A server may obtain teacher artificial intelligence (AI) models from source base stations; obtain target traffic data from a target base station; obtain an integrated teacher prediction based on the target traffic data by integrating teacher prediction results of the teacher AI models based on teacher importance weights; obtain a student AI model that is trained to converge a student loss on the target traffic data; update the teacher importance weights to converge a teacher loss between a student prediction of the student AI model on the target traffic data, and the integrated teacher prediction of the teacher AI models on the target traffic data; update the student AI model based on the updated teacher importance weights being applied to the teacher prediction results of the teacher AI models; and predict a communication traffic load of the target base station using the updated student AI model.

Systems, methods, and devices are described to facilitate soft signaling between a user equipment (UE) and a network element. A UE and a network element can exchange HTTP or Websocket messages to identify and request network resources needed for the UE to access and use application services. The network element can use requested network resources to cause the configuration of a connection between the UE and a radio access network.

A system and method for providing an MAP for an unsolicited grant to a modem in a wireless backhaul environment based on centralized small cell (cSC) data received at a modem termination system (MTS) is described herein.

One or more network devices create, in a network, a network slice with multiple network slice instances (NSIs) having multiple slice instance variations, where each of the multiple slice instance variations services a slice variation type and one of multiple slice variation levels. The slice variation type corresponds to a first performance characteristic of one or more performance characteristics met by the network slice while servicing sessions and the multiple slice variation levels sub-divide the slice variation type into multiple different levels of service within the slice variation type. The one or more network devices allocate, instantiate, and provision virtual resources for each of the multiple NSIs; and services User Equipment (UE) sessions via one of the multiple slice instance variations based on UE selection of one of the multiple slice variation levels of the slice variation type.

Fifth generation and beyond (5G+) systems are expected to adopt new network architectures, services, and deployment schemes for compatibility with the latest technologies and end user's needs. With increase in user equipment (UE), also come variety of advanced applications and use-cases, wherein each application type has its own KPI requirements. Existing resource allocation schemes in cellular networks are not able to handle such dynamic requirements due to which network slice can lead to unwanted mismanagement of resources. Present application provides systems and methods for application-aware dynamic slicing in radio access network (RAN), wherein RAN slicing is proactively managed by learning historical slice demands and consumptions. Once slices are created, the system allocates resources to user equipment by following optimal inter-slice and intra-slice mechanisms based on application type(s), traffic demand(s) and wireless characteristics of UE. Upon resource allocation the UE are further monitored to avoid resource misutilization and resource wastage.

A method and network node for classification of interference connections between Citizens Broadband Radio Service Devices, CBSDs, in a wireless communication network are provided. According to one aspect, a method includes calculating an interference level, the calculation being based on whether two interfering CBSDs are operating in one of the alternate channels, adjacent channels and the same channel. The method also includes comparing the calculated interference level to a threshold to determine a classification of an interference connection.

A method and network node for classification of interference connections between Citizens Broadband Radio Service Devices, CBSDs, in a wireless communication network are provided. According to one aspect, a method includes calculating an interference level, the calculation being based on whether two interfering CBSDs are operating in one of the alternate channels, adjacent channels and the same channel. The method also includes comparing the calculated interference level to a threshold to determine a classification of an interference connection.

Techniques for distributed computation are provided. A plurality of edge computing devices available to execute a computing task for a client device is identified, and a first latency of transmitting data among the plurality of edge computing devices is determined. A second latency of transmitting data from the client device to the plurality of edge computing devices is determined, and a set of edge computing devices, from the plurality of edge computing devices, is determined to execute the computing task based at least in part on the first and second latencies. Execution of the computing task is facilitated using the set of edge computing devices, where the client device transmits a portion of the computing task directly to each edge computing device of the set of edge computing devices.

Techniques for distributed computation are provided. A plurality of edge computing devices available to execute a computing task for a client device is identified, and a first latency of transmitting data among the plurality of edge computing devices is determined. A second latency of transmitting data from the client device to the plurality of edge computing devices is determined, and a set of edge computing devices, from the plurality of edge computing devices, is determined to execute the computing task based at least in part on the first and second latencies. Execution of the computing task is facilitated using the set of edge computing devices, where the client device transmits a portion of the computing task directly to each edge computing device of the set of edge computing devices.

Methods, systems, and devices for wireless communications are described in which multiple operators may perform spectrum sharing using shared radio units (RUs), where the multiple different operators can access a same RU for communications with a user equipment (UE). A shared RU may receive requests for resources from two or more network nodes of two or more different network operators, for wireless resources in a first time period. The RU may determine a first resource allocation for the first time period based on different priorities of the different network operators. A first network operator may have a higher priority than a second or third network operator, and resources may be allocated to the first network operator ahead of the second or third network operators. The RU may transmit the first resource allocation to each of the different network nodes that transmitted requests for resources.