基于大数据挖掘的LTE网络弱覆盖分析及覆盖优化研究  

LTE network weak coverage analysis and coverage optimization based on big data mining

作　　者：邓扬鑫 赵夙[1] 朱晓荣[1] DENG Yangxin;ZHAO Su;ZHU Xiaorong(Jiangsu Key Laboratory of Wireless Communications,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学江苏省无线通信重点实验室,江苏南京210003

出　　处：《南京邮电大学学报（自然科学版）》2021年第2期20-28,共9页Journal of Nanjing University of Posts and Telecommunications：Natural Science Edition

基　　金：江苏省无线通信重点实验室开放研究基金(2019WICOM01);国家自然科学基金(61871237);江苏省高校自然科学研究重大项目(16KJA510005)资助项目。

摘　　要：随着LTE移动网络的发展,基站和用户数量爆炸性增加使得当前网络环境越发复杂,导致LTE网络中的弱覆盖问题越来越多。针对复杂场景的弱覆盖问题,进行了基于大数据挖掘的LTE网络弱覆盖分析及覆盖优化研究。首先,通过数据挖掘技术对现网数据集进行相关性分析与数据清洗,用于将杂乱的数据转换成有用数据集;然后针对数据集采用加权KNN算法建立信号预测模型;最后,以信号预测模型为基础,采用粒子群算法建立网络覆盖优化模型得到满足要求的最少基站数目与最优基站部署。通过现网数据的实验结果表明,该模型可将采样区域的弱覆盖栅格全部优化并且减少基站数目。With the development of long term evolution(LTE)mobile networks,the increasing number of base stations and users makes the current network environment more complicated,resulting in weak coverage problems increasingly in LTE networks.Aiming at the problem of the weak coverage in complex scenarios,the LTE network weak coverage analysis and the coverage optimization based on big data mining are studied.Firstly,a data mining technology is used to perform correlation analysis and data cleaning on the existing network dataset to convert the messy data into an useful dataset.Then,a weighted K⁃nearest neignbor(KNN)algorithm is used to establish a signal prediction model for the dataset.Finally,based on the signal prediction model,the particle swarm optimization algorithm is used to establish the network optimization planning model to obtain the minimum number of base stations and the optimal base station deployment.Experimental results of actual data show that the model can optimize all the weak coverage grids in the sampling area and reduce the number of base stations.

关 键 词：LTE 数据挖掘 加权KNN 粒子群算法 基站部署 

分 类 号：TN929.5[电子电信—通信与信息系统]