. These forwarding domains typically include Segment Routing (SR) and SR-Multiprotocol Label Switching (SR-MPLS). Paths through the network are determined by a Path Computation Engine and/or based on route advertisements such associated with Binding Segment Identifiers (BSIDs) (e.g.

Abstract: In one embodiment, a computing device trains a multi-class classifier (having a plurality of classes) on a training dataset, and evaluates the multi-class classifier on a testing dataset to determine a performance of each of the plurality of classes. The plurality of classes may then be partitioned into either learnable or unlearnable based on whether the performance each particular class surpasses a particular threshold, and then a predicting classifier can be trained on the training dataset, where data of the training dataset is labelled as either learnable or unlearnable based on the particular class to which the data corresponds. Accordingly, the computing device may then use the predicting classifier on a new class to predict whether samples associated with the new class are learnable or unlearnable, and may retrain the multi-class classifier with the samples associated with the new class in response to predicting that the samples are learnable.

Abstract: In a wireless local area network (WLAN) that includes one or more wireless access points capable of serving one or more wireless clients, presence of one or more instances of interference from a particular type of interferer is detected on at least one channel in an unlicensed frequency band. In response to detecting the interference, a radio resource management process is biased to continue operation of at least one of the one or more access points, or individual radios of a multi-radio access point, on the channel to make at least some use of the channel for one or more wireless clients.

Abstract: Presented herein are techniques for matching a user, e.g., a child, with an autonomous vehicle instructed to pick up the child. In an embodiment, a method includes receiving, at a server, information from an autonomous vehicle, receiving, at the server, information from a user device, receiving, at the server, information from a responsible party device, processing, by the server, the information from the autonomous vehicle, the information from the user device, and the information from the responsible party device, and based on the processing of the information from the autonomous vehicle, the information from the user device, and the information from the responsible party device, verifying, by the server, that the autonomous vehicle is matched with a user of the user device.

Abstract: In one embodiment, a device in a network receives a query walker agent configured to query information from a distributed set of devices in the network based on a query. The device executes the query walker agent to identify the query. The device updates state information of the executing query walker agent using local information from the device and based on the query. The device unloads the executing query walker agent after updating the state information. The device propagates the query walker agent with the updated state information to one or more of the distributed set of devices in the network, when the updated state information does not fully answer the query.

Abstract: In one embodiment, a computing device collects ransomware behavioral data of known ransomware, the ransomware behavioral data based on one or more file writing features, and trains a ransomware classifier with the ransomware behavioral data to detect ransomware. The computing device may then share the ransomware classifier with a detection device to cause the detection device to behaviorally detect ransomware based on applying the ransomware classifier to monitored file writing activities. In another embodiment, in response to behaviorally detecting ransomware, based on applying the ransomware classifier to monitored file writing activities, the detection device may then perform one or more ransomware mitigation measures in response to behaviorally detecting ransomware.

Abstract: Methods and network devices are disclosed for replication and switching of Internet Protocol (IP) packets in professional media networks. In one embodiment, a method includes encapsulating a unicast IP packet with a packet bit array and forwarding the encapsulated packet via a replication fabric within a network. In this embodiment, each receiver of a plurality of receivers reachable via the replication fabric is represented by a relative bit position in the packet bit array, a respective IP address is assigned to each receiver of the plurality of receivers, and the replication fabric is adapted to store disposition information mapping a relative bit position representing one or more of the plurality of receivers to IP addresses assigned to the one or more of the plurality of receivers. An embodiment of a network device includes a processor operably coupled to a network interface and adapted to perform steps of the method.

Abstract: Methods and systems are disclosed wherein TCP may approximate Reliable Transport Protocol (RTP) or UDP delivery for real-time video/data conferencing applications that have long RTT connections.

Abstract: A computer-implemented method is provided that includes receiving a telephone call placed by a device associated with a user. The user is identified based on a caller identifier obtained from the telephone call. A user identifier is determined for the user based on the caller identifier. Using the user identifier, access is made to a calendar associated with the user to determine from the calendar for the user whether there are any online meetings scheduled for the user at or near a current time. When there is at least one online meeting in the calendar for the user at or near the current time, the user is joined to the at least one online meeting, which results in connecting the telephone call to an audio portion of the at least one online meeting served by a meeting service.

Abstract: Profile prioritization in a roaming consortium environment may be provided. First, a client device may initiate a network discovery with a network device. Next, the client device may receive in response to initiating the network discovery, a response. The response may comprise an organization identifier and a plurality of response access identifiers corresponding to the organization identifier. A one of the plurality of response access identifiers may be labeled as preferred. Then the client device may determine to access the network based on the organization identifier. The client device may then select, from a plurality of profiles, a profile for accessing the network. The selected profile may have a profile access identifier corresponding to the one of the plurality of response access identifiers labeled as preferred.

Abstract: In one embodiment, a computing device determines a plurality of probability-based trajectories a mobile device could traverse through a plurality of access point (AP) cells within a given area depending on an entry point of the mobile device into the given area. A predictive dwell time may also be associated to each AP cell based on how long a mobile device is expected to remain within the respective AP cell. Based on i) current locations of mobile devices, ii) the plurality of probability-based trajectories a mobile device could traverse through the plurality of AP cells, and iii) the predictive dwell time of each AP cell, the computing device can compute a probability of mobile device density surpassing a potential flash crowd threshold within each AP cell at any given future time. In response, the computing device may then perform one or more mitigation actions.

Abstract: A network management entity is configured to communicate with one or more network security devices. Each network security device is configured to store in a respective event queue an event for each attempt to access a network accessible destination through the security device. Each event indicates the destination of the attempted access. The management entity periodically collects from the event queues the stored events so that less that all of the events stored in the event queues over a given time period are collected. The management entity determines, based on the collected events, top destinations as the destinations that occur most frequently in the collected events. The management entity determines, based on the collected events, bottom destinations as the destinations that occur least frequently in the collected events. The management entity generates for display indications of the top destinations and generates for display indications of the bottom destinations.