Method and system for dynamically deploying CU under CU Pool

Abstract

The invention discloses a method and a system for dynamically deploying a CU under a CU Pool. The method comprises the following steps: S1, constructing a machine learning model by adopting a preset method; S2, performing collection and information reporting on the centralized unit platform sample data extracted by the machine learning model; S3, adopting a control center to perform data processing on reported sample data, and achieving machine learning, prediction and decision making; and S4, realizing data synchronization of the main and standby centralized units and switching between main and standby centralized unit platforms. The method has the beneficial effects that a reasonable machine learning model can be constructed by extracting system key data; through continuous machine training, the influence of the user service on the CU service platform can be accurately predicted and evaluated, so that the optimal CU service platform is selected from the CU POOL to perform dynamic CU module deployment; and the performance and reliability of the system are effectively improved, the abnormal risk of the CU is reduced, and reasonable allocation of CU resources is realized.

Description

technical field [0001] The present invention relates to the technical field of wireless communication, in particular to a method and system for dynamically deploying CUs in a CU Pool. Background technique [0002] With the development of wireless communication technology, 3GPP divides the 5G baseband unit into two logical nodes, CU and DU. Its CU is a centralized unit node, responsible for handling high-level protocol functions and managing multiple DUs. DU is a distributed unit node, which is responsible for completing part of the underlying baseband protocol processing functions. The CU is connected to the 5GC through the NG interface, and connected to the DU through the F1 interface. CU and DU jointly complete the entire NR baseband processing function. 3GPP discussed 8 candidate schemes for CU and DU splitting options, and the standardization work mainly focuses on Option2, that is, CU mainly completes RRC / PDCP baseband upper layer processing functions, and DU complet...

AI Technical Summary

Problems solved by technology

[0007] 2) The differences in CU unit operating platform resources (CPU, memory, bandwidth, etc.) are not considered. Through the CU load high and low threshold judgment, when the CU unit load of the high-performance CU platform is migrated to the low-performance CU platform, low performance may result. The CU platform is crushed

Images