一种基于GRNN模型的5G基站电磁辐射预测方法  

A prediction method of 5G base station electromagnetic radiation based on GRNN model

作　　者：周晓雅 石丹[1] 张朋 马红兵[2] 钟志刚[3] 马俊[4] 张方建 ZHOU Xiaoya;SHI Dan;ZHANG Peng;MA Hongbing;ZHONG Zhigang;MA Jun;ZHANG Fangjian(School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China;China United Network Communication Group Co.,Ltd.,Beijing 100048,China;China Information Technology Designing&Consulting Institute Co.,Ltd.,Zhengzhou Henan 450007,China;ZTE Corporation,Shenzhen Guangdong 510000,China;Henan Branch of China Tower Co.,Ltd.,Pingdingshan Henan 467036,China)

机构地区：[1]北京邮电大学电子工程学院,北京100876 [2]中国联合网络通信集团有限公司,北京100048 [3]中讯邮电咨询设计院有限公司郑州分公司,河南郑州450007 [4]中兴通讯股份有限公司,广东深圳510000 [5]中国铁塔股份有限公司河南省分公司,河南平顶山467036

出　　处：《太赫兹科学与电子信息学报》2023年第11期1357-1363,1402,共8页Journal of Terahertz Science and Electronic Information Technology

基　　金：北京邮电大学研究生创新创业资助项目(2022-YC-A052)。

摘　　要：为更好地表征5G基站电磁辐射水平,本文针对电磁辐射预测方法进行研究,提出了一种基于广义回归神经网络(GRNN)模型的基站电磁辐射环境表征方法,对基站周围的理论最大辐射点接地平面处的瞬时宽带电场强度进行预测。在给定天线发射功率、5G基站与其理论最大辐射点的距离和数据传输时间的情况下,利用80%的数据作为训练集,20%的数据作为测试集,所得平均绝对百分比误差(MAPE)为0.0871,运行时间为3~5 min,表现出较好的预测精确度和较快的运行速度。与其他模型进行对比,预测精确度和求解效率大幅提高,且随着基站周围区域面积增大,优势愈发明显,具有很好的场景适用性。The electromagnetic radiation prediction method of 5G base station is studied.A General Regression Neural Network(GRNN)model-based electromagnetic radiation environment representation method for base station is proposed,and the instantaneous broadband electric field strength at the ground plane of the theoretical maximum radiation point around the base station is predicted.80%of the data is taken as the training set and 20%as the test set.Given the antenna transmission power,the distance between the 5G base station and its theoretical maximum radiant point,the data transmission time,the obtained Mean Absolute Percentage Error(MAPE)is 0.0871,and the operating time is 3~5 min.The method shows good prediction accuracy and fast running speed.At the same time,by comparing with other models,the superiority of the method is verified,which is manifested in the substantial improvement of prediction accuracy and efficiency.With the increase of the prediction range around the base station,the advantages become more obvious,and the method has good applicability to different scenarios.

关 键 词：基站电磁辐射 GRNN模型 电场强度 电磁环境表征 

分 类 号：TN929.5[电子电信—通信与信息系统]