Abstract: In one embodiment, an issue analysis service obtains telemetry data from a plurality of devices in a network across a plurality of time intervals. The service detects a failure event in which a device in the network is in a failure state. The service clusters the telemetry data obtained prior to the failure event into rounds according to time intervals in which the telemetry data was collected. Each round corresponds to a particular time interval. The service applies a machine learning-based classifier to each one of the rounds of clustered telemetry data to identify one or more common traits appearing in the telemetry data for each round. The service generates a trait change report indicating a change in the one or more common traits appearing in the telemetry data across the rounds leading up to the failure event.

Abstract: Techniques for dynamic prioritization of presenting devices in wireless deployments are provided. Data relating to a transmission between a first device and a second device is received, and the first device is classified as a presenting device for the transmission based on the data relating to the transmission. An access point (AP) providing connectivity to the first device is identified, and the AP is configured to prioritize traffic transmitted from the first device responsive to classifying the first device as the presenting device.

Abstract: This disclosure describes techniques for providing notifications about events that occur during an online meeting. For instance, a system may establish an online meeting, such as a video conferencing meeting, for users. While in the meeting, a first user may view video of a second user and determine that the second user is experiencing an emergency event. As such, a user device of the first user may receive an input indicating that the emergency event is occurring with the second user. The system may receive the indication from the user device and verify that the emergency event is occurring. Additionally, the system may then send a notification to emergency personnel that indicates at least that the emergency event is occurring and a location of the second user. Furthermore, the system may send notification(s) to contact(s) associated with the second user that indicate at least that the emergency event is occurring.

Abstract: This disclosure describes techniques for diagnosing a presence or malfunction of a network node. In an example method, a first network node receives an indication of a diagnostic transmission originating from a second network node. The second network node further receives a forwarded transmission corresponding to the diagnostic transmission. The first network node diagnoses at least one of a presence or a malfunction of an intermediary node between the first network node and the second network node based on at least one of the indications of the diagnostic transmission or the forwarded transmission.

Abstract: In one embodiment, an issue analysis service determines that an issue exists with a device in a network. The service searches a decision tree for a solution to the issue, wherein branch nodes of the decision tree comprise diagnostic checks. The service clusters, based on a determination that a solution to the issue does not exist in the decision tree, telemetry for the device with telemetry for one or more other devices that also experienced the issue. The service uses a neural network to identify a difference between the clustered telemetry and telemetry from one or more devices for which the issue was resolved. The service adds a leaf node to the decision tree with the identified difference as a solution to the issue.

Abstract: This disclosure describes techniques for monitoring communications in an application cloud infrastructure. The techniques may include determining whether a performance issue associated with the communications is related to an application server for a hosted application, or to a computing network that transmits the communications across the application cloud infrastructure. The techniques may also further include testing to define a performance issue, and/or taking action in response to a performance issue, including potentially mitigating the performance issue. As such, monitoring communications may help improve network performance by efficiently identifying and isolating instances of potential performance degradation.

Abstract: This disclosure describes techniques for monitoring communications in an application cloud infrastructure. The techniques may include determining whether a performance issue associated with the communications is related to an application server for a hosted application, or to a computing network that transmits the communications across the application cloud infrastructure. The techniques may also further include testing to define a performance issue, and/or taking action in response to a performance issue, including potentially mitigating the performance issue. As such, monitoring communications may help improve network performance by efficiently identifying and isolating instances of potential performance degradation.

Abstract: Techniques for identifying a trusted SSID for a wireless network are disclosed. Prior to establishing a connection with a wireless network comprising a service set identifier (SSID), a network message is received at a wireless station (STA), from an access point (AP) associated with the wireless network. The STA identifies an encrypted identifier in the network message. The STA validates the encrypted identifier, and in response determines that the AP corresponds to a trusted wireless network. The SSID is designated as trusted, at the STA.

Abstract: Aspects of the disclosed technology address the problems of manually identifying and optimizing service chain (SC) performance bottlenecks by providing solutions for automatically identifying and tuning various SC parameters. In some aspects, a SC optimization process of the disclosed technology includes the replication or cloning of a SC for which traffic flow is to be optimized. Traffic flows for the production chain can then be simulated over one or more SC clones to identify and tune individual system parameters, for example, to determine if the simulated changes produce a positive, negative, or neutral change in flow performance. Systems and machine-readable media are also provided.

Abstract: Disclosed are systems, methods and non-transitory computer-readable mediums for dynamically presenting and updating a directed time graph displayed in a graphical user interface. In some examples, the method can include displaying a suggested path within a graphical user interface on a computer screen, the suggested path can include outstanding issues of elements of a network. The displaying the suggested path can include determining based on one or more factors an efficient ordering of the outstanding issues and ordering the outstanding issues based on the one or more factors. The method can also include monitoring, at regular intervals, updates to the one or more outstanding issues and automatically updating the suggested path, by a processor, based on the updates to the one or more outstanding issues.

Abstract: In one embodiment, a service classifies a device in a network as human-controlled or self-controlled. The service also classifies an online resource as designed for access by human-controlled devices or by self-controlled devices. The service obtains traffic data regarding an attempt by the device to access the online resource via the network. The service determines that the attempt by the device to access the online resource is a security violation, based on the classifications of the device and the online resource. The service initiates a mitigation action in the network for the security violation.

Abstract: In one embodiment, an issue analysis service determines that an issue exists with a device in a network. The service searches a decision tree for a solution to the issue, wherein branch nodes of the decision tree comprise diagnostic checks. The service clusters, based on a determination that a solution to the issue does not exist in the decision tree, telemetry for the device with telemetry for one or more other devices that also experienced the issue. The service uses a neural network to identify a difference between the clustered telemetry and telemetry from one or more devices for which the issue was resolved. The service adds a leaf node to the decision tree with the identified difference as a solution to the issue.

Abstract: In one embodiment, a supervisory service of a parking area may send a light fidelity (Li-Fi) based advertisement indicative of an offer to send video streams of the parking area to an autonomous vehicle. The supervisory service may receive an acceptance of the offer by the autonomous vehicle that includes an identifier for the autonomous vehicle. The supervisory service may identify one or more video streams of the parking area as associated with the autonomous vehicle based in part on a location of the autonomous vehicle in the parking area. The supervisory service may annotate the one or more identified video streams with metadata regarding a feature of the parking area. The supervisory service may send the annotated one or more video streams to the autonomous vehicle, wherein the autonomous vehicle uses the metadata of the annotated one or more video streams to avoid the feature of the parking area.

Abstract: In one embodiment, a device in a network maintains an information module to recommend system actions for a monitored system in the network. The information module generates recommendations using an information library database populated by one or more data sources. The device assesses behaviors of the information module and determines a review cadence for the information library database based on the assessed behaviors of the information module. The device updates the information library database according to the determined review cadence.

Abstract: Aspects of the disclosed technology address the problems of manually identifying and optimizing service function chaining (SFC) performance in response to changes in traffic profiles. In one aspect of the present disclosure, a method includes monitoring, by a first network component, incoming data packets; detecting, by the first network component, a change in a traffic profile of the incoming data packets; generating, by the first network component, in-band information on changes in the traffic profile; and transmitting, by the first network component, the in-band information with one or more data packets of the incoming data packets, the in-band information being used by a second network component to adjust one or more corresponding settings for servicing the incoming data packets.

Abstract: In one embodiment, a device of an electric vehicle requests in-motion charging of the electric vehicle. The device receives an indication of a charging vehicle able to provide in-motion charging to the first electric vehicle. The device coordinates in-motion docking of the electric vehicle to the charging vehicle. The device supervises in-motion charging of the electric vehicle by the charging vehicle.

Abstract: Aspects of the disclosed technology address the problems of manually identifying and optimizing service chain (SC) performance bottlenecks by providing solutions for automatically identifying and tuning various SC parameters. In some aspects, a SC optimization process of the disclosed technology includes the replication or cloning of a SC for which traffic flow is to be optimized. Traffic flows for the production chain can then be simulated over one or more SC clones to identify and tune individual system parameters, for example, to determine if the simulated changes produce a positive, negative, or neutral change in flow performance. Systems and machine-readable media are also provided.

Abstract: A computer-implemented method is provided for a network controller to implement an update on network elements with minimal disruption. The network controller receives a request to install the update on a number of network elements in one or more networks. Installing the update in each respective network element removes it from operation for an outage duration of time. The network controller identifies at least one set of critical network elements based on business factors associated with removing the critical network elements from operation. The network controller generates an update plan including timing for installing the update on each respective network element. The timing is based on minimizing the outage duration for the set of critical network elements. The network controller installs the update in each network element according to the timing of the update plan.

Abstract: In one embodiment, a first vehicle makes, using a first machine learning-based model, a determination that raw image data captured by the first vehicle does not indicate the presence of a driving hazard. The first vehicle sends a hazard assessment request to a second vehicle in communication proximity of the first vehicle that includes the raw image data. The first vehicle receives a hazard detection response from the second vehicle that indicates a driving hazard identified by the second vehicle by applying a second machine learning-based model to the raw image data included in the hazard assessment request. The first vehicle adjusts a path of travel of the first vehicle to avoid the driving hazard identified by the second vehicle.

Abstract: Presented herein are techniques for enabling delegated access control of an enterprise network. In particular, data representing a trust chain formed between a local domain and a remote domain is stored in an identity management system. The local domain has an associated secure enterprise computing network and wherein the trust chain identifies one or more outside entities associated with the remote domain that are authorized to access the secure enterprise computing network. The identity management system receives a request for access to the secure enterprise computing network by a first outside entity of the one or more outside entities associated with the remote domain. Access by the outside entity to the secure enterprise computing network is controlled/determined based on an analysis of the trust chain.