5G network weak coverage area locking and adjusting method based on GNG mode

Abstract

The invention provides a 5G network weak coverage area locking and adjusting method based on a GNG mode. The 5G network weak coverage area locking and adjusting method comprises the following steps: step 1, initializing an input space N; step 2, initializing a network A; step 3, updating the input space N; and step 4, executing a GNG algorithm, gradually increasing new nodes, adjusting the positions of original nodes in the network A, and training a stable network A. According to the invention, the loss of the weak coverage area caused by unreasonable setting of the DBSCAN threshold can be avoided.

Description

technical field [0001] The invention belongs to the technical field of mobile communication, and in particular relates to a method for locking and adjusting a weak coverage area of ​​a 5G network based on a GNG method. Background technique [0002] With the issuance of 5G licenses in 2019, my country's 5G construction has entered the stage of large-scale deployment. Due to the high frequency band of 5G, the single-station coverage capability is weaker than that of 4G. In the early stage of 5G network deployment, base stations and 4G sites are co-located at a ratio of 1:1, which is prone to weak coverage areas. To ensure that operators build 5G quality networks with excellent experience, more accurate positioning methods for weak coverage areas are required. [0003] The existing 4G weak coverage area positioning adopts the MR (Measurement Report) big data positioning method, and uses the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to perfor...

AI Technical Summary

Problems solved by technology

[0010] (1) When the density of spatial clustering is not uniform and the distance between clusters is very different, it is difficult to select the parameters MinPts and Eps, and the clustering effect is not ideal: if the value of MinPts is too small, the results in sparse clusters will be less dense than MinPts. Therefore, it is considered as a boundary point and is not used for further expansion in the class; if the value is too large, two adjacent clusters with higher density may be merged into the same cluster

If MinPts remains unchanged and the value of Eps is too large, most points will be gathered in the same cluster; if Eps is too small, a cluster will split; A cluster midpoint is marked as an outlier, and the MinPts is too small, which will lead to the discovery of a large number of core points

[0011] (2) It only reflects the phased weak coverage problem, which is easily affected by short-term factors such as seasons and holidays, and it is difficult to observe the overall trend, which has certain limitations for guiding construction: in suburban agricultural areas, the degree of leaf density has a greater impact on network coverage. The signal propagation attenuation is as high as 10dB due to the shading of trees in summer. When data is extracted in summer months, there are obviously more weak coverage areas than in winter, and there are more demands for building stations after clustering; Or the MR data in January cannot expose weak coverage areas using the DBSCAN clustering algorithm, and form reasonable construction suggestions

Images