An Improved SVM Algorithm for Azimuth Estimation of Base Station Sector

doi:10.19678/j.issn.1000-3428.0057604

Abstract

Abstract: The azimuth of base station sector is an important parameter for the operation and maintenance of mobile networks,and also a key element of Base Station Almanac(BSA).However,currently the sector azimuth data is collected and managed manually,which increases the cost and disables real-time data update.To address the limits of the existing azimuth estimation methods,this paper simplifies azimuth estimation into the searching of optimal soft-margin of cell boundary under the constraints of base station location,and on this basis proposes an azimuth estimation method for base station sector based on soft-margin Support Vector Machine(SVM).The proposed algorithm utilizes mobile crowdsensing to estimate the azimuth based on the temporal-spatial distribution data of base station signals collected from the massive smart terminals.Considering the influence of imbalanced neighboring sector sample distribution on the estimation performance,the balanced C parameter is introduced into the algorithm for optimization.The experimental results show that compared with the Gaussian method and radial rasterization method,the proposed algorithm has higher accuracy and robustness,and is also less sensitive to the size of data samples.The new algorithm offers the prospect of improving the efficiency and intelligence of mobile network operation and maintenance.

Key words: soft-margin Support Vector Machine(SVM), sector azimuth, Base Station Almanac(BSA), mobile crowdsensing, network measurement

摘要： 基站扇区方向角是电信运营商进行移动网络运维的重要工参，也是基站信息表的关键要素，以人工方式为主的扇区方向角数据采集和管理方式存在成本高、数据更新不及时等问题。在分析现有方向角估计方法局限性的基础上，通过将方向角估计问题转化为基站站址约束下的最优软间隔边界求解问题，提出一种基于软间隔支持向量机的基站扇区方向角检测方法。利用移动众包感知的方式对从海量用户智能终端上采集的基站信号时空分布数据进行方向角估计，考虑到相邻扇区样本量分布差异对估计性能的影响，引入平衡C参数对检测方法进行优化。实验结果表明，相比高斯方法和径向栅格化方法，该方法的准确性和鲁棒性较高，对样本量的依赖性较低，在提高网络运维效率和智能化水平方面具有较高的应用价值。

关键词: 软间隔支持向量机, 扇区方向角, 基站信息表, 移动众包感知, 网络测量

CLC Number:

TP391

WANG Hai, WENG Chenao, LI Ke, LUO Xi. An Improved SVM Algorithm for Azimuth Estimation of Base Station Sector[J]. Computer Engineering, 2021, 47(4): 120-126.

王海, 翁晨傲, 李克, 骆曦. 一种面向基站扇区方向角估计的改进SVM算法[J]. 计算机工程, 2021, 47(4): 120-126.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0057604

http://www.ecice06.com/EN/Y2021/V47/I4/120

Figures/Tables 11

References

[1] LIANG Songbai,CHEN Feng,SONG Haiping,et al.Optimal azimuth positioning algorithm for base station antenna based on Gaussian distribution[J].Telecommunica-tions Science,2018,34(7):128-134.(in Chinese)梁松柏,陈锋,宋海平,等.基于高斯分布的基站天线最佳方向角定位算法[J].电信科学,2018,34(7):128-134.
[2] GAO Feng,LEI Lei,DU Rilan,et al.Verification of the cell azimuth based on clustering of sampling point and division of switching quadrant[J].Telecommunications Science,2017,33(5):106-112.(in Chinese)高峰,雷蕾,杜日览,等.基于采样点聚类和切换象限划分核查小区方位角[J].电信科学,2017,33(5):106-112.
[3] LI Ke,WANG Hai,XU Xiaolong,et al.Mobile network cell information detection method based on mobile crowdsensing[J].Computer Engineering,2019,45(2):92-100.(in Chinese)李克,王海,徐小龙,等.基于众包感知的移动网络小区信息侦测方法[J].计算机工程,2019,45(2):92-100.
[4] GANTI R,YE F,LEI H.Mobile crowdsensing:current state and future challenges[J].IEEE Communications Magazine,2011,49(11):32-39.
[5] WANG Leye,ZHANG Daqing,WANG Yasha,et al.Sparse mobile crowdsensing:challenges and opportunities[J].IEEE Communications Magazine,2016,54(7):161-167.
[6] LIU Yunhao.Crowd computing[J].Communications of the CCF,2012,8(10):38-42.(in Chinese)刘云浩.群智感知计算[J].中国计算机学会通讯,2012,8(10):38-42.
[7] CASAS P,SEUFERT M,WAMSER F,et al.Next to you:monitoring quality of experience in cellular networks from the end-devices[J].IEEE Transactions on Network and Service Management,2016,13(2):181-196.
[8] MOHAN P,PADMANABHAN V,RAMJEE R.Nericell:RICH monitoring of road and traffic conditions using mobile smartphones[C]//Proceedings of the 6th ACM Conference on Embedded Network Sensor Systems.New York,USA:ACM Press,2008:323-336.
[9] DUTTA P,AOKI P,KUMAR N,et al.Common sense:participatory urban sensing using a network of handheld air quality monitors[C]//Proceedings of the 7th ACM Conference on Embedded Networked Sensor Systems.New York,USA:ACM Press,2009:349-350.
[10] BULUT M F,DEMIRBAS M,FERHATOSMANOGLU H.LineKing:coffee shop wait-time monitoring using smartphones[J].IEEE Transactions on Mobile Computing,2015,14(10):2045-2058.
[11] VAPNIK V N.The nature of statistical learning theory[M].Berlin,Germany:Springer,2000.
[12] CORTES C,VAPNIK V N.Soft margin classifier[EB/OL].[2020-01-25].http://www.freepatentsonline.com/5640492.pdf.
[13] SHAWE-TAYLOR J,CRISTIANINI N.On the gene-ralization of soft margin algorithms[J].IEEE Transactions on Information Theory,2002,48(10):2721-2735.
[14] XU X,TSANG I W,XU D.Soft margin multiple kernel learning[J].IEEE Transactions on Neural Networks & Learning Systems,2013,24(5):749-761.
[15] HAJEWSKI J,OLIVEIRA S,STEWART D.Smoothed hinge loss and ℓ1 support vector machines[C]//Proceedings of ICDMW'18.Washington D.C.,USA:IEEE Press,2018:156-169.
[16] TATSUMI K,KAWACHI R,HAYASHIDA K,et al.Multiobjective multiclass soft-margin support vector machine maximizing pair-wise interclass margins[C]//Proceedings of ICONIP'09.Washington D.C.,USA:IEEE Press,2009:122-136.
[17] WANG Zhenghai,FAN Chen,HE Fengping,et al.Hyperspectral rock spectral classification based on the Decision Tree-Support Vector Machine(DT-SVMs)[J].Acta Scientiarum Naturalium Universitatis Sunyatseni,2014,53(6):93-97.(in Chinese)王正海,方臣,何凤萍,等.基于决策树多分类支持向量机岩性波谱分类[J].中山大学学报(自然科学版),2014,53(6):93-97.
[18] PARK K,DESAI J P.Machine learning approach for breast cancer localization[C]//Proceedings of 2017 International Conference on Manipulation,Automation and Robotics at Small Scales.Washington D.C.,USA:IEEE Press,2017:14-27.
[19] GEIB C,JILGE M,LAKES T,et al.Estimation of seismic vulnerability levels of urban structures with multisensor remote sensing[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2016,9(5):1913-1936.
[20] GUERMEUR Y.Combining discriminant models with new multi-class SVMs[J].Pattern Analysis & Applications,2002,5(2):168-179.

Please choose a citation manager

Content to export