基于深度残差神经网络的5G信号室内分布预测  

Prediction of indoor 5G signal distribution based on deep residual neural network model

作　　者：胡荣青 张成挺[2] 任国伟 吕俊事 许高明[1] 刘太君[1] Hu Rongqing;Zhang Chengting;Ren Guowei;Lv Junshi;Xu Gaoming;Liu Taijun(Faculty of Electrical Engineering and Computer Science,Ningbo University,Ningbo 31521l,China;China Tobacco Zhejiang Industrial Co.,Ltd.,Ningbo 315504,China)

机构地区：[1]宁波大学信息科学与工程学院,浙江宁波315211 [2]浙江中烟工业有限责任公司,浙江宁波315504

出　　处：《电子技术应用》2024年第12期77-81,共5页Application of Electronic Technique

基　　金：国家自然科学基金(62371266,62071264)。

摘　　要：为解决5G信号室内覆盖的质量与稳定性问题,提出了一种基于深度残差神经网络的5G信号室内分布预测方法。采用基于全连接的深度残差神经网络构建预测模型,利用发射机与接收机的三维空间坐标信息和接收机的参考信号接收功率(Reference Signal Receiving Power, RSRP)数据作为输入特征,而无需收集复杂的环境特征信息。实验结果表明,该深度残差神经网络模型在不依赖详细环境参数的情况下,经归一化训练,预测出的RSRP与实际值相比,MAE为0.029 455,RMSE为0.041 495,能有效地预测室内的5G信号分布,验证了基于深度残差神经网络的预测方法在室内5G信号覆盖预测问题上的有效性,为优化室内5G网络部署和提升用户体验提供了科学依据和技术手段,具有重要的实际应用价值。In order to solve the problem of the quality and stability of indoor signal coverage of the fifth generation mobile com-munication technology(5G),a new indoor 5G signal distribution prediction method is proposed in this paper.A depth residual neural network model based on the full connection layer is adopted.The three-dimensional spatial coordinate information of trans-mitter and receiver and Reference Signal Receiving Power(RSRP)data of receiver are used as input features,without the need to collect complex environmental features.The experimental results show that the depth residual neural network model can effec-tively predict the indoor 5G signal distribution with MAE of 0.029455 and RMSE of 0.041495 compared with the actual value after normalized training without relying on detailed environmental parameters.This study confirms the effectiveness of the pre-diction method based on deep residual neural network in indoor 5G signal coverage prediction,which provides scientific basis and technical means for optimizing indoor 5G network deployment and improving user experience,and has important practical ap-plicationvalue.

关 键 词：深度残差神经网络 信号分布 信号强度 信号预测 RSRP 

分 类 号：TN929.5[电子电信—通信与信息系统]