基于改进GA-Elman的无线智能传播损耗预测方法

doi:10.19678/j.issn.1000-3428.0058231

摘要/Abstract

摘要： 在5G移动通信系统商用落地的背景下，设计准确、高效的信道估计方法对无线网络性能优化具有重要意义。基于改进GA-Elman算法，提出一种新的无线智能传播损耗预测方法。对Elman神经网络中的连接权值、阈值和隐藏神经元进行实数编码，在隐藏神经元编码中加入二进制控制基因，同时利用自适应遗传算法对权值、阈值和隐藏神经元数量进行优化，解决网络易陷入局部极小值和神经元数目难以确定的问题，从而提高预测性能。仿真结果表明，与仅优化连接权值及阈值的GA-Elman神经网络和标准Elman神经网络相比，该方法具有较高的预测精度。

关键词: 5G通信, 无线信道, 传播损耗, 遗传算法, Elman神经网络, 信道估计

Abstract: As the commercial use of 5G mobile communication systems starts,it is of great significance to design an accurate and efficient channel estimation method to optimize wireless network performance.Based on the improved GA-Elman algorithm,this paper proposes a new method for predicting the wireless propagation loss.The method employs real numbers to encode the connection weights,thresholds and hidden neurons of Elman neural network,and binary control genes are added to the hidden neuron coding.At the same time,the weights,thresholds and the number of hidden neurons are optimized by using the adaptive Genetic Algorithm(GA) in order to help prevent Elman neural network from falling into local minimum,and help determine the number of neurons,improving the prediction performance.The simulation results show that,compared with GA-Elman neural network which only has connection weights and thresholds optimized and standard Elman neural network,this method has higher predition accuracy.

Key words: 5G communication, wireless channel, propagation loss, Genetic Algorithm(GA), Elman neural network, channel estimation

中图分类号:

TN929.5

郑娟毅, 崔卓, 苏海龙, 殷帅帅, 刘遥遥. 基于改进GA-Elman的无线智能传播损耗预测方法[J]. 计算机工程, 2021, 47(7): 155-160,167.

ZHENG Juanyi, CUI Zhuo, SU Hailong, YIN Shuaishuai, LIU Yaoyao. Intelligent Method Based on Improved GA-Elman for Predicting the Wireless Propagation Loss[J]. Computer Engineering, 2021, 47(7): 155-160,167.

https://www.ecice06.com/CN/Y2021/V47/I7/155

图/表 8

20210721090708

20210721090711

20210721090714

20210721090718

20210721090721

20210721090724

20210721090727

20210721090731

参考文献

[1] 杨杉.基于高分辨率算法的室内毫米波无线信道传播特性研究[D].南京:南京邮电大学,2019. YANG S.Study on propagation characteristics of indoor millimeter wave wireless channel based on high resolution algorithm[D].Nanjing:Nanjing University of Posts and Telecommunications,2019.(in Chinese)
[2] 张华炜.无线MIMO信道建模与信道容量研究[D].西安:西安电子科技大学,2009. ZHANG H W.Research of wireless MIMO channel modeling and capacity[D].Xi'an:Xidian University,2009.(in Chinese)
[3] 于得水.高速环境下宽带无线信道测量、数据处理及信道模型的研究[D].北京:北京邮电大学,2014. YU D S.Research of channel measurement,data processing and channel modeling on wideband wireless channel in high-speed environment[D].Beijing:Beijing University of Posts and Telecommunications,2014.(in Chinese)
[4] BOCCARDI F,HEATH R W,LOZANO A,et al.Five disruptive technology directions for 5G[J].IEEE Communications Magazine,2014,52(2):74-80.
[5] OSTLIN E,ZEPERNICK H,SUZUKI H.Macrocell path loss prediction using artificial neural networks[J].IEEE Transactions on Vehicular Technology,2010,59(6):2735-2747.
[6] 韩晨,牛英滔.基于分层Q学习的联合抗干扰算法[J]. 计算机工程,2019,45(5):279-284. HAN C,NIU Y T.Joint anti-jamming algorithm based on hierarchical Q learning[J].Computer Engineering,2019, 45(5):279-284.(in Chinese)
[7] PHILLIPS C,SICKER D,GRUNWALD D.A survey of wireless path loss prediction and coverage mapping methods[J].IEEE Communications Surveys & Tutorials,2013,15(1):255-270.
[8] AYADI M,BEN Z A,TABBANE S.A UHF path loss model using learning machine for heterogeneous networks[J].IEEE Transactions on Antennas & Propagation,2017,65(7):3675-3683.
[9] 张摇.面向5G的室外高低频大尺度传播特性测量和信道模型分析[D].南京:南京邮电大学,2017. ZHANG Y.Outdoor large scale propagation characteristics measurements and channel models analysis at low and high frequencies for 5G wireless networks[D].Nanjing:Nanjing University of Posts and Telecommunications,2017.(in Chinese)
[10] IMT-2020(5G) Advance Group. White paper of 5G concept[EB/OL].[2020-04-02].http://www.imt-2020.cn/zh/documents/download/23.(in Chinese) IMT-2020(5G)推进组. 5G概念白皮书[EB/OL].[2020-04-02].http://www.imt-2020.cn/zh/documents/download/23.
[11] WANG C X,BIAN J,SUN J,et al.A survey of 5G channel measurements and models[J].IEEE Communications Surveys & Tutorials,2018,20(4):3142-3168.
[12] FENG R,HUANG J,SUN J,et al.A novel 3D frequency domain SAGE algorithm with applications to parameter estimation in mmWave massive MIMO indoor channels[J].Science China(Information Science),2017,60(8):54-65.
[13] HUANG J,WANG C X,FENG R,et al.Multi-frequency mmWave massive MIMO channel measurements and characterization for 5G wireless communication systems[J].IEEE Journal on Selected Areas in Communications,2017,35(7):1938-1983.
[14] ZHANG Y,WEN J X,YANG G S,et al.Path loss prediction based on machine learning:principle,method,and data expansion[J].Applied Sciences,2019,9(9):1908.
[15] ISABONA J,SRIVASTAVA V M.Hybrid neural network approach for predicting signal propagation loss in urban microcells[C]//Proceedings of 2016 IEEE Region 10 Humanitarian Technology Conference.Washington D.C.,USA:IEEE Press,2016:1-5.
[16] 胡文龙.LTE网络的无线传播模型校正和覆盖区域预测[D].武汉:华中科技大学,2018. HU W L.Wireless propagation model correction and coverage area prediction for LTE network[D].Wuhan:Huazhong University of Science and Technology,2018.(in Chinese)
[17] ZHANG H X,LU J.Creating ensembles of classifiers via fuzzy clustering and deflection[J].Fuzzy Sets & Systems,2010,161(13):1790-1802.
[18] 张广斌,张润梅.基于改进Elman神经网络的徽派古建筑寿命预测[J].中国科学技术大学学报,2017,47(10):817-822. ZHANG G B,ZHANG R M.Life span prediction of Huizhou architecture based on improved Elman neural network[J].Journal of University of Science and Technology of China,2017,47(10):817-822.(in Chinese)
[19] LI P H,LI Y G,XIONG Q Y,et al.Application of a hybrid quantized Elman neural network in short-term load forecasting[J].International Journal of Electrical Power & Energy Systems,2014,55:749-759.
[20] OKTA N,FADZIL H M,NORDIN Z,et al.A study of fluctuations and confidence of implementation in genetic algorithm optimized network in data centre[J].Intelligent Decision Technologies,2018,12(1):25-37.
[21] 邝先验,周扬栋,宋二猛.基于自适应GA_Elman神经网络的短时交通预测[J].计算机仿真,2018,35(7):103-107. KUANG X Y,ZHOU Y D,SONG E M.Short-term traffic forecasting based on adaptive GA_Elman neural network[J].Computer Simulation,2018,35(7):103-107.(in Chinese)
[22] 左世奇.大规模MIMO信道空间非平稳特性研究与统计性建模[D].南京:南京邮电大学,2018. ZUO S Q.Research on spatial non-stationary characteristics and statistical modeling of large-scale MIMO channels[D].Nanjing:Nanjing University of Posts and Telecommunica-tions,2018.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容