基于连续聚类算法的5G站址敏捷规划方案

Research on 5G site planning scheme based on continuous clustering algorithm

目前5G站址规划方法主要基于人工规划或者简单的密度聚类算法输出,人工规划方法虽然准确度较高,但是需投入大量人力资源,较大程度依赖规划设计人员的经验和学识等,耗时长且过程繁琐。因此人工规划方法只能适用于小范围(补点)的站址规划,无法适用于5G大范围及全网的站址规划。针对上述问题,本文提出一种基于栅格密度的连续聚类算法,通过5G仿真结果作为数据源输入,对弱覆盖栅格进行前置处理,经过首次DBSCAN密度聚类输出初步有效栅格数据,再次引用K-Means聚类算法输出5G规划站址,最后再使用K-Value等于3的K-Means聚类算法完成初始工参规划,较好提升5G站址和工参等规划的精准性及高效性。

At present,5G site agile planning method is mainly based on manual planning or simple density clustering algorithm output.Although the manual planning method has high accuracy,it needs to invest a lot of human resources,and largely depends on the experience and knowledge of planning and design personnel,which is time-consuming and cumbersome.Therefore,the manual planning method can only be applied to the station location planning in a small area(additional points),but can not be applied to the station location planning in 5G large area and the whole network.In order to solve the above problems,a continuous clustering algorithm based on grid density is proposed.5G simulation results are used as the data source input,and the weak coverage grid is preprocessed.After the fi rst DBSCAN density clustering,the preliminary effective grid data is output.Then the K-means clustering algorithm is used to output 5G planning site.Finally,the K-means clustering algorithm with k-value equal to 3 is used to complete the initial work parameters.To better improve the accuracy and effi ciency of 5G station site planning and engineering reference planning.