Technologies for managing sensor and telemetry data on an edge networking platform

{
  "publication_number": "US11082525B2",
  "country": "US",
  "kind": "B2",
  "title": "Technologies for managing sensor and telemetry data on an edge networking platform",
  "abstract": "Technologies for managing telemetry and sensor data on an edge networking platform are disclosed. According to one embodiment disclosed herein, a device monitors telemetry data associated with multiple services provided in the edge networking platform. The device identifies, for each of the services and as a function of the associated telemetry data, one or more service telemetry patterns. The device generates a profile including the identified service telemetry patterns.",
  "claims": [
    "1. A device comprising: circuitry to: monitor telemetry data associated with a plurality of services provided in an edge network; identify, for each of the plurality of services and as a function of the associated telemetry data, one or more service telemetry patterns; generate a machine learning model to identify a first service telemetry pattern of change associated with a sensor data; predict a second service telemetry pattern based on the generated machine learning model; generate a profile including the first and second service telemetry patterns; evaluate, for one of the plurality of services, the monitored telemetry data for a change in activity relative to the first and second service telemetry patterns; and upon a determination that the change in activity is detected, perform an action responsive to the change.",
    "2. The device of claim 1, wherein to perform the action responsive to the change includes to determine the action as a function of an identified configuration state associated with the change in activity and a policy.",
    "3. The device of claim 1, wherein to perform the action responsive to the change further includes to reconfigure, as a function of the change, resources assigned to the one of the plurality of services.",
    "4. The device of claim 1, wherein to perform the action responsive to the change further includes to migrate the one of the plurality of services to a second device.",
    "5. The device of claim 1, wherein to monitor the telemetry data associated with the plurality of services provided in the edge network includes to monitor the telemetry data for one or more resources registered to a tenant.",
    "6. The device of claim 5, wherein the circuitry is further to store a public key associated with the tenant in a data store.",
    "7. The device of claim 6, wherein the circuitry is further to: sign, using a private key associated with the one or more resources, the telemetry data and a corresponding timestamp; and encrypt, using the public key associated with the tenant, the signed telemetry data and the corresponding timestamp.",
    "8. The device of claim 5, wherein the circuitry is further to: monitor thermal telemetry data in the one or more resources; evaluate the monitored thermal telemetry data in each of the one or more resources against a corresponding threshold; and upon a determination that the corresponding threshold is exceeded, determine, from a service level agreement associated with the resources, a thermal budget for the one or more resources.",
    "9. The device of claim 8, wherein the circuitry is further to, upon a determination that the thermal budget is exceeded, notify an orchestrator device of the one or more resources exceeding the corresponding threshold.",
    "10. The device of claim 8, wherein the circuitry is further to, upon a determination that the thermal budget is not exceeded, perform one or more cooling techniques on the one or more resources to reduce a thermal load thereon.",
    "11. The device of claim 1, wherein the circuitry is further to: receive sensor data from one or more edge devices connected with the edge network; store the sensor data in a data store; filter the stored sensor data; and send the filtered sensor data to a core data center in the edge network.",
    "12. The device of claim 11, wherein to filter the stored sensor data, the circuitry is to: identify, from the sensor data, one or more patterns; and apply a filtering technique on the sensor data as a function of the identified one or more patterns.",
    "13. The device of claim 12, wherein to identify, from the sensor data, the one or more patterns, the circuitry is to identify, based on a machine learning technique, the one or more patterns.",
    "14. The device of claim 12, wherein to identify, from the sensor data, the one or more patterns, the circuitry is to identify, as a function of a type of the sensor data, the one or more patterns.",
    "15. One or more machine-readable storage media storing a plurality of instructions, which, when executed, cause a device to: monitor telemetry data associated with a plurality of services provided in an edge network; identify, for each of the plurality of services and as a function of the associated telemetry data, one or more service telemetry patterns; generate a machine learning model to identify a first service telemetry pattern of change associated with a sensor data; predict a second service telemetry pattern based on the generated machine learning model; generate a profile including the first and second service telemetry patterns; evaluate, for one of the plurality of services, the monitored telemetry data for a change in activity relative to the first and second service telemetry patterns; and upon a determination that the change in activity is detected, perform an action responsive to the change.",
    "16. The one or more machine-readable storage media of claim 15, wherein to monitor the telemetry data associated with a plurality of services provided in the edge network includes to monitor the telemetry data for one or more resources registered to a tenant, and wherein the plurality of instructions, when executed, cause the device to: store a public key associated with the tenant in a data store; sign, using a private key associated with the one or more resources, the telemetry data and a corresponding timestamp; and encrypt, using the public key associated with the tenant, the signed telemetry data and the corresponding timestamp.",
    "17. The one or more machine-readable storage media of claim 15, wherein the plurality of instructions, when executed, cause the device to: monitor thermal telemetry data in the one or more resources; evaluate the monitored thermal telemetry data in each of the one or more resources against a corresponding threshold; upon a determination that the corresponding threshold is exceeded, determine, from a service level agreement associated with the resources, a thermal budget for the one or more resources; upon a determination that the thermal budget is exceeded, notify an orchestrator device of the one or more resources exceeding the corresponding threshold; and upon a determination that the thermal budget is not exceeded, perform one or more cooling techniques on the one or more resources to reduce a thermal load thereon.",
    "18. The one or more machine-readable storage media of claim 15, wherein the plurality of instructions, when executed, cause the device to: receive sensor data from one or more edge devices connected with the edge network; store the sensor data in a data store; identify, from the sensor data, one or more patterns; apply a filtering technique on the sensor data as a function of the identified one or more patterns; and send the sensor data with the filtering technique applied to a core data center in the edge network.",
    "19. A device comprising: means for monitoring telemetry data associated with a plurality of services provided in an edge network; means for identifying to: identify, for each of the plurality of services and as a function of the associated telemetry data, one or more service telemetry patterns; generate a machine learning model to identify a first service telemetry pattern of change associated with a sensor data; and predict a second service telemetry pattern based on the generated machine learning model; and means for generating a profile including the identified first and second service telemetry patterns; means for evaluating, for one of the plurality of services, the monitored telemetry data for a change in activity relative to the first and second service telemetry patterns; and means for performing, upon a determination that the change in activity is detected, an action responsive to the change."
  ],
  "description_excerpt": "Edge computing provides techniques for processing resources at a location in closer network proximity to a requesting device, as opposed to a centralized location in a cloud network. Doing so ensures that devices receive critical data relatively quickly. For example, an edge device may include multiple sensors that collect various data, such as temperature measures over time. The edge device may transmit the sensor data to the edge network, and edge compute resources in the network further processes the sensor data. For instance, the compute resources may aggregate the sensor data with the sensor data of other devices. Continuing the example, the compute resources may analyze the aggregated data to generate a weather map in a smart city architecture.\n\nGenerally, each component in the edge network is subject to various performance requirements, such as those specified in a service level agreement (SLA), a quality-of-service (QoS) specification, and the like. For example, a QoS requirement may specify that edge device requests are to be serviced under a given latency measure. Performance monitors in the edge network may collect telemetry data from each component. Doing so allows orchestrators in the edge network to adjust resource allocation and usage accordingly to ensure that the performance requirements are satisfied.\n\nThe concepts described herein are illustrated by way of example and not by way of limitation in the accompanying figures. For simplicity and clarity of illustration, elements illustrated in the figures are not necessarily drawn to scale.",
  "cpc": [
    "H04L 67/303",
    "H04L 63/0428",
    "H04L 63/123",
    "H04L 63/1408",
    "H04L 67/10",
    "H04L 67/12",
    "H04L 9/0825",
    "H04L 9/3247",
    "H04L 9/3297",
    "H04W 12/02",
    "H04W 12/10"
  ],
  "ipc": [
    "H04L 29/06",
    "H04L 29/08",
    "H04L 9/08"
  ],
  "assignees": [
    "Intel Corp"
  ],
  "inventors": [
    "Ramanathan Sethuraman",
    "Timothy Verrall",
    "Ned M. Smith",
    "Thomas Willhalm",
    "Brinda Ganesh",
    "Francesc Guim Bernat",
    "Karthik Kumar",
    "Evan Custodio",
    "Suraj Prabhakaran",
    "Ignacio Astilleros Diez",
    "Nilesh K. Jain",
    "Ravi Iyer",
    "Andrew J. Herdrich",
    "Alexander Vul",
    "Patrick G. Kutch",
    "Kevin Bohan",
    "Trevor Cooper"
  ],
  "filing_date": "2019-05-17",
  "publication_date": "2021-08-03",
  "grant_date": "2021-08-03",
  "priority_date": "2019-05-17",
  "application_number": "US-201916415138-A",
  "family_id": "67843636",
  "cited_by_count": 14,
  "citations": [
    "US7490073B1",
    "US20070078943A1",
    "US20130204997A1",
    "US20140277788A1",
    "US20160112263A1",
    "US20160287189A1",
    "US20180309506A1",
    "US9910470B2",
    "US20170353367A1",
    "US20180026913A1",
    "US20190281078A1",
    "US20190306011A1",
    "US20190044812A1",
    "US20200344252A1"
  ]
}