Network state partition method based on SON, device and network system

Abstract

An embodiment of the invention provides a network state partition method based on an SON, a device and a network system, and relates to the communication field. Maintenance cost for network problems can be reduced, and efficiency of solving the network problems can be improved. The method comprises the steps that network state parameters are obtained, wherein the network state parameters comprise network KPIs, cell measurement values and control parameters; variable dimensionality reduction is conducted on the network state parameters; the network state parameters with the variably reduced dimensionality are clustered; change analysis is conducted on the network state parameters according to clustering results.

Description

technical field [0001] The present invention relates to the communication field, in particular to a network state division method, device and network system based on an ad hoc network (SON). Background technique [0002] In the process of operation and maintenance of the cellular network, the acquisition of the network status is obtained by the operator through the network management system Key Performance Indicator (KPI) statistical value to understand the current operating status of the network. When the network KPI statistical value Beyond the range preset by the operator, that is, when the network performance cannot reach the predetermined target, the operation and maintenance and network management personnel will learn about the problems caused by unreasonable network parameter configuration in network operation through empirical analysis methods. After obtaining the information, the network management personnel modify the corresponding network parameters according to t...

AI Technical Summary

Problems solved by technology

[0003] In the process of realizing the above-mentioned KPI statistics, the inventors found that the network status represented only by KPIs cannot reflect the problems of the network, and manual analysis is required, which requires a lot of human cost input and relevant expert knowledge

The trend of base station miniaturization leads to a large number of network elements in the network, which makes a large number of network performance statistical reports and the complexity of network problems increase sharply. Therefore, the network maintenance method that only relies on manpower not only causes high maintenance costs, but is also difficult to be effective. Accurately locate and solve network problems

Images