Abstract: Techniques for managing resource utilization across heterogeneous physical hosts are described. Resource utilization of a first plurality of physical hosts in a provider network may be monitored, each physical host comprising a plurality of resources. A future resource utilization can be determined, the future resource utilization including quantities of a plurality of resource types. The future resource utilization can be matched to a plurality of physical host types, each physical host type associated with a different plurality of resources. A second plurality of physical hosts corresponding to the plurality of physical host types can be deployed to the provider network.

Abstract: A component of a computing service obtains respective indications of placement policies that contain host selection rules for application execution environments such as guest virtual machines. With respect to a request for a particular application execution environment, a group of applicable placement policies is identified. A candidate pool of hosts is selected using the group of placement policies, and members of the pool are ranked to identify a particular host on which the requested application execution environment is instantiated.

Abstract: Disclosed are various embodiments for using unmanned vehicles to manage radio-based network infrastructure. In one embodiment, a determination is made to add coverage to a radio-based network via a radio unit. An unmanned vehicle carrying the radio unit as a payload is instructed to travel to a particular location. The unmanned vehicle is instructed to deliver the radio unit to the particular location. The radio unit is activated to add the coverage to the radio-based network.

Abstract: Techniques are described for enabling users of a service provider to manage placement preferences used to launch virtualized computing resources into a fleet of dedicated physical servers. Users can use one or more service provider interfaces to provide input indicating various placement preferences associated with a fleet of physical servers dedicated for use by a user of the service provider. These placement preferences can be used to determine at which physical server virtualized computing resources—for example, virtual machine (VM) instances, containers, and the like—are launched in response to launch requests. Among other benefits, the ability to configure customized placement preferences enables users to better satisfy various performance, reliability, software licensing, and other considerations users may have with respect to how their resources are placed within physical server fleets.

Abstract: Techniques are described for enabling users of a cloud provider network to discover “availability groups” provided by a cloud provider network and to request the launch of computing resources into selected availability groups. Some cloud provider networks are expanding the definition of traditional “availability zones” to include new types of availability zones representing various types of provider substrate extension edge locations—including, for example, cloud-provider managed substrate extensions associated with separate control planes, 5G-enabled provider substrate extensions connected to communications service provider networks, and the like. Availability groups can be used to represent various defined collections these new types of provider substrate extensions, where each availability group may be defined such that includes a set of provider substrate extensions with a similar set of characteristics and capabilities.

Abstract: Disclosed are various embodiments for automated deployment of radio-based networks. In one embodiment, a request to provision a radio-based network for a customer by a provider according to a network plan is received via an application programming interface (API) of a cloud provider network. An arrangement of a plurality of cells for the customer is determined. Respective antennas and radio units for individual ones of the plurality of cells are preconfigured to implement the radio-based network before shipping the respective antennas and the radio units to the customer.

Abstract: Disclosed are various embodiments relating to an intersection of on-demand network slicing and content delivery. In one embodiment, in response to an application programming interface (API) request, a network slice is provisioned with a quality-of-service requirement in a radio-based network having a radio access network and an associated core network. Also in response to the API request, a transfer of content to a content delivery service at an edge location in the radio-based network is initiated in order to meet the quality-of-service requirement for the network slice.

Abstract: Disclosed are various embodiments for managing computing capacity in radio-based networks and associated core networks. In one embodiment, it is determined that a set of computing hardware implementing a radio-based network for a customer has an excess capacity. At least one action is implemented to reallocate the excess capacity of the computing hardware.

Abstract: Disclosed are various embodiments for managing radio-based private networks. In one embodiment, a cellular network comprises at least one cell that provides a radio-based private network coverage of a site of an organization. The system further comprises at least one computing device in a cloud provider network that implements one or more network functions for an associated core network of the radio-based private network.

Abstract: Disclosed are various embodiments that provide highly available data-processing network functions for radio-based networks. In one embodiment, a tunnel host consistently routes network traffic associated with a range of network addresses in a radio-based network to a first instance of a data-processing network function instead of a second instance of the data-processing network function. A problem with the first instance of the data-processing network function is then detected. Additional network traffic associated with the range of network addresses is redirected from the first instance of the data-processing network function to the second instance of the data-processing network function.

Abstract: A determination is made, at a first server of an extension resource group of a provider network, that a network function of a radio-based application is to be executed. A request for the network function is transmitted from a first server to a second server of the extension resource group. The network function is executed at a network function accelerator card of the second server. A result of the execution is sent to a radio unit of the radio-based application from the second server.

Abstract: Techniques for capacity bursting using a remote control plane are described. A method of capacity bursting using a remote control plane includes determining that a first control plane associated with a first area of a provider network has insufficient capacity to manage a plurality of resources in the first area, sending a request for a second control plane in a second area of the provider network to manage at least a first portion of the plurality of resources in the first area, the second control plane identified based at least on a backup hierarchy, and updating management of at least the first portion of the resources in the first area from the first control plane to the second control plane, wherein one or more references to endpoints of the first control plane are updated to be references to endpoints of the second control plane for at least the first portion of the resources managed by the second control plane.

Abstract: Techniques for distributed network connectivity monitoring of provider network edge location resources from cellular networks are described. A central service transmits test suites of commands to agents executed by test devices, which can execute the commands to test network characteristics between the test devices and target locations via one or multiple cellular communications networks. Results of the testing are sent back to the central service for processing, and the resultant metrics can be used for intelligent latency-based routing of clients, latency-based placement of resources, and/or performance monitoring of deployed resources.

Abstract: Techniques for dynamic resource movement in heterogeneous computing environments including provider substrate extensions are described. A dynamic resource movement service of a provider network monitor conditions of heterogeneous computing environments, including provider substrate extensions of the cloud provider network, to evaluate customer-provided movement policy conditions governing when to move customer application resources from these environments, where to move the resource to, and/or how to move the customer application resources. The customer-provided movement policy conditions may be based on a variety of factors, such as a latency between end-users of the customer application and the application itself.

Abstract: Disclosed are various embodiments for on-demand application-driven network slicing. In one embodiment, it is determined that an application executed in a particular computing device has a quality-of-service requirement. The particular computing device is connected to a communications network. A request is sent that causes a network slice allocation service to reserve a network slice having the quality-of-service requirement in the communications network. Data to or from the application is transmitted using the network slice.

Abstract: Techniques for distributed network connectivity monitoring of provider network edge location resources from cellular networks are described. A central service transmits test suites of commands to agents executed by test devices, which can execute the commands to test network characteristics between the test devices and target locations via one or multiple cellular communications networks. Results of the testing are sent back to the central service for processing, and the resultant metrics can be used for intelligent latency-based routing of clients, latency-based placement of resources, and/or performance monitoring of deployed resources.

Abstract: Generally described, one or more aspects of the present application relate to an instance resource oversubscription service for scheduling a burst period for a running virtual machine instance based on a time window specified by a user of the virtual machine instance. For example, the instance resource oversubscription service can predict future resource usage and identify the appropriate timing and physical host machine for letting the user burst (e.g., temporarily use the virtual machine instance in a manner than consumes a higher amount of computing resources such as CPU cycles, memory, network bandwidth, etc.). In doing so, the instance resource oversubscription service may consider, for example, the historical and current resource utilization levels of the virtual machine instances running on a set of available physical host machines and the burst period scheduling requests from other users of the instance resource oversubscription service.

Abstract: Disclosed are various embodiments for managing assignments of network slices. In one embodiment, a request is received to allocate a network slice in a radio-based network having a radio access network and an associated core network to an application connected to the radio-based network. The request specifies a set of quality-of-service constraints required for the network slice. A set of network functions in the radio-based network is configured to implement the network slice.

Abstract: Techniques for distributed network connectivity monitoring of provider network edge location resources from cellular networks are described. A central service transmits test suites of commands to agents executed by test devices, which can execute the commands to test network characteristics between the test devices and target locations via one or multiple cellular communications networks. Results of the testing are sent back to the central service for processing, and the resultant metrics can be used for intelligent latency-based routing of clients, latency-based placement of resources, and/or performance monitoring of deployed resources.

Abstract: An administrative agent running at a virtualization host of a network-accessible virtualized computing service determines that a first virtual machine is to be instantiated. The agent initiates at least a first configuration operation to enable connectivity for at least a portion of network traffic associated with the first virtual machine. The first configuration operation is performed at least in part using a first virtualization offloading card of the virtualization host. The agent causes a virtualization intermediary process of the virtualization host to launch one or more execution threads of the virtualization intermediary process to implement the first virtual machine. The intermediary process may be swapped to persistent storage, e.g., based on an analysis of resources of the virtualization host.