The described technology is generally directed towards predicting a need for provisioned (e.g., cloud computing) resources so that the provisioned resources are proactively provisioned and operational before their actual need. Historical data is used to predict upcoming resource demand so that resources begin to be scaled up to meet demand in advance, at a prediction time, given that there is a “spin-up” delay between requesting resources and their actual availability. The predictive resource provisioning is adaptable to override customary historical data with expected exceptions, and is flexible to handle variable spin-up times, constraints, and optimizations.

A network device may receive configuration data identifying resource subscription thresholds associated with a plurality of respective endpoint devices and may receive traffic from the plurality of endpoint devices. The network device may process the traffic and the configuration data, with a resource allocation model, to determine that processing traffic associated with a first endpoint device requires allocating a resource of the network device, and may process the configuration data, with the resource allocation model, to identify the resource of the network device from a particular resource of the network device that is currently allocated to traffic associated with a second endpoint device. The network device may allocate the particular resource of the network device to the traffic associated with the first endpoint device, and may process the traffic associated with the first endpoint device with the particular resource to generate processed traffic.

Resource allocation limitations include resource limits and resource guarantees. A consumer is vulnerable to interruption by other consumers if using more resources than guaranteed. Resources are designated and/or assigned consumers based on resource limits and resource guarantees. A constraint programming (CP) solver determines resource limits and resource guarantees that minimize vulnerability and/or vulnerability cost based on resource usage data. A CP data model includes limit elements, guarantee elements, and vulnerability elements. The CP data model further includes guarantee-vulnerability constraints, which relies on exceedance distributions generated from resource usage data for the consumers. The CP data model declaratively expresses combinatorial properties of a problem in terms of constraints. CP is a form of declarative programming.

Methods, systems, and apparatuses for synchronizing data transmission activity by user equipment (UE). In one aspect, the method comprises determining, by the UE and based on current usage of resources, that alignment of subsequent usage of resources is to be adjusted, generating, by the UE, data that indicates a plurality of activity alignment parameters that are to be adjusted in order to cause the adjusted alignment of subsequent usage of resources, encoding, by the UE, the generated data for transmission to a base station, and transmitting, by the UE, the encoded data to the base station.

A communication device (100) that operates as a management node in a first zone being a management domain on a network, the communication device (100) including: a communication unit (110) that executes communication with another node; and a control unit (130) that controls communication executed by the communication unit (110), in which the control unit (130) operates such that, when having received, from a user, a request regarding an application that chains one or more application functions (AFs) to act on a packet flowing in the network, the control unit (130) acquires information regarding the application from a second zone being a management domain other than the first zone, and then calculates a deployment destination of the AFs in the network including the first zone and the second zone based on the information.

A communication device (100) that operates as a management node in a first zone being a management domain on a network, the communication device (100) including: a communication unit (110) that executes communication with another node; and a control unit (130) that controls communication executed by the communication unit (110), in which the control unit (130) operates such that, when having received, from a user, a request regarding an application that chains one or more application functions (AFs) to act on a packet flowing in the network, the control unit (130) acquires information regarding the application from a second zone being a management domain other than the first zone, and then calculates a deployment destination of the AFs in the network including the first zone and the second zone based on the information.

A dynamic network resource allocation method based on network slicing is provided. A historical resource demand dataset of an accessed network slice is inputted into a first neural network for training. Based on a trained first neural network and the historical resource demand of the accessed network slice, a resource demand prediction information corresponding to the accessed network slice in a first prediction time period is determined. Resources are pre-allocated to the accessed network slice based on the resource demand prediction information, and resources are allocated to the accessed network slice when the first prediction time period arrives. In this way, the service provider can reasonably allocate network resources for network slices without violating the SLA, thus avoiding the waste of network resources.

A dynamic network resource allocation method based on network slicing is provided. A historical resource demand dataset of an accessed network slice is inputted into a first neural network for training. Based on a trained first neural network and the historical resource demand of the accessed network slice, a resource demand prediction information corresponding to the accessed network slice in a first prediction time period is determined. Resources are pre-allocated to the accessed network slice based on the resource demand prediction information, and resources are allocated to the accessed network slice when the first prediction time period arrives. In this way, the service provider can reasonably allocate network resources for network slices without violating the SLA, thus avoiding the waste of network resources.

An embodiment includes determining, based on historical data associated with a specific task, a baseline bandwidth recommendation for completing the specific task. The embodiment assigns, for a first time period, the specific task to a first computing device on a network. The embodiment allocates, for the first time period based on the baseline bandwidth recommendation, a first baseline bandwidth to the first computing device. The embodiment allocates, for the first time period, a portion of a shared buffer bandwidth as a first buffer bandwidth to the first computing device based on a weight value assigned to the specific task. The first buffer bandwidth combines with the first baseline bandwidth as a first total bandwidth for the specific task. The embodiment throttles, during the first time period, data packets associated with the specific task based on the first total bandwidth for the specific task.

Systems and methods for managing distributed compute resources are described herein. A system is configured to receive, from an agent operating at a first compute domain of a plurality of compute domains, a request for compute resources; broadcast the request for compute resources to respective agents at the plurality of compute domains; receive a plurality of offers for available compute resources from at least a portion of the plurality of compute domains; transmit, to a selected agent at a selected compute domain of the plurality of compute domains, a commit message to reserve compute resources of the selected compute domain associated with a selected offer of the plurality of offers; and transmit an indication of the commit message to the agent at the first compute domain, wherein the first compute domain is to use the compute resources reserved at the selected compute domain for workloads of the first compute domain.