A method includes obtaining, by a management device, sub-interface information that includes a correspondence between an identifier of a first sub-interface of a first device and a first network slice identifier, a correspondence between an identifier of a second sub-interface of a second device and a second network slice identifier, and information indicating that the first sub-interface is directly connected to the second sub-interface, and determining, by the management device, a network slice topology based on the obtained sub-interface information.

Technologies for dynamic accelerator selection include a compute sled. The compute sled includes a network interface controller to communicate with a remote accelerator of an accelerator sled over a network, where the network interface controller includes a local accelerator and a compute engine. The compute engine is to obtain network telemetry data indicative of a level of bandwidth saturation of the network. The compute engine is also to determine whether to accelerate a function managed by the compute sled. The compute engine is further to determine, in response to a determination to accelerate the function, whether to offload the function to the remote accelerator of the accelerator sled based on the telemetry data. Also the compute engine is to assign, in response a determination not to offload the function to the remote accelerator, the function to the local accelerator of the network interface controller.

Technologies for dynamic accelerator selection include a compute sled. The compute sled includes a network interface controller to communicate with a remote accelerator of an accelerator sled over a network, where the network interface controller includes a local accelerator and a compute engine. The compute engine is to obtain network telemetry data indicative of a level of bandwidth saturation of the network. The compute engine is also to determine whether to accelerate a function managed by the compute sled. The compute engine is further to determine, in response to a determination to accelerate the function, whether to offload the function to the remote accelerator of the accelerator sled based on the telemetry data. Also the compute engine is to assign, in response a determination not to offload the function to the remote accelerator, the function to the local accelerator of the network interface controller.

Global Internet of things (IoT) quality of service (QoS) is provided through self-forming, self-healing, and/or collaborative edge IoT gateways. Moreover, global IoT services are provided by logically extending cellular networks with roaming partners to backhaul, track, and/or manage the globally deployed edge IoT gateways. In one aspect, real-time QoS and/or monitoring capabilities for the global IoT services can be provided through a communication between the edge IoT gateways and an edge gateway controller deployed within a cloud. The edge IoT gateways form a structured mesh network to coordinate workload execution under control of the edge gateway controller, which can facilitate a highly efficient QoS and/or SLA management for mobile IoT sensors, to provide a secure monitoring and/or diagnostic capability for the global IoT services.

An architecture for providing an on-demand dynamic cloudlet instantiation by leveraging a grouping of software defined network devices and their respective associated analytics modules. A method can comprise receiving quality of service data representing a 5G small cell device of a group of 5G small cell devices; generating a policy rule representing a predictive policy to facilitate an instantiation of a dynamic on-demand cloudlet node into a fog of dynamic on-demand cloudlet node instantiations; and facilitating the instantiation of the dynamic on-demand cloudlet node into the fog, by a hybrid fiber coaxial device, based on the policy rule and an indication received from the hybrid fiber coaxial that a traffic surge in communications with the 5G small cell device has occurred.

An architecture for providing an on-demand dynamic cloudlet instantiation by leveraging a grouping of software defined network devices and their respective associated analytics modules. A method can comprise receiving quality of service data representing a 5G small cell device of a group of 5G small cell devices; generating a policy rule representing a predictive policy to facilitate an instantiation of a dynamic on-demand cloudlet node into a fog of dynamic on-demand cloudlet node instantiations; and facilitating the instantiation of the dynamic on-demand cloudlet node into the fog, by a hybrid fiber coaxial device, based on the policy rule and an indication received from the hybrid fiber coaxial that a traffic surge in communications with the 5G small cell device has occurred.

A technique involves modular storage of network service plan components and provisioning of same. A subset of the capabilities of a service design system can be granted to a sandbox system to enable customization of service plan offerings or other controls.

In one embodiment, a device obtains telemetry data that results from an edge router sending probes to a cloud-hosted application via a plurality of points of presence. The device makes, based on the telemetry data, predictions as to whether use of each of the plurality of points of presence by the edge router to access the cloud-hosted application will result in a violation of a service level agreement. The device selects, based on the predictions, a particular point of presence from among the plurality of points of presence that the edge router should use to access the cloud-hosted application during a time window. The device causes the edge router to access the cloud-hosted application via the particular point of presence during the time window.

This disclosure describes techniques for resolving discrepancies that occur to interrelated computing resources from computing resource drift. Users may describe computing resources in an infrastructure template. However, computing resource drift occurs when “out-of-band” modifications are made to the computing resources and are not reflected in the infrastructure template. To resolve discrepancies between the infrastructure template and the out-of-band modifications to the computing resources, a notification may be output to a user account associated with the computing resources detailing the differences. An updated infrastructure template may be received that resolves the differences, such as by including configuration settings that reflect a current state of the computing resources. The computing resources may then execute a workflow using the updated template, such that the workflow is executed on all of the computing resources in a current state.

This disclosure describes techniques for resolving discrepancies that occur to interrelated computing resources from computing resource drift. Users may describe computing resources in an infrastructure template. However, computing resource drift occurs when “out-of-band” modifications are made to the computing resources and are not reflected in the infrastructure template. To resolve discrepancies between the infrastructure template and the out-of-band modifications to the computing resources, a notification may be output to a user account associated with the computing resources detailing the differences. An updated infrastructure template may be received that resolves the differences, such as by including configuration settings that reflect a current state of the computing resources. The computing resources may then execute a workflow using the updated template, such that the workflow is executed on all of the computing resources in a current state.