基于数据挖掘的RPMA低功耗广域网网络规划方法

doi:10.11959/j.issn.1000-436x.2019050

通信学报 ›› 2019, Vol. 40 ›› Issue (3): 28-35.doi: 10.11959/j.issn.1000-436x.2019050

基于数据挖掘的RPMA低功耗广域网网络规划方法

朱晓荣,沈瑶

南京邮电大学江苏省无线通信重点实验室，江苏南京 210003

修回日期:2019-01-16 出版日期:2019-03-01 发布日期:2019-04-04
作者简介:朱晓荣（1977- ），女，山东临沂人，博士，南京邮电大学教授、博士生导师，主要研究方向为5G网络、异构网络、无线传感器网络等无线资源管理、跨层优化算法及协议设计、性能评估及建模分析等。|沈瑶（1994- ），女，江苏常州人，南京邮电大学硕士生，主要研究方向为5G网络优化、无线大数据处理等。
基金资助:
江苏省研究生科研实践创新计划基金资助项目(KYCX17_0766);国家自然科学基金资助项目(61871237);江苏省高校自然科学研究重大项目基金资助项目(16KJA510005)

RPMA low-power wide-area network planning method based on data mining

Xiaorong ZHU,Yao SHEN

Jiangsu Key Laboratory of Wireless Communications,Nanjing University of Posts and Telecommunications,Nanjing 210003,China

Revised:2019-01-16 Online:2019-03-01 Published:2019-04-04
Supported by:
The Post Graduate Research ＆ Practice Innovation Program of Jiangsu Province(KYCX17_0766);The National Natural Science Foundation of China(61871237);The Natural Science Foundation of the Higher Education Institutions of Jiangsu(16KJA510005)

摘要/Abstract

摘要：

针对RPMA低功耗广域网基站密度大、业务分布不均匀等特点，提出了一种基于数据挖掘的网络规划方法。首先，利用提升回归树算法建立了信号质量预测模型，用于提取网络的覆盖分布空间模式；然后，针对覆盖分布空间模式，采用加权k-centroids分簇算法得到适应当前模式的最优基站部署；最后，根据总目标函数判定得到最终的基站拓扑。通过真实数据集的仿真实验结果表明，与传统的网络规划方法相比，所提的方法很好地提升低功耗广域网网络的覆盖质量。

关键词: 低功耗广域网, 提升回归树, 加权k-centroids, 基站部署

Abstract:

A network planning method based on data mining was proposed for RPMA low-power wide-area network with large density of base stations and uneven traffic distribution.First,a signal quality prediction model was established by using the boosting regression trees algorithm,which was used to extract the coverage distribution spacial pattern of the network.Then ,the weighted k-centroids clustering algorithm was utilized to obtain the optimal base station deployment for the current spacial pattern.Finally,according to the total objective function,the best base station topology was determined.Experiment results with the real data sets show that compared with the traditional network planning method,the proposed method can improve the coverage of low-power wide-area networks.

Key words: low power wide area network, boosting regression trees, weighted k-centroids, base station deployment

中图分类号:

TN915.81

朱晓荣,沈瑶. 基于数据挖掘的RPMA低功耗广域网网络规划方法[J]. 通信学报, 2019, 40(3): 28-35.

Xiaorong ZHU,Yao SHEN. RPMA low-power wide-area network planning method based on data mining[J]. Journal on Communications, 2019, 40(3): 28-35.

图/表 11

图1

图2

表1

表2

图3

图4

图5

表3

图6

图7

图8

参考文献 14

[1]	PATEL D , WON M . Experimental study on low power wide area networks (LPWAN) for mobile internet of things[C]// Vehicular Technology Conference. IEEE, 2017: 1-5.
[2]	HERNANDEZ D M , PERALTA G , MANERO L ,et al. Energy and coverage study of LPWAN schemes for Industry 4.0[C]// Electronics,Control,Measurement,Signals and their Application to Mechatronics . IEEE, 2017: 1-6.
[3]	KRUPKA L , VOJTECH L , NERUDA M . The issue of LPWAN technology coexistence in IoT environment[C]// International Conference on Mechatronics-Mechatronika. IEEE, 2016: 1-8.
[4]	YU G J , YEH K Y . A k-means based small cell deployment algorithmfor wireless access networks[C]// International Conference on Networking and Network Applications. IEEE, 2016: 393-398.
[5]	WANG S , ZHAO W , WANG C . Budgeted cell planning for cellular networks with small cells[J]. IEEE Transactions on Vehicular Technology, 2015,64(10): 4797-4806.
[6]	AMALDI E , CAPONE A , MALUCELLI F . Planning UMTS base station location:optimization models with power control and algorithms[J]. IEEE Transactions on Wireless Communications, 2003,2(5): 939-952.
[7]	LEE C Y , KANG H G . Cell planning with capacity expansion in mobile communications:a tabu search approach[J]. IEEE Transactions on Vehicular Technology, 2000,49(5): 1678-1691.
[8]	GHAZZAI H , YAACOUB E , ALOUINI M S ,et al. Optimized LTE cell planning with varying spatial and temporal user densities[J]. IEEE Transactions on Vehicular Technology, 2016,65(3): 1575-1589.
[9]	YANG Z H , CHEN M , WEN Y P ,et al. Cell planning based on minimized power consumption for LTE networks[C]// IEEE Wireless Communications and Networking Conference. IEEE, 2016: 1-6.
[10]	WANG S , RAN C . Rethinking cellular network planning and optimization[J]. IEEE Wireless Communications, 2016,23(2): 118-125.
[11]	ISTV S , FAZEKAS P . An algorithm for automatic base station placement in cellular network deployment[C]// EUNICE/IFIP WG 6.6 Conference on Networked Services and Applications:Engineering,Control and Management. Springer-Verlag, 2010: 21-30.
[12]	FRIEDMAN J H . Greedy function approximation:a gradient boosting machine[J]. The Annals of Statistics, 2001,29(5): 1189-1232.
[13]	WEN R , YAN W , ZHANG A N . Weighted clustering of spatial pattern for optimal logistics hub deployment[C]// IEEE International Conference on Big Data. IEEE, 2016: 3792-3797.
[14]	KANUNGO T , MOUNT D M , NETANYAHU N S ,et al. An efficient k-means clustering algorithm:analysis and implementation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002,40(7): 881-892.

属性名	说明
B_lat	基站经度
B_lon	基站纬度
B_alt	基站高度
B_power	发射功率
A_height	天线挂高
B_name	基站名
deploy region	部署地区号
last connect time	最后连接时间
last connect address	最后连接地址
UL PER（UL PDU error rate）	上行链路PDU误码率
UL SNR	上行链路信噪比
UL SF	上行链路扩频因子
UL signaled excess SNR	上行信号的信噪比盈余
UL target SNR error	上行信号信噪比与预定值的误差
network state	网络状态

属性名	说明
DL RSSI	下行链路接收信号强度指示器
DL SF	下行链路传输一个SDU时的平均扩频因子
P_lat	测试点经度
P_lon	测试点纬度

迭代次数/次	总目标函数值
1	640.93
2	581.79
3	554.43
4	548.89
5	548.66
6	547.08
7	546.87
8	539.41
9	535.54
10	535.41

基于数据挖掘的RPMA低功耗广域网网络规划方法

RPMA low-power wide-area network planning method based on data mining

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 14

相关文章 4

Metrics

推荐阅读 0

[1]	朱晓荣,张佩佩. 基于GAN的异构无线网络故障检测与诊断算法[J]. 通信学报, 2020, 41(8): 110-119.
[2]	朱晓荣,张倩. 面向多业务需求的NFV和SDN融合的资源优化算法[J]. 通信学报, 2018, 39(11): 54-62.
[3]	秦丹阳,贾爽,杨松祥,马静雅,张岩,丁群. 基于信任感知的无线传感器网络安全路由机制研究[J]. 通信学报, 2017, 38(10): 60-70.
[4]	袁泉,汤红波,黄开枝,王晓雷,赵宇. 基于Q-learning算法的vEPC虚拟网络功能部署方法[J]. 通信学报, 2017, 38(8): 172-182.