基于大数据挖掘的LTE网络重叠覆盖优化方法  

Optimization method for overlapping coverage of LTE networks based on big data mining

作　　者：张吉[1] 赵夙[1] 朱晓荣[1] ZHANG Ji;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）》2020年第6期92-99,共8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：随着无线网络的快速发展,网络中重叠覆盖现象越来越严重,重叠覆盖区域频繁切换,导致系统容量减小,增加了掉话的可能,极大降低受影响区域的用户感知性能,因此重叠覆盖是网络结构优化中的研究重点。文中基于南京市江宁地区的实际路测数据,提出了基于大数据的LTE网络重叠覆盖优化方法。首先,对采集到的数据进行预处理和扩充,然后使用随机森林算法提取产生重叠覆盖的重要参数,基于区域重叠覆盖率对该参数进行调节,并使用支持向量机算法预测参数调节后的区域重叠覆盖率。仿真实验结果表明,该方法有效降低了区域的重叠覆盖率。With the rapid development of wireless networks, the overlapping coverage of LTE networks is becoming more and more serious.Frequent handovers in overlapping coverage areas reduce the system capacity, increase the possibility of dropped calls and degrade the perceived performance of users in the areas affected by the overlapping coverage.Therefore, the overlapping coverage is the research focus in network structure optimization.According to the actual road test data in Jiangning New Area of Nanjing, an optimization method for the overlapping coverage in LTE networks based on big data mining is proposed.Firstly, the collected data are preprocessed and expanded.Then, the important parameters resulting in overlapping coverage are extracted by using a random forest algorithm.The parameters are adjusted based on the regional overlapping coverage rate.Finally, the support vector machine is used to predict the area overlapping coverage rate after adjustment.Simulation results show that the method can effectively reduce the overlapping coverage rate of the area.

关 键 词：LTE 重叠覆盖 数据挖掘 功率调节 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]