摘要
随着5G技术蓬勃发展,我国铁路行业积极探索5G技术应用。通过部署铁路5G专网,可以提升专网承载能力,降低时延,提高铁路安全性、可靠性。铁路5G专网大尺度信道建模可辅助网络规划,优化铁路5G专网基站布设间距,从而降低网内干扰,节省建设成本。针对铁路5G专网,搭建外场试验环境,选用SS-RSRP作为场强检测指标,采集120 km/h运行速度下的数据,对3GPP TR 38.901模型进行修正,对不同PCI下数据进行平均处理及等间隔处理,利用Savitzky-Golay方法进行滑动平均滤波,梯度下降法进行传播模型路损公式拟合,最后使用RMSE、MAPE两个指标验证拟合公式的准确性。结果表明,120 km/h下RMSE降低了13.42%,MAPE降低了10.71%。使用京张高铁实测数据对拟合公式进行检验,RMSE降低了43.32%,MAPE降低了45.76%,说明修正后公式较TR 38.901模型更为准确,模型泛化能力增强,更加吻合实测数据,可提升铁路5G专网场景下的适用性。
With the booming of 5 G technology, China’s railway industry is actively exploring the application of 5 G technology. The deployment of railway dedicated 5 G network can improve the carrying capacity of the dedicated network, reduce latency, as well as enhance railway safety and reliability. Large scale channel modeling of railway dedicated 5 G network can assist network planning and optimize the layout of base stations of railway dedicated 5 G network, so as to reduce inter-system interference and save construction cost. Aiming at the railway dedicated 5 G network, this paper builds an out-field test environment. SS-RSRP is selected as the field strength detection indicator;data for 120 km/h operating speed are collected to modify the 3 GPP TR 38.901 model, and average processing and equal interval processing are performed based on the data under different PCIs. In addition, the Savitzky-Golay method is used for moving average filtering, and the gradient descent method is employed to fit the propagation model path loss formula. Finally, the two indicators of RMSE and MAPE are applied to verify the accuracy of the fitting formula. The results show that RMSE is decreased by 13.42% and MAPE by 10.71% at 120 km/h. Moreover, the measured data of the Beijing-Zhangjiakou High-speed Railway are employed to test the fitting formula, showing that the RMSE is decreased by 43.32% and the MAPE by 45.76%, which indicates that the revised formula is more accurate than the TR 38.901 model, the model generalization capacity is enhanced and more consistent with the measured data, and the applicability in the railway dedicated 5 G network is significantly improved.
作者
李岸宁
李辉
梁轶群
LI Anning;LI Hui;LIANG Yiqun(Postgraduate Department,China Academy of Railway Sciences,Beijing 100081,China;Signal and Communication Research Institute,China Academy of Railway Sciences Corporation Limited,Beijing 100081,China;National Research Center of Railway Intelligence Transportation System Engineering Technology,Beijing 100081,China)
出处
《铁道标准设计》
北大核心
2022年第8期162-167,共6页
Railway Standard Design
基金
中国国家铁路集团有限公司科技研究开发计划-系统性重大项目(P2020G004)
中国铁道科学研究院集团有限公司重大专项课题(2020YJ016)。
