A network device obtains service requirements associated with a customer identifier, obtains a first profile describing an infrastructure design of multiple transport domains associated with at least one network slice of a network, and obtains a second profile describing performance characteristics of the multiple transport domains of the at least one network slice. The network device receives training data associated with performance measurements of the multiple transport domains of the at least one network slice, and updates a machine learning model based on the training data. The network device selects at least one of the multiple transport domains for orchestration using the updated machine learning model, the service requirements, the first profile, and the second profile.

Method handling uplink (UL) bearer split configuration in multi-connectivity system includes identifying first UL data of a packet data convergence protocol (PDCP) layer, transmitting first data of first UL data to a primary radio link control (RLC) entity for a first time period, and transmitting second data of the first UL data to a secondary RLC entity for a second time period, identifying at least one first network parameter of a first UL path associated with the primary RLC entity for the first time period, and identifying at least one second network parameter of a second UL path associated with the secondary RLC entity for the second time period, determining a split factor for splitting second UL data of the PDCP layer between the primary RLC entity and the secondary RLC entity based on the at least one first network parameter and the at least one second network parameter, and transmitting the second UL data to the primary and secondary RLC entities for a third time period based on the split factor.

Disclosed by the present application are a data transmission method and related apparatus, used for an electronic device enabling a plurality of wireless communication links, said method comprising: if it is detected that a target game application is running in the foreground, then determining a target anti-addiction control duration of said target game application; if it is detected that the target game application offloads and transmits a game data packet by means of a smart link aggregation (SLA), then recording the offload transmission duration of the offloading and transmission of said game data packet; if it is detected that the offload transmission duration is longer than the target anti-addiction control duration, then ceasing to offload the game data packets by means of the SLA and transmitting the game data packets by means of one wireless communication link of the plurality of wireless communication links.

User equipment (UE) can be connected to both a first base station and a second base station. A flow controller at the first base station can determine packet latency goals associated with packets. The flow controller can also determine connection latencies associated with a first connection from the first base station to the UE and a second connection from the second base station to the UE, where one leg of a split bearer passes from the first base station to the UE over the first connection and another leg of the split bearer passes from the first base station to the second base station and then to the UE over the second connection. The flow controller can route packets with lower packet latency goals via the leg of the lower-latency connection, and route other packets with higher packet latency goals over the leg of the higher-latency connection.

An apparatus and system for generating KPIs based on packet delay performance measurements through a NG-RAN or 5GC are described. Integrated average UL and DL delays in NG-RAN, gNB DU delays and e2e delays are determined for each sub-network, network slice subnet, and network slice, and for a gNB DU. An overall NR cell DU delay including air interface delay and delay within the NR cell DU, and an overall gNB-CU delay including F1 interface delay and delay within the gNB-CU-UP, are each independently weighted for each gNB and in each direction for the integrated delay KPI in the NG-RAN. The e2e delay KPIs are average UL or DL delays between a UPF and UE(s) for a network slice based on e2e delays for each N3 and N9 interface weighted by number of packets or data volume of the interface for the corresponding direction.

Systems, methods, and computer software are disclosed for providing an Open Radio Access Network (RAN) networking infrastructure. In one embodiment a method is disclosed, comprising: providing real-time OpenRAN controller responsible for radio connection management, mobility management, QoS management, edge services, and interference management for the quality of end user experience; and providing a non-real-time controller in communication with the real-time OpenRAN controller, the non-real-time controller providing functionality such as configuration management, device management, fault management, performance management, and lifecycle management for all network elements in a network.

A data packet transmission method—that includes: obtaining, by a terminal, N application programs that are running; and if the N application programs include an application program including a low-latency service; determining whether an unlicensed frequency band is in a congestion state; and instructing a network device to schedule a data packet of the terminal to a licensed frequency band for transmission when the unlicensed frequency band is in a congestion state. When determining that the N running application programs include the application program including the low-latency service, the terminal may instruct the network device to schedule the data packet of the terminal to the licensed frequency band for transmission, so as to transmit a data packet of the low-latency service by using the licensed frequency band. Resources in the licensed frequency band are centrally scheduled by the network device, instead of being used through contention.

The described technology is generally directed towards reducing latency in a wireless communications network. Radio access network latency data corresponding to a measured latency impact criterion is obtained by a network device of a wireless network. Based on the radio access network latency data, latency guidance data usable by the radio network device to achieve a reduction in communication latency that is experienced by a user equipment is predicted, e.g., by a learned model. The latency guidance data can be used to facilitate a reduction in the communication latency that is experienced by a user equipment.

The described technology is generally directed towards reducing latency in a wireless communications network. Radio access network latency data corresponding to a measured latency impact criterion is obtained by a network device of a wireless network. Based on the radio access network latency data, latency guidance data usable by the radio network device to achieve a reduction in communication latency that is experienced by a user equipment is predicted, e.g., by a learned model. The latency guidance data can be used to facilitate a reduction in the communication latency that is experienced by a user equipment.

Systems and methods described herein provide an intelligent MEC resource scheduling service. A network device in a MEC network stores, in a memory, threshold values indicating overload conditions for resource usage by a first MEC cluster; monitors resource usage in the first MEC cluster; determines, based on the monitoring, when one of the threshold values is reached; identifies available resources in a second MEC cluster; and re-directs, based on the identifying, at least some of the resource usage from the first MEC cluster to the second MEC cluster.