A method for providing a predicting bandwidth utilization for a customer of a connectivity service provider is disclosed. The method includes receiving bandwidth utilization data over time for a customer of a connectivity service provider. The method further includes training a machine learning model for the bandwidth utilization data during a time period based on the received data. In an embodiment, training the machine learning model includes determining a value for a parameter. The bandwidth utilization may be substantially periodic over the time period. Relying on the periodicity of the bandwidth utilization, the method further includes predicting, using the trained model, future bandwidth utilization over time.

Disclosed aspects manage a shared pool of configurable computing resources. A resource demand value is identified for a target host. Resource supply values of dynamically-assigned resources are computed for donor hosts. Using the resource demand value and the resource supply values, dynamically-assigned resources are reclaimed from the donor hosts and distributed to the target host.

A cloud-management system intercepts API calls from a client application. Based on the expected amount of cloud resources required to service the API call, and given the terms of the client's billing plan, the system estimates the cost to service the call. The system embeds this cost into its response to the API call and the client application, or an IDE hosting the application, keeps a running total of API-related costs incurred by the application. The system can also run in an emulation mode, estimating the application's API resource-consumption costs without actually consuming cloud resources. In this mode, the system replaces each GET and PUT call in the intercepted API call with an equivalent HEAD call that does not consume resources. The system still, however, predicts the actual cost of the original API call by returning the cost of each original GET and PUT.

A system, smart device and method for apportioning costs of smart device operations between purposes. Operation information concerning operations performed by the smart device is recorded. The operations are apportioned between purposes based on categorization information and the operation information. The cost of the apportioned operations performed by the device is determined for the purposes based on the operation information and tariff information.

Disclosed aspects manage a shared pool of configurable computing resources. A resource demand value is identified for a target host. Resource supply values of dynamically-assigned resources are computed for donor hosts. Using the resource demand value and the resource supply values, dynamically-assigned resources are reclaimed from the donor hosts and distributed to the target host.

A method of adjusting user experience on a social networking service includes setting a data-usage threshold for a plurality of features in the social networking service, providing the plurality of features to a user of the social networking service at an initial quality of service, and monitoring data usage by the user during a period of time in which the plurality of features is provided to the user. The method further includes, in response to a determination that the data usage by the user during the period of time satisfies the data-usage threshold: (1) reducing the quality of service for the user for one or more features of the plurality of features, and (2) providing the one or more features to the user at the reduced quality of service.

Methods, systems, and devices for wireless communications are described. A source user equipment (UE) may determine which subscriber identity module (SIM) card to use based on information of the target UE. For example, the target UE may have poor call quality using a first SIM, but high call quality when using a second SIM. The target UE may indicate the call quality for each SIM in subscription information to the source UE. The source UE may determine to use the second SIM of the target UE instead of the first SIM, resulting in higher call quality for the target UE. The subscription information may include a variety of information related to the target UE, such as subscriptions of the target UE, RAT availabilities for the target UE, etc. The target UE may also configure settings for receiving or rejecting data calls. The target UE may configure whether to receive data calls based on connectivity parameters.

Systems, methods, and computer-readable media are described for generating customized service plans for a wireless telecommunications network. An operator of a wireless telecommunications network may allow users to access the network in accordance with a service plan, which may specify terms and conditions associated with usage of the network (e.g., types of usage, amounts of usage, geographic areas, associated mobile devices and users, subscription fees, etc.). Customized, user-specific service plans for the wireless network may be generated and implemented by determining that a user satisfies one or more criteria for applying service plan modifications. A user may be required to agree to specified conditions, such as upgrading a mobile device or subscribing for a specified time period, in order to accept a customized service plan. Multiple modifications may be applied to a base service plan, and plans and/or modifications for which the user is eligible may be identified.

Disclosed aspects manage a shared pool of configurable computing resources. A resource demand value is identified for a target host. Resource supply values of dynamically-assigned resources are computed for donor hosts. Using the resource demand value and the resource supply values, dynamically-assigned resources are reclaimed from the donor hosts and distributed to the target host.

Embodiments of the present disclosure describe methods, apparatuses, storage media, and systems for utilizing network data analytics function (NWDAF) to influence fifth generation (5G) quality of service (QoS) configuration and adjustment. Various embodiments enable NWDA-assisted QoS provisioning, NWDA-assisted determination of policy, and NWDA-assisted QoS adjustment. Other embodiments may be described and claimed.