CLOUD COMPUTING IN COMMUNICATIONS SERVICE PROVIDER NETWORKS

Techniques for reducing latency between resources of a cloud provider network and end user devices are described. In one embodiment, a computer-implemented method comprises: executing, in a first network, a control plane component to at least partially manage edge locations that are physically separate from the first network, wherein the edge locations are adapted to execute containers for one or more customers, and wherein a first edge location of the edge locations is embedded within a cellular communications service provider network; receiving, by the control plane component, a profile from a customer including one or more constraints for use in identifying edge locations where containers for an application of the customer are to be deployed, wherein the one or more constraints comprise a latency constraint; determining, by the control plane component, to launch a customer container at the first edge location based at least in part due to the first edge location satisfying the latency constraint; transmitting, by the control plane component to the first edge location, a message to launch the customer container; and launching the customer container on a computer system of the first edge location, wherein the computer system obtains a container image specified by the customer that is stored outside the first edge location and launches the customer container based on the container image, and wherein the customer container communicates with a mobile device of a subscriber to the cellular communications service provider via the cellular communications service provider network.