Abstract: A method includes detecting a communication session in a wireless network and obtaining at least one resource utilization metric associated with the communication session. The method further includes determining, based on the at least one resource utilization metric, that network resources associated with the communication session are underutilized, and relaxing a performance-limiting policy associated with the communication session based on determining that the network resources are underutilized. The method may further include detecting a triggering condition associated with the communication session and initiating an inspection of data associated with the communication session in response to detecting the triggering condition. The method may also include detecting an anomalous condition based on the inspection and generating an alert based on detecting the anomalous condition.

Abstract: Systems and methods described herein provide a slice management and prioritization service on a per user equipment (UE) device level. A network device in a core network may receive a notification that a UE device has exhausted a quota of available simultaneous data radio bearers (DRBs) and, afterwards, receive an indication that an application on the UE device has requested a new protocol data unit (PDU) session on a requested network slice that is not currently active for the UE device. The network device may identify relative priorities for the requested network slice and active network slices for the UE device; determine, based on the relative priorities, if the new PDU session can preempt a DRB for an active PDU session; and delete the active PDU session when it is determined the new PDU session can preempt a DRB for an active PDU session.

Abstract: A method, a network device, and a non-transitory computer-readable storage medium are described in relation to an radio spectrum binding service. The service may include generating and provisioning binding information. The binding information may include radio frequencies correlated to applications or categories of applications associated with packet data unit sessions or radio frequencies correlated to applications or categories of applications associated with packet data unit sessions, and network slice identifiers. The service may include selecting and using the binding information for packet data unit sessions.

Abstract: A system described herein may receive a set of attributes associated with a particular User Equipment (“UE”), such as a location of the UE, Quality of Service (“QoS”) parameters, or UE power class. The system may identify a set of radio access network (“RAN”) configuration parameters based on the received set of attributes associated with the particular UE, wherein the RAN configuration parameters include radio frequency (“RF”) channel configuration parameters such as an orthogonal frequency-division multiplexing (“OFDM”) slot format. The system may provide the identified set of RAN configuration parameters to the RAN, and the RAN may utilize the RF channel configuration parameters included in the identified set of RAN configuration parameters to configure one or more channels between the RAN and the particular UE.

Abstract: A device receives User Equipment device (UE) Policy Section Codes (UPSCs) and a first version of associated UE policy rules. The device further receives first inconsistency detection codes for the UPSCs and a current version of the associated UE policy rules. The device determines, based on the UPSCs and the first version of the associated UE policy rules, second inconsistency detection codes, and compares the first and second inconsistency detection codes to identify inconsistencies between the first version of the UE policy rules and the current version of the UE policy rules. The device sends, when the comparison identifies the inconsistencies, a request for updated UE policy rules, and receives one of the UPSCs and an updated version of an associated UE policy rule of the one of the UPSCs.

Abstract: Techniques for packet flow description (PDF) management are disclosed. In one embodiment, a method is disclosed comprising obtaining, by an application function (AF), information about network functions (NFs) instantiated as virtual machines (VMs) on compute resources of a cloud platform, obtaining, by the AF, information about the compute resources, obtaining, by the AF, information about a plurality of UEs accessing the NFs, and using, by the AF, the information about the NFs, compute resources of the cloud platform and the plurality of UEs to make an assessment of a workload placement corresponding to the NFs instantiated on the compute resources of the cloud platform.

Abstract: A device may include a processor configured to detect a Protocol Data Unit (PDU) session associated with a user equipment (UE) device. The processor may be further configured to obtain at least one congestion metric value for a base station associated with the PDU session; determine that the obtained at least one congestion metric value is less than a maximum throughput enforcement threshold; and override a maximum throughput enforcement policy on a User Plane Function (UPF) associated with the UE device, based on determining that the obtained at least one congestion metric value is less than the maximum throughput enforcement threshold.

Abstract: Systems and methods described herein provide a slice management and prioritization service on a per user equipment (UE) device level. A network device in a core network may receive a notification that a UE device has exhausted a quota of available simultaneous data radio bearers (DRBs) and, afterwards, receive an indication that an application on the UE device has requested a new protocol data unit (PDU) session on a requested network slice that is not currently active for the UE device. The network device may identify relative priorities for the requested network slice and active network slices for the UE device; determine, based on the relative priorities, if the new PDU session can preempt a DRB for an active PDU session; and delete the active PDU session when it is determined the new PDU session can preempt a DRB for an active PDU session.

Abstract: A device may include a processor configured to detect a Protocol Data Unit (PDU) session associated with a user equipment (UE) device. The processor may be further configured to obtain at least one congestion metric value for a base station associated with the PDU session; determine that the obtained at least one congestion metric value is less than a maximum throughput enforcement threshold; and override a maximum throughput enforcement policy on a User Plane Function (UPF) associated with the UE device, based on determining that the obtained at least one congestion metric value is less than the maximum throughput enforcement threshold.

Abstract: In some implementations, the techniques described herein relate to a method including: receiving input features associated with a cellular network that includes key performance indicators and metrics collected from computing devices in the cellular network; preprocessing the input features to generate input features; providing the input features to a machine learning model to generate a predicted user experience classification, wherein the machine learning model is trained using a dataset including a plurality of sets of input features and corresponding user experience labels; and performing one or more actions based on the predicted user experience classification, wherein performing one or more actions includes identifying a root cause of a user experience issue and generating a recommendation to modify the cellular network to address the root cause.

Abstract: Embodiments described herein allow reduced latency and computational costs by identifying a slice associated with a packet and determining an action to be performed with respect to the packet without having to perform deep packet inspection on the packet. An aspect of the present disclosure is a method comprising receiving a packet including a slice identifier corresponding to a slice of a network, the slice identifier having a plurality of bits; determining a bit value for each bit in a subset of the plurality of bits; and performing an action with respect to the packet based on the bit value of at least one bit in the subset.

Abstract: A system described herein may receive an indication that a particular User Equipment (“UE”) has wirelessly connected to a radio access network (“RAN”) of a wireless network. The RAN may be communicatively coupled to a core network of the wireless network. The system may identify that a core bypass policy is associated with the particular UE, and may instruct the RAN to bypass the core network when routing traffic associated with the particular UE. Based on the instruction to bypass the core network, the RAN may route traffic, received from the particular UE, to a Data Network (“DN”) without routing the traffic to the core network.

Abstract: A device may receive, from a user equipment (UE), a request for an application, and may receive, from the UE, parameters of the application and key performance indicator (KPI) targets for the application. The device may receive, based on the request, KPIs from a core network, a mobile edge computing (MEC) device, and an application server, and may compare the KPIs and the KPI targets for the application. The device may determine, based on comparing the KPIs and the KPI targets, whether to utilize the MEC device or the application server for providing the application to the UE. The device may selectively identify a first user plane function (UPF) associated with the MEC device based on determining to utilize the MEC device, or may identify a second UPF associated with the application server based on determining to utilize the application server.

Abstract: A base station determines a latency requirement of a user equipment device (UE), and receives latency measurements associated with multiple neighboring cells or cell sectors having coverage areas within a certain proximity to the base station. The base station measures a latency associated with a first cell or cell sector, having a coverage area generated by the base station, that is currently serving the UE. The base station triggers a mobility event for the UE, based on the UE's latency requirement, the measured latency of the first cell or cell sector, and the latency measurements associated with the multiple neighboring cells or cell sectors, to a selected one of the multiple neighboring cells or cell sectors.

Abstract: A network device may maintain a list of existing slice identifiers, associated with slices of a core network, that are in use in active UE sessions, and may receive a slice identifier associated with a slice of the core network and provided in a request to establish a session between a UE and the slice of the core network. The network device may determine whether the slice identifier matches an existing slice identifier included in the list, and may create a new network address, with an address of the network device and the slice identifier, based on the slice identifier failing to match an existing slice identifier included in the list. The network device may utilize the new network address to establish the session between the UE and the slice of the core network.

Abstract: A method, a network device, and a non-transitory computer-readable storage medium are described in relation to a coordinated domain-based L4S service. The service may enable end-to-end congestion control based on a predetermined order of domains, which are associated with L4S devices that support a packet flow, for which congestion control responses are to be provided. The service may provide independent feedback loops of state information from each domain and associated L4S device. The feedback loops may operate on different timescales. The service may coordinate congestion control among domains of an end-to-end path that support the packet flow and prevent fragmented or contentious congestion control responses between the domains.

Abstract: A computer device may include a memory storing instructions and processor configured to execute the instructions to host a network function container that implements a microservice for a network function in a wireless communications network, wherein the network function container is deployed by a container orchestration platform; host a service proxy container associated with the network function container, wherein the service proxy container is deployed by the container orchestration platform; and configure the hosted service proxy container to apply a wireless network policy to the microservice for the network function. The processor may be further configured to intercept messages associated with the microservice for the network function using the configured service proxy container; and apply the wireless network policy to the intercepted messages using the configured service proxy container.

Abstract: In some implementations, a network device may transmit an indication of physical properties associated with a user equipment (UE), wherein the physical properties include a route associated with the UE. The network device may receive a metric associated with a line-of-sight (LOS) of the UE with a base station, wherein the LOS is while the UE is traveling along the route. The network device may transmit a message to enable dual connectivity for the UE based on the metric and one or more other slice parameters.

Abstract: Embodiments described herein allow reduced latency and computational costs by identifying a slice associated with a packet and determining an action to be performed with respect to the packet without having to perform deep packet inspection on the packet. An aspect of the present disclosure is a method comprising receiving a packet including a slice identifier corresponding to a slice of a network, the slice identifier having a plurality of bits; determining a bit value for each bit in a subset of the plurality of bits; and performing an action with respect to the packet based on the bit value of at least one bit in the subset.

Abstract: A method, a network device, and a non-transitory computer-readable storage medium are described in relation to an EASDF secure service. The EASDF secure service may include a network-side service that may validate access and authorization to use a domain name system (DNS) resolver device, such as an edge application server discovery function. The network-side service may validate access and authorization of an end device based on tokens. The EASDF secure service may include an end device-side service that includes a token with a DNS query to the DNS resolver device. The end device-side service may further provide authorization regarding access and use of applications, networks, and application devices that host applications and/or assets by the end device at the end device. The end device-side service may determine access and/or authorization based on tokens and a validation procedure performed at the end device.