Systems and methods for deploying computer application workload elements among a plurality of computing resources are described. An elastic workload orchestration architecture includes a workload queue that is configured to receive application workload elements for processing using one or more distributed hybrid application services. The workload elements are evaluated to confirm whether they are properly formatted for deployment among the distributed hybrid application services and, if such confirmation cannot be made, the workload elements are adapted into a proper format. An elastic workload operator then deploys the workload elements to the distributed hybrid application services.

An electronic device is provided. The electronic device includes a communication circuit, a memory configured to store a learning model, and at least one processor, wherein the at least one processor is configured to obtain data related to a network situation of a base station from the communication circuit, calculate a performance indicator value related to network performance according to a performance indicator, based on the data related to the network situation, train the model, based on the performance indicator value calculated according to the performance indicator, determine an off threshold of traffic for turning off a cell, based on the trained model, and transmit the determined off threshold to the base station via the communication circuit.

Devices, computer-readable media and methods are disclosed for dynamic capacity scaling for whitebox core networks. In one example, a method includes monitoring network traffic traversing a whitebox core network of a communications service provider, detecting a level of network traffic on a first link in the whitebox core network is greater than a threshold level of network traffic, and re-routing, in response to the detecting, at least one tunnel in the whitebox core network from the first link to a second link in the whitebox core network.

An electronic device is provided. The electronic device includes a communication circuit, a memory configured to store a learning model, and at least one processor, wherein the at least one processor is configured to obtain data related to a network situation of a base station from the communication circuit, calculate a performance indicator value related to network performance according to a performance indicator, based on the data related to the network situation, train the model, based on the performance indicator value calculated according to the performance indicator, determine an off threshold of traffic for turning off a cell, based on the trained model, and transmit the determined off threshold to the base station via the communication circuit.

A processing system may apply a data set comprising utilization metrics of a cells of a cell sector to a throughput prediction model to obtain a first predicted throughput for the cell sector for a designated future time period and for all cells being in an active state. The processing system may generate a first modified data set simulating a first cell being placed in an inactive state, by distributing utilization metrics of the first cell over at least one additional cell, and may apply the first modified data set to the throughput prediction model to obtain a second predicted throughput. The processing system may then determine that the second predicted throughput meets a threshold throughput that is based on the first predicted throughput, and transmit at least one instruction to place the first cell in the inactive state for the designated future time period in response to the determining.

A processing system may apply a data set comprising utilization metrics of a cells of a cell sector to a throughput prediction model to obtain a first predicted throughput for the cell sector for a designated future time period and for all cells being in an active state. The processing system may generate a first modified data set simulating a first cell being placed in an inactive state, by distributing utilization metrics of the first cell over at least one additional cell, and may apply the first modified data set to the throughput prediction model to obtain a second predicted throughput. The processing system may then determine that the second predicted throughput meets a threshold throughput that is based on the first predicted throughput, and transmit at least one instruction to place the first cell in the inactive state for the designated future time period in response to the determining.

Embodiments are directed towards systems and methods for user plane function (UPF) and network slice load balancing within a 5G network. Example embodiments include systems and methods for load balancing based on current UPF load and thresholds that depend on UPF capacity; UPF load balancing using predicted throughput of new UE on the network based on network data analytics; UPF load balancing based on special considerations for low latency traffic; UPF load balancing supporting multiple slices, maintaining several load-thresholds for each UPF and each slice depending on the UPF and network slice capacity; and UPF load balancing using predicted central processing unit (CPU) utilization and/or predicted memory utilization of new UE on the network based on network data analytics.

Embodiments are directed towards systems and methods for user plane function (UPF) and network slice load balancing within a 5G network. Example embodiments include systems and methods for load balancing based on current UPF load and thresholds that depend on UPF capacity; UPF load balancing using predicted throughput of new UE on the network based on network data analytics; UPF load balancing based on special considerations for low latency traffic; UPF load balancing supporting multiple slices, maintaining several load-thresholds for each UPF and each slice depending on the UPF and network slice capacity; and UPF load balancing using predicted central processing unit (CPU) utilization and/or predicted memory utilization of new UE on the network based on network data analytics.

The system obtains multiple thresholds for multiple bandwidth usage types associated with a UE. The threshold indicates an amount of bandwidth available to the UE over a predetermined period. Each threshold corresponds to a bandwidth usage type. The multiple thresholds include: roaming data, home data, voice over IP, international voice over IP, roaming voice over IP, international data, and tethering data threshold. The system obtains multiple bandwidth usage patterns of the UE, where each bandwidth usage pattern corresponds to a threshold. The system iterates over each bandwidth usage to determine whether the UE has exceeded or is likely to exceed the threshold within the predetermined period. Upon determining that a bandwidth usage pattern has exceeded or is likely to exceed the threshold within the predetermined period, the system determines an increase to the threshold. The system sends an indication of the increase to the threshold to the UE.

This disclosure provides methods, components, devices and systems for techniques to increase capacity with multi-link operation (MLO). Some aspects more specifically relate to modifying a usage of a multi-link connection based on observed traffic metrics associated with wireless devices. A first wireless device may observe a traffic metric that indicates an absence of traffic associated with one or more links of the multi-link connection or an underutilization of the one or more links of the multi-link connection over a time window. The first wireless device may request a reduction in a quantity of operating links of the multi-link connection between the first wireless device and a second wireless device in accordance with the observed traffic metric. The first wireless device may request reduction in a quantity of operating links, and may communicate with the second wireless device in accordance with the requested reduction in the quantity of operating links.