The present disclosure provides for methods, apparatuses, and non-transitory computer-readable storage media for load balancing traffic scenarios by a network device. In an embodiment, a method includes training a plurality of learning agents to load balance a respective plurality of traffic scenarios to obtain a plurality of control policies. The method further includes performing at least one clustering iteration. Each clustering iteration includes selecting a pair of control policies and merging the pair of control policies into a clustered control policy that replaces the pair of control policies. The method further includes determining to stop the performing of the at least one clustering iteration when a quantity of control policies remaining in the plurality of control policies meets a predetermined value. The method further includes deploying to each base station of a plurality of base stations a corresponding control policy from the plurality of control policies.

This application provides a data transmission method and an apparatus, and may be applied to fields such as user equipment cooperation, sidelink relay, user relay, and internet of vehicles. A first terminal apparatus receives at least two pieces of downlink control information from a first network apparatus in a first slot, where the at least two pieces of downlink control information include first downlink control information and second downlink control information, the first downlink control information is used to indicate a first sidelink resource used by the first terminal apparatus to send first sidelink information to a second terminal apparatus, and the second downlink control information is used to indicate a second sidelink resource used by the first terminal apparatus to send second sidelink information to a third terminal apparatus.

A method of OFDMA subcarrier allocation for stations in a wireless network includes determining a total downlink buffered traffic load for downlink traffic from a gateway device to the stations, and receiving a total uplink buffered traffic load for uplink traffic from the stations to the gateway device. The method further includes determining a first ratio of total downlink buffered traffic load for each station in relation to total downlink buffered traffic load for all stations, determining a second ratio of total uplink buffered traffic load for each station in relation to total uplink buffered traffic load for all stations, performing OFDMA subcarrier allocation for the downlink traffic by assigning available channel bandwidth proportional to the first ratio for each station, and performing OFDMA subcarrier allocation for the uplink traffic by assigning available channel bandwidth proportional to the second ratio for each station.

Presented are systems, methods, apparatuses, or computer-readable media for data forwarding in centralized unit (CU) and distributed unit (DU) split architectures. A DU may receive, from a CU, context information for forwarding of data from a wireless communication device that is in radio resource control (RRC) inactive state. The DU may receive, from the wireless communication device, the data from the wireless communication device that is in RRC inactive state. The DU may process the data according to the context information. The DU may send, to the CU, the processed data according to the context information.

According to various embodiments, a method of operating a radio access network intelligent controller (RIC) may include: identifying a deployment request for a first xAPP, based on the request, identifying information related to a message processed by each of at least some of a plurality of nodes executed in the RIC, and based on E2 node subscription-related information about the first xAPP, and deploying the first xAPP to a first node selected from among the plurality of nodes, based on the information related to the message processed by each of the at least some of the plurality of nodes.

According to various embodiments, a method of operating a radio access network intelligent controller (RIC) may include: identifying a deployment request for a first xAPP, based on the request, identifying information related to a message processed by each of at least some of a plurality of nodes executed in the RIC, and based on E2 node subscription-related information about the first xAPP, and deploying the first xAPP to a first node selected from among the plurality of nodes, based on the information related to the message processed by each of the at least some of the plurality of nodes.

Various arrangements of hybrid cloud cellular network systems are presented herein. A cellular radio access network (RAN) that includes multiple base stations (BSs) can be in communication with a cloud computing platform. Multiple cloud-implemented national data centers (NDCs) can be present and executed on the public cloud computing platform. Network functions (NFs) are executed within each cloud-implemented NDC on the public cloud computing platform. The system further includes a cellular network database function. An instance of the cellular network database function is executed within each cloud-implemented NDC on the public cloud computing platform and updates each other instance of the cellular network database function.

A server may receive a first traffic data and a second traffic data from a first base station and a second base station; obtain a first augmented traffic data for the first base station, based on the first traffic data and a subset data of the second traffic data; obtain a second augmented traffic data for the second base station, based on the second traffic data and a subset data of the first traffic data; obtain a first artificial intelligence (AI) model via imitation learning based on the first augmented traffic data; obtain a second AI model imitation learning based on the second augmented traffic data; obtain a generalized AI model via knowledge distillation from the first AI model and the second AI model; and predict a future traffic load of each of the first base station and the second base station based on the generalized AI model.

A master RAN node (1) sends, to a control plane function (5) in a core network (4), a modification request for modification of a first PDU session already established between a radio terminal (3) and a user plane function (6) in the core network (4). The modification request implicitly or explicitly indicates that PDU session split is needed for the first PDU session. The modification request causes the control plane function (5) to control the user plane function (6) to move a specific one or more QoS flows of a plurality of QoS flows associated with the first PDU session from a first tunnel between the user plane function (6) and the master RAN node (1) to a second tunnel between the user plane function (6) and a secondary RAN node (2). This contributes, for example, to implementing PDU session split in a radio communication network.

A first apparatus (101) for a first method comprising receiving input data of at least one user equipment (102), determining an input to at least a part of at least one input layer (112A) of an artificial neural network depending on the input data, determining an output of a first part of the artificial neural network and transmitting the output of this part of the artificial neural network, and a second apparatus (105) for a second method comprising receiving an input for another part of the artificial neural network, determining an output of this part of the artificial neural network for at least one user equipment (102) depending on the input, the other part of the rtificial neural network comprising at least a part of at least one hidden layer (118A) or at least a part of an output layer (114A) of he artificial neural network or at least a part of at least one hidden layer (118A) and at least a part of an output layer (114A) of the artificial neural network, and outputting the output.