Abstract: Systems and method are provided for a temporary network slice usage barring service within a core network. A network device in the core network receives a slice barring information message for an application function (AF). The slice barring information message includes a unique subscriber identifier associated with a user equipment (UE) device to be barred from a network slice and indicates a barring expiration time. The network device stores barring parameters based on the slice barring information message. The barring parameters include a slice identifier associated with the AF, the unique subscriber identifier, and the barring expiration time. The network device sends a barring instruction message to another network device associated with the network slice. The barring instruction message includes the unique subscriber identifier and the barring expiration time. The other network device enforces temporary barring of the UE device from the network slice based on the barring instruction message.

Abstract: A system can include a producer device to receive reference data from a reference station. The system can include a queue device to store a reference message, corresponding to the reference data, in a message queue. The system can include a mapping device to store mapping information indicating that the message queue is associated with the reference station. The system can include a consumer device to identify the message queue as being associated with a microservice to be provided to a client device based on a microservice request. The message queue can be identified based on the mapping information. The consumer device can obtain the reference message from the message queue, generate corrections data associated with the client device, and provide the corrections data.

Abstract: A method, a device, and a non-transitory storage medium are described in which a TDD slot format selection service is provided. The service may calculate a distance between a radio access network device and an end device and use the distance to select a TDD configuration for the end device. The service may use other criteria to select the TDD configuration such as downlink or uplink ratios and/or interference value pertaining to a neighboring radio access network device. The service may also include scheduling of traffic adjustments based on a determined traffic bias associated with the end device and slot format symbols.

Abstract: A method for profiling the performance of a wireless local area network may include receiving, from a wireless access point (WAP), measurements associated with client devices in a wireless local area network (WLAN), and identifying a dominance of the client devices in the WLAN. The method may further include classifying the received measurements into categories representing channel qualities with the client devices in the WLAN, and transforming the categories of the client devices into values. The method may further include determining a profile of the WLAN based on the values and the dominance of the client devices.

Abstract: A system described herein may provide a technique for the simulation of User Equipment (“UEs”) and/or radio access network (“RANs”) over packet-based networks. Virtual UEs (“vUEs”) and virtual RANs (“vRANs”) may each include a virtual physical layer (“vPHY”) component that simulates the physical ingress and egress of radio frequency (“RF”) traffic to and/or from the vUE, and the vRAN may include a vPHY component that simulates the physical ingress and egress of RF traffic to and/or from the vRAN. Geographical locations of the vUEs and coverage areas of the vRANs may be further simulated, in order to properly route traffic between respective vUEs and vRANs.

Abstract: A system described herein may provide for the tracking and/or calculating of performance metrics associated with a network by marking traffic and determining performance characteristics of the marked traffic. Such performance characteristics or metrics may include throughput, latency, jitter, and/or other metrics. The marking may be performed on “user” traffic, which may be traffic that is generated or sent via the network by an application or service (e.g., a voice call service, a content streaming service, etc.), as opposed to “synthetic” or “test” traffic, which is traffic that is generated or sent for the purposes of testing performance of the network (e.g., traffic related to a “speed test” or the like).

Abstract: A method, a device, and a non-transitory storage medium are described in which a registration area-based application exposure and network slice selection service is provided. The service may include the generation of multiple sets of allowed network slices based on a type of end device, current tracking area, and registration area information. The service may also include selecting one of the sets of allowed network slices based on a mobility pattern of the end device. The service may also translate allowed network slices, current tracking area and registration area information, and expose the translated information to an application function.

Abstract: A mobile gateway may provide access to one or more networks based on a variety of configurable parameters, constraints, etc. A Mobile Gateway Management System (“MGMS”) may maintain different sets of rules, parameters, etc. associated with multiple different mobile gateways, such that a network may be able to determine whether to provide access to a particular mobile gateway based on location parameters, temporal parameters, account parameters, or other parameters. When access is granted to the network based on the parameters, the mobile gateway may serve as an interface between one or more User Equipment (“UEs”) and the network.

Abstract: A method, a device, and a non-transitory storage medium are described in which a containerized network function (CNF) management service is provided. The service may provide for allocating discrete sets of CNF resources deployed as pods to provide application services to end devices; identifying at least one threshold resource value associated with a first number of the deployed pods which are activated to provide the application services; determining an anticipated nonsatisfaction of the at least one threshold resource value associated with the first number of the deployed pods; and invoking, for a period of time, horizontal pod autoscaling (HPA) via an application programming interface to activate a second number of the deployed pods to provide the application services, wherein the HPA is performed non-incrementally until at least one of the period of time has elapsed or each of the deployed pods has been activated to provide the application services.

Abstract: A method, a device, and a non-transitory storage medium are described in which an component carrier management service is provided. The service may monitor data pertaining to a transmit power of an end device and a component carrier of a carrier aggregation. Based on the monitoring, the service may determine when the end device is at or near a maximum transmit power. The service may perform a mitigation procedure to prevent or minimize the end device shutting off a component carrier in a radio transmitter chain.

Abstract: A method, a device, and a non-transitory storage medium each provide an object recognition service that identifies an object within an image or a video. An object is identified according to a general classification based on a domain-based inference model, and is subsequently further identified according to a sub-classification of the general classification based on another domain-based inference model. The domain-based inference models are hierarchical. The object recognition of the object may be used in support of end user services.

Abstract: A method may include establishing, by a first service provider and via an application programming interface (API), an agreement with a second entity. The agreement may identify services that can be modified without submission of a new order. The method may also include receiving a first message requesting a change associated with a service and determining, by the first service provider, whether the requested change corresponds to a change that is permitted based on the agreement and whether resources are available in the first network to implement the requested change. The method may further include determining whether the requested change is accepted, sending a second message to the second entity that indicates whether the change is accepted and in response to determining that the change is accepted, automatically implementing the change to the service in the first network.

Abstract: Systems and methods described herein direct an end device to a multi-access edge computing (MEC) service instance among MEC instances with different service levels for different geographic areas. A network device stores a map of a geographic area with unique identifiable regions (UIRs) that each include cells for different wireless stations of a transport network. The network device receives application parameters, for a designated coverage area, for an application to be serviced using MEC resources. The network device associates the designated coverage area with one or more target UIRs from the map and deploys, when the MEC resources are available to support the application parameters, an instance of the application at a MEC cluster. The deployed instance of the application meets the application parameters for the target UIRs. The network device updates a MEC-domain name service (DNS) for the deployed instance of the application at the MEC cluster.

Abstract: A system described herein may train an explanation model based on a set of images and a set of explanation labels. The system may receive input data, and may provide the input data to the explanation model and a second model. The second model may provide a set of output labels, which may include performing unknown or “black box” processing on the input data. The explanation model may generate one or more images based on the input data, compare the images to the set of images based on which the explanation model was trained, and accordingly identify one or more explanation labels with bounding boxes associated with the generated one or more images. The system may output, in response to the input data, the set of output labels provided by the second model as well as the identified explanation labels.

Abstract: A method, a device, and a non-transitory storage medium are described in which an application layer network management service is provided. The service may allow third parties associated with an application layer network to develop and on-board application-aware logic that manages application services. The application-aware logic may include optimization of the application service and remedial procedures that address events associated with degradation and/or performance of the application service. The application-aware logic may be implemented in conjunction with other logic provisioned by a network provider.

Abstract: A system described herein may provide a technique for identifying and remediating potential threat vectors in a system, such as containers or applications in a virtual or cloud computing environment. Attributes of potential threat vectors may be identified, and the potential threat vectors may be scored based on the attributes. Values or scores of individual attributes may be determined through machine learning or other suitable techniques. Scores exceeding a threshold may indicate that a remedial measure should be performed. A remedial measure may be identified using machine learning or other suitable techniques. After the remedial measure is performed, the threat vector may be scored again, and a machine learning model may be refined based on whether the remedial measure was successful.

Abstract: In some implementations, a device may receive historical content data indicating historical characteristics associated with one or more groups of content. The device may determine, based on the historical content data, one or more characteristics associated with a time period. The device may determine, based on the one or more characteristics, a new group of content associated with the time period. The device may generate a display element for accessing content included in the new group of content during the time period.

Abstract: Systems and methods provide for configuring, by a first wireless station using radio resource control (RRC), a plurality of Fifth Generation (5G) wireless stations associated with 5G secondary cell groups (SCGs), wherein the first wireless station is associated with a first anchor cell for the SCGs; determining, by the wireless station, that a dual connectivity (DC) user equipment (UE) device has a wireless connection to a first 5G wireless station via a first 5G cell, wherein a second 5G SCG is associated with a second one of the 5G wireless stations and the DC-UE device is located in an area associated with the first anchor cell and in an area associated with a second anchor cell; and switching, using a media access control (MAC) control element (CE) of the DC-UE device, the wireless connection from the first 5G cell to the second 5G cell.

Abstract: A device may receive customer data associated with customers of items, and may identify customer characteristics based on the customer data. The device may process the customer characteristics, with a first model, to group the customers into groups of customers, and may process item data and data identifying the groups of customers, with a second model, to determine associations between the item data and the groups of customers. The device may receive, from a user device associated with a particular customer, particular customer data, and may identify particular customer characteristics based on the particular customer data. The device may assign the particular customer to a particular group, of the groups of customers, based on the particular customer characteristics, and may generate an item recommendation, for the particular customer, based on the item data associated with the particular group. The device may provide the item recommendation to the user device.

Abstract: Techniques for stateless address auto-configuration with support for multiple, different subnets are disclosed. In one embodiment, a method is disclosed comprising receiving, by a network device, a router solicitation (RS) message from a network node, generating, by the network device, a router advertisement (RA) message for use in determining the network node's network address, the RA message including a network address prefix and subnetting information, the subnetting information comprising a subnet address, a subnet address length and a subnet option type, and transmitting, by the network device, the RA message to the network node.