Granted Patent B2

US 12,348,388 · App. 18/256,122 · Granted Jul 1, 2025

Inventors: Shubin Yue (Shenzhen, CN); Hua Ni (Shenzhen, CN); Yongsheng Du (Shenzhen, CN)

Assignee: ZTE CORPORATION

H04L41/5009H04L41/16H04L41/40H04L43/091H04W24/02

Abstract

Claims (42)

1. An operation and maintenance management method of a network slice subnet, comprising:

obtaining a correlation relationship of multiple service parameters of each network function, NF, with certain key performance indicators of the network slice subnet based on an analytical model; and taking the correlation relationship as a performance analysis result, wherein the performance analysis result is obtained by the analytical model in the NF, and the analytical model is obtained by multiple NFs and a common node based on federated learning;

obtaining multiple instantiated parameters in the network slice subnet corresponding to the multiple service parameters; and

optimizing certain NFs with the multiple instantiated or service parameters based on the correlation relationship;

wherein the correlation relationship of multiple service parameters of each NF with certain key performance indicators of the network slice subnet based on the analytical model, and taking the correlation relationship as the performance analysis result comprises:

obtaining a contribution degree of certain key performance indicators of each NF to the certain key performance indicators of the network slice subnet and a relationship of some multiple service parameters of each NF with its certain key performance indicators based on the analytical model; and

taking the contribution degree as the performance analysis result;

wherein the optimizing certain NFs with the multiple instantiated or service parameters based on the correlation relationship comprises:

determining a NF to be optimized based on the contribution degree to obtain information of the NF to be optimized; and

sending the information of the NF to be optimized to a network function virtual orchestrator (NFVO) of the network slice subnet, for the NFVO to initiate an optimal deployment of an NF instance or a new creation of the NF instance to a virtual network function (VNFM) based on the information of the NF to be optimized.

2. The operation and maintenance management method of the network slice subnet according to claim 1 , wherein before the obtaining the correlation relationship of multiple service parameters of each NF with the KPI of the network slice subnet based on the analytical model, and taking the correlation relationship as the performance analysis result, further comprises:

using the common node to send a model training task to each NF, for each NF to perform model training based on the model training task and to report a model parameter obtained by training to the common node, wherein the model training task comprises a federated learning policy information, a machine learning algorithm information, and a subscription data information;

using the common node to perform model aggregation based on the reported model parameter;

sending the aggregated model parameters to each NF for iterative learning; and

obtaining the analytical model after reaching a preset number of iterations or a preset model accuracy.

3. The operation and maintenance management method of the network slice subnet according to claim 1 , wherein the optimizing certain NFs with the multiple instantiated or service parameters based on the correlation relationship comprises:

determining, based on the correlation relationship, the multiple service parameters to be optimized and a target NF corresponding to the multiple service parameters to be optimized; and

sending to the target NF a request for modifying the service parameters, for the target NF to modify the multiple service parameters to be optimized based on the request, wherein the request comprises the modified multiple service parameters.

4. The operation and maintenance management method of the network slice subnet according to claim 1 , wherein the common node is a network slice subnet management function (NSSMF).

5. An electronic device, comprising:

at least one processor; and

a memory communicated with the at least one processor;

wherein the memory stores instructions executable by the at least one processor, the instructions are executed by the at least one processor to enable the at least one processor to perform the operation and maintenance management method of the network slice subnet comprising:

obtaining a correlation relationship of multiple service parameters of each network function, NF, with certain key performance indicators of the network slice subnet based on an analytical model; and taking the correlation relationship as a performance analysis result, wherein the performance analysis result is obtained by the analytical model in the NF, and the analytical model is obtained by multiple NFs and a common node based on federated learning;

obtaining certain NFs with multiple instantiated or service parameters in the network slice subnet corresponding to the multiple service parameters; and

optimizing the multiple instantiated parameters based on the correlation relationship;

wherein the correlation relationship of multiple service parameters of each NF with the KPI of the network slice subnet based on the analytical model, and taking the correlation relationship as the performance analysis result comprises:

obtaining a contribution degree of certain key performance indicators of each NF to the certain key performance indicators of the network slice subnet based on the analytical model; and

taking the contribution degree as the performance analysis result;

wherein the optimizing certain NFs with the multiple instantiated or service parameters based on the correlation relationship comprises:

determining a NF to be optimized based on the contribution degree to obtain information of the NF to be optimized; and

sending the information of the NF to be optimized to a network function virtual orchestrator (NFVO) of the network slice subnet, for the NFVO to initiate an optimal deployment of an NF instance or a new creation of the NF instance to a virtual network function (VNFM) based on the information of the NF to be optimized.

6. A non-transitory computer readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the operation and maintenance management method of the network slice subnet comprising:

obtaining a correlation relationship of multiple service parameters of each network function, NF, with certain key performance indicators of the network slice subnet based on an analytical model; and taking the correlation relationship as a performance analysis result, wherein the performance analysis result is obtained by the analytical model in the NF, and the analytical model is obtained by multiple NFs and a common node based on federated learning;

obtaining multiple instantiated parameters in the network slice subnet corresponding to the multiple service parameters; and

optimizing certain NFs with the multiple instantiated or service parameters based on the correlation relationship;

wherein the correlation relationship of multiple service parameters of each NF with the KPI of the network slice subnet based on the analytical model, and taking the correlation relationship as the performance analysis result comprises:

obtaining a contribution of certain key performance indicators of each NF to the certain key performance indicators of the network slice subnet based on the analytical model; and

taking the contribution degree as the performance analysis result;

wherein the optimizing the multiple instantiated parameters based on the correlation relationship comprises:

determining a NF to be optimized based on the contribution degree to obtain information of the NF to be optimized; and

sending the information of the NF to be optimized to a network function virtual orchestrator (NFVO) of the network slice subnet, for the NFVO to initiate an optimal deployment of an NF instance or a new creation of the NF instance to a virtual network function (VNFM) based on the information of the NF to be optimized.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (13)