基于二维LMBP神经网络的ISM频段预测算法

doi:10.11959/j.issn.1000-0801.2016083

Abstract

Abstract:

With the rapid development and application of short-range wireless communications technology，the electromagnetic interference of ISM（2.4 GHz）band has become more apparent.Using the spectral prediction algorithm to predict the information of spectrum occupancy has become an effective way to solve the problem of compatible coexistence between devices.On the basis of verifying the time-domain and frequency-domain correlation of ISM band，an LMBP neural network of time and frequency domain was proposed and applied in the spectral prediction of ISM band.Through simulations and theoretical analysis，the best training combination of time-frequency point （△t=5，△f=2）was obtained.This point improves 95% of the spectrum prediction accuracy under the conditions of the input vector N=9 of the neural network.It increased 9% and 4% prediction accuracy compared with Markov algorithm and time-domain LMBP neural network and it had a better convergence time of training.

Key words: time-frequency correlation of ISM band, BP neural network, LMBP neural network of time and frequency domain, accuracy of the spectrum prediction

Xiaoyu WAN,Pan HU,Zhengqiang WANG. Spectrum prediction algorithm in ISM band based on two-dimensional LMBP neural network[J]. Telecommunications Science, 2016, 32(3): 53-59.

Figures/Tables 10

References 15

[1]	GUNGOR V C ， HANCKE G P . Industrial wireless sensor networks： challenges，design principles and technical approaches[J]. IEEE Transactions on Industrial Electronics， 2009，56（10）：4258-4265.
[2]	FIRDAU S ， NUGROHO E ， SAHRONI A . ZigBee and wifi network interface on wireless sensor networks[C]// 2014 Makassar International Conference on Engineering and Informatics， November 26-30，2014， Makassar，Indonesia. New Jersey： IEEE Press， 2014：54-58.
[3]	XU R T ， SHI G T ， LUO J ， et al. MuZi：multi-channel ZigBee networks for avoiding wifi interference[C]// 2011 International Conference on Internet of Things and 4th International Conference on Cyber，Physical and Social Computing， October 19-22，2011， Dalian，China. New Jersey： IEEE Press， 2011：323-329.
[4]	MITOLA J ， MAQUIRE G Q . Cognitive radios：making software radios more personal[J]. IEEE Transactions on Personal Communications， 1999，6（4）：13-18.
[5]	XING X ， JING T ， CHENG W ， et al. Spectrum prediction in cognitive radio networks[J]. IEEE Transactions on Wireless Communications， 2013，20（2）：90-96.
[6]	HUANG P ， LIU C J ， YANG X ， et al. Wireless spectrum occupancy prediction based on partial periodic pattern mining[J]. IEEE Transactions on Parallel and Distributed Systems， 2014，25（7）：1925-1934.
[7]	吴建绒，胡津铭，秦继新 . 基于K-RBF 神经网络的认知无线电频谱预测[J]. 电视技术， 2014，38（5）：105-108. WU J R ， HU J M ， QIN J X . Prediction of spectrum based on K-RBF neural network in cognitive radio[J]. Video Engineering， 2014，38（5）：105-108.
[8]	张松 . 基于马尔科夫链的ZigBee信道选择算法的研究[D]. 上海：上海海洋大学， 2014. ZHANG S . ZigBee channel selection algorithm research based on Markov chain[D]. Shanghai： Shanghai Ocean University， 2014.
[9]	陈斌华 . 认知无线电系统中的频谱预测算法研究[D]. 北京：北京邮电大学， 2011. CHEN B H . Research on the spectrum prediction algorithm in cognitive radio system[D]. Beijing： Beijing University of Posts and Telecommunications， 2011.
[10]	CHEN D W ， YIN S X ， QIAN Z ， et al. Mining spectrum usage data：a large-scale spectrum measurement study[J]. IEEE Transactions on Mobile Computing， 2012，11（6）：1033-1046.
[11]	BAI S ， ZHOU X ， XU F J ， et al. “Soft decision”spectrum prediction based on improved-back-propagation neural networks[C]// 2015 11th International Conference on Natural Computation， April 27-29，2014， Zhangjiajie，China. New Jersey： IEEE Press， 2015：128-133.
[12]	DING G ， WANG J ， WU Q ， et al. Joint spectral-temporal spectrum prediction from incomplete historical observations[C]// 2014 IEEE Global Conference on Signal and Information Processing， October 19-22，2011， Atlanta，USA. New Jersey： IEEE Press， 2014：1325-1329.
[13]	DAS D ， DAS S ， et al. A survey on spectrum occupancy measurement for cognitive radio[J]. Wireless Personal Communications， 2015，85（4）：2581-2598.
[14]	习国泰 . 改进Levenberg-Marquardt算法的复杂度分析[D]. 上海：上海交通大学， 2012. XI G T . On the complexity of the modified Levenberg-Marquardt algorithm for nonlinear equations[D]. Shanghai： Shanghai Jiaotong University， 2012.
[15]	ZHOU G ， JENNIE S . Advanced neural network training algorithm with reduced complexity based on Jacobian deficiency[J]. IEEE Transactions on Neural Networks， 1998，9（3）：445-453.

Metrics

Recommended 0

No Suggested Reading articles found!

实测选项	参数值
实测仪器	Rohde＆Schwarz fsl3频谱分析仪
测量地点	重庆
测量时间	2015年2月7-13日
频率范围/GHz	2.4～2.483 5
采样频点/个	110
采样间隔/min	5
天线半径/m	90

算法			误差目标

	10^-1	10^-2	10^-3	10^-4	10^-5
时频二维LMBP	1.67	5.17	19.87	57.34	126.98
时域LMBP	3.61	9.87	28.17	75.36	253.17
Markov算法	5.54	19.92	38.13	87.95	312.43

Spectrum prediction algorithm in ISM band based on two-dimensional LMBP neural network

RichHTML

PDF下载

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 15

Related Articles 5

Metrics

Recommended 0

[1]	Lu LIU, Dan YANG, Ruijie CHEN, Jia LI, Xi ZHOU. Research on POI quality prediction based on KPCA-GA-BP neural network [J]. Telecommunications Science, 2023, 39(1): 108-116.
[2]	Jie ZHANG, Lihua YANG, Zenghao WANG, Bo HU, Qian NIE. A novel deep learning based time-varying channel prediction method [J]. Telecommunications Science, 2021, 37(1): 39-47.
[3]	Zenghao WANG,Lihua YANG,Lu CHENG,Jie ZHANG,Yan LIANG. BP neural network based Doppler frequency offset estimation method for 5G high-speed mobile system [J]. Telecommunications Science, 2020, 36(4): 83-90.
[4]	Huimin ZHAO,Jiangtao LUO,Junchao YANG,Zheng XU,Xiao LEI,Lin LUO. Research and application of prediction model based on ensemble BP neural network [J]. Telecommunications Science, 2016, 32(2): 60-67.
[5]	Yajun Jiang,Zhenlun Yang. Data Prefetching Model for VOD Proxy Based on GA-BP Neural Network [J]. Telecommunications Science, 2011, 27(5): 104-109.