基于高斯过程回归的链路质量预测模型

doi:10.11959/j.issn.1000-436x.2018113

通信学报 ›› 2018, Vol. 39 ›› Issue (7): 148-156.doi: 10.11959/j.issn.1000-436x.2018113

基于高斯过程回归的链路质量预测模型

舒坚¹,刘满兰²,尚亚青²,陈宇斌¹,刘琳岚²()

¹ 南昌航空大学软件学院，江西南昌 330063
² 南昌航空大学信息工程学院，江西南昌 330063

修回日期:2018-05-25 出版日期:2018-07-01 发布日期:2018-08-08
作者简介:舒坚（1964-），男，江西南昌人，南昌航空大学教授、硕士生导师，主要研究方向为无线传感器网络、软件工程等。|刘满兰（1992-），女，湖南耒阳人，南昌航空大学硕士生，主要研究方向为无线传感器网络。|尚亚青（1991-），女，河南开封人，南昌航空大学硕士生，主要研究方向为无线传感器网络。|陈宇斌（1977-），男，江西南昌人，南昌航空大学讲师，主要研究方向为无线传感器网络、高性能计算。|刘琳岚（1968-），女，湖南东安人，南昌航空大学教授，主要研究方向为无线传感器网络、分布系统等。
基金资助:
国家自然科学基金资助项目(61762065);国家自然科学基金资助项目(61363015);国家自然科学基金资助项目(61501218);国家自然科学基金资助项目(61501217);江西省自然科学基金资助项目(20171BAB202009);江西省自然科学基金资助项目(20171ACB20018)

Link quality prediction model based on Gaussian process regression

Jian SHU¹,Manlan LIU²,Yaqing SHANG²,Yubin CHEN¹,Linlan LIU²()

¹ School of Software,Nanchang Hangkong University,Nanchang 330063,China
² School of Information Engineering,Nanchang Hangkong University,Nanchang 330063,China

Revised:2018-05-25 Online:2018-07-01 Published:2018-08-08
Supported by:
The National Natural Science Foundation of China(61762065);The National Natural Science Foundation of China(61363015);The National Natural Science Foundation of China(61501218);The National Natural Science Foundation of China(61501217);The Natural Science Foundation of Jiangxi Province(20171BAB202009);The Natural Science Foundation of Jiangxi Province(20171ACB20018)

摘要/Abstract

摘要：

基于链路质量的路由选择机制可有效感知当前链路的变化，且对无线传感器网络的可靠通信起着重要作用，基于此，提出基于高斯过程回归的链路质量预测模型。通过灰关联方法计算链路质量参数与分组接收率的关联度，选取链路质量指示均值和信噪比均值作为模型的输入参数，以降低计算复杂度。采用链路质量指示均值、信噪比均值和分组接收率构建基于组合协方差函数的高斯过程回归模型预测链路质量。稳定场景与不稳定场景下的实验结果表明，与动态贝叶斯网络预测模型相比，所提模型具有更好的预测精确度。

关键词: 无线传感器网络, 高斯过程回归, 链路质量预测, 组合协方差函数, 灰关联算法

Abstract:

Link quality is an important factor of reliable communication and the foundation of upper protocol design for wireless sensor network.Based on this,a link quality prediction model based on Gaussian process regression was proposed.It employed grey correlation algorithm to analyze correlation between link quality parameters and packet receive rate.The mean of the link quality indication and the mean of the signal-to-noise were selected as input parameters so as to reduce the computational complexity.The above parameters and packet receive rate were taken to build Gaussian process regression model with combination of covariance function,so that link quality could be predicted.In the stable and unstable scenarios,the experimental results show that the proposed model has better prediction accuracy than the one of dynamic Bayesian network prediction model.

Key words: wireless sensor network, Gaussian process regression, link quality prediction, combination of covariance function, grey correlation algorithm

中图分类号:

TP393

舒坚,刘满兰,尚亚青,陈宇斌,刘琳岚. 基于高斯过程回归的链路质量预测模型[J]. 通信学报, 2018, 39(7): 148-156.

Jian SHU,Manlan LIU,Yaqing SHANG,Yubin CHEN,Linlan LIU. Link quality prediction model based on Gaussian process regression[J]. Journal on Communications, 2018, 39(7): 148-156.

图/表 10

图1

图2

图3

表1

稳定场景下灰关联度值"

参数	取值
$γ_{_{01}}$	0.84
$γ_{_{02}}$	0.89
$γ_{_{03}}$	0.85

表1

表2

不稳定场景下灰关联度值"

参数	取值
$γ_{_{01}}$	0.68
$γ_{_{02}}$	0.77
$γ_{_{03}}$	0.71

表2

图4

图5

表3

表4

表5

参考文献 34

[1]	孙佩刚, 赵海, 罗玎玎 ,等. 无线传感器网络链路通信质量测量研究[J]. 通信学报, 2007,28(10): 14-22.
	SUN P G , ZHAO H , LUO D D ,et al. Study on measurement of link communication quality in wireless sensor networks[J]. Journal on Communications, 2007,28(10): 14-22.
[2]	BACCOUR N,KOUB?A A , MOTTOLA L ,et al. Radio link quality estimation in wireless sensor networks:a survey[J]. ACM Transactions on Sensor Networks, 2012,8(4): 1-35.
[3]	PENGWON K , KOMOLMIS T , CHAMPRASERT P . Solving asymmetric link problems in WSNs using site link quality estimators and dual-tree topology[C]// International Conference on Electrical Engineering/electronics,Computer,Telecommunications and Information Technology. 2016: 1-4.
[4]	BAS C U , ERGEN S C . Spatio-temporal characteristics of link quality in wireless sensor networks[C]// IEEE Wireless Communications and Networking Conference. 2012: 1152-1157.
[5]	DEZFOULI B , RADI M , RAZAK S A ,et al. Modeling low-power wireless communications[J]. Journal of Network ＆ Computer Applications, 2015,51(C): 102-126.
[6]	SRINIVASAN K , LEVIS P . RSSI is under appreciated[C]// IEEE the Third Workshop on Embedded Networkd Sensors (EmNets). 2006: 239-242.
[7]	TANG L , WANG K C , HUANG Y ,et al. 4-compliant radio for factory environments[J]. IEEE Transactions on Industrial Informatics, 2007,3(2): 99-110.
[8]	QIN F , DAI X , MITCHELL J E . Effective-SNR estimation for wireless sensor network using Kalman filter[J]. Ad Hoc Networks, 2013,11(3): 944-958.
[9]	WOO A , CULLER D . Evaluation of efficient link reliability estimators for low-power wireless networks[C]// UCB Technical Report. 2003: 1-20.
[10]	黄庭培, 李栋, 张招亮 ,等. 突发性链路感知的自适应链路质量估计方法[J]. 通信学报, 2012,33(6): 30-39.
	HUANG T P , LI D , ZHANG Z L ,et al. Bursty-link-aware adaptive link quality estimation method[J]. Journal on Communications, 2012,33(6): 30-39.
[11]	COUTO D S J D , AGUAYO D , BICKET J ,et al. A high-throughput path metric for multi-hop wireless routing[J]. Wireless Networks, 2005,11(4): 419-434.
[12]	BOANO C A , Zú?IGA M A , VOIGT T ,et al. The triangle metric:fast link quality estimation for mobile wireless sensor networks[C]// The 19th International Conference on Computer Communication and Networks. 2010: 1-7.
[13]	BACCOUR N , KOUB?A A , YOUSSEF H .et al. F-LQE:a fuzzy link quality estimator for wireless sensor networks[C]// European Conference on Wireless Sensor Networks (EWSN). 2010: 240-255.
[14]	LIU T , CERPA A E . Data-driven link quality prediction using linkfeatures[J]. ACM Transactions on Sensor Networks, 2014,10(2): 1-35.
[15]	舒坚, 汤津, 刘琳岚 ,等. 基于模糊支持向量回归机的 WSNs 链路质量预测[J]. 计算机研究与发展, 2015,52(8): 1842-1851.
	SHU J , TANG J , LIU L L ,et al. Fuzzy support vector regression-based link quality prediction model for wireless sensor networks[J]. Journal of Computer Research and Development, 2015,52(8): 1842-1851.
[16]	WENG L N , ZHANG P , FENG Z Y ,et al. Short-term link quality prediction using nonparametric time series analysis[J]. Science China Information Sciences, 2015,58(8): 1-15.
[17]	舒坚, 刘松, 刘琳岚 ,等. 基于动态贝叶斯网络的 WSNs 链路质量预测[J]. 工程科学与技术, 2017,49(2): 152-159.
	SHU J , LIU S , LIU L L ,et al. Link quality prediction for WSNs based on dynamic Bayesian networks[J]. Advanced Engineering Sciences, 2017,49(2): 152-159.
[18]	FEOFLUSHING E , KUDELSKI M , NAGI J ,et al. Poster abstract:link quality estimation:a case study for on-line supervised learning in wireless sensor networks[C]// The 5th Workshop on Real-World Wireless Sensor Networks. 2014: 97-101.
[19]	夏战国, 夏士雄, 蔡世玉 ,等. 类不均衡的半监督高斯过程分类算法[J]. 通信学报, 2013,34(5): 42-51.
	XIA Z G , XIA S X , CAI S Y ,et al. Semi-supervised Gaussian process classification algorithm addressing the class imbalance[J]. Journal on Communications, 2013,34(5): 42-51.
[20]	CHEN X , WANG H , HUANG J ,et al. APU degradation prediction based on EEMD and Gaussian process regression[C]// IEEE International Conference on Sensing,Diagnostics,Prognostics,and Control. 2017: 98-104.
[21]	孙斌, 姚海涛, 刘婷 . 基于高斯过程回归的短期风速预测[J]. 中国电机工程学报, 2012,32(29): 104-109.
	SUN B , YAO H T , LIU T . Short-term wind speed forecasting based on Gaussian process regression model[J]. Proceedings of the Chinese Society for Electrical Engineering, 2012,32(29): 104-109.
[22]	李振刚 . 基于高斯过程回归的网络流量预测模型[J]. 计算机应用, 2014,34(5): 1251-1254.
	LI Z G . Network traffic forecasting model based on Gaussian process regression[J]. Journal of Computer Applications, 2014,34(5): 1251-1254.
[23]	陈艳, 王子健, 赵泽 ,等. 传感器网络环境监测时间序列数据的高斯过程建模与多步预测[J]. 通信学报, 2015,36(10): 252-262.
	CHEN Y , WANG Z J , ZHAO Z ,et al. Gaussian process modeling and multi-step prediction for time series data in wireless sensor network environmental monitoring[J]. Journal on Communications, 2015,36(10): 252-262.
[24]	李军, 张友鹏 . 基于高斯过程的混沌时间序列单步与多步预测[J]. 物理学报, 2011,60(7): 143-152.
	LI J , ZHANG Y P . Single-step and multiple-step prediction of chaotic time series using Gaussian process model[J]. Acta Physica Sinica, 2011,60(7): 143-152.
[25]	彭虹桥, 顾洁, 胡玉 ,等. 基于混沌粒子群—高斯过程回归的饱和负荷概率预测模型[J]. 电力系统自动化, 2017,41(21): 25-32,155.
	PENG H Q , GU J , HU Y ,et al. Forecasting model of saturated loadbased on ch aotic particle swar rm and optimizatioon-Gaussian proceess regression[J]. Automation of Electric Power Sysstems, 2017,41(211): 25-32,155.
[26]	乔少杰, 金琨, 韩楠 ,等. 一种基于高斯混合模型的轨迹预测算法[J]. 软件学报, 2015,26(5): 1048-10063.
	QIAO S J,JIIN K , HAN N .et al. Trajectory predicction algorithm base ed on Gaussiann mixture model[J]. Journal of Sofftware, 2015,26(55): 1048-1063.
[27]	耿雪青, 佘青山, 韩笑 ,等. 基于人工蜂群优化高斯过程的运动想象脑电信号分类[J]. 传感技术学报, 2017,30(3): 378-384.
	GENG X Q , SHE Q S , HAN X ,et al. Classificati on of motor imageery EEG based oon Gaussian processs optimized with arrtificial bee colony[[J]. Chinese Jourrnal of Sensor and Actuators, 2017,300(3): 378-384.
[28]	SRINIVASAN K , DUTTA P , TAVAKOLI A .et al. An empirical stud dy of low-poweer wireless[J]. ACM Transactions on Sensor Network ks, 2010,6(2): 1-49.
[29]	GUNGOR V C , LU B , HANCKE G P . Opportunitties and challenges of wireless senssor networks in smart grid[J]. IEEE Transactions on I Industrial Electtronics, 2010,57(10 0): 3557-3564.
[30]	HONG L , LIU X , ZHANG L ,et al. Towards ssensitive link qualiity prediction in ad hoc routing prootocol based on grey theory[J]. Wirele ess Networks, 2015,21(7): 2315-23325.
[31]	梁宁, 耿立艳, 张占福 ,等. 基于GRA与SVM-mixed的货运量预测方法[J]. 交通运输系统工程与信息, 2016,16(6): 94-99.
	LIANG N , GENG L Y , ZHANG Z F ,et al. A p prediction method of railway freigght volumes using GRA and SVM- mixed[J]. Journal of Transportatio on Systems Enginneering and Info rrmation Technolog gy, 2016,16(6): 94-99.
[32]	田民, 刘思峰, 卜志坤 . 灰色关联度算法模型的研究综述[J]. 统计与决策,2008, 2008(1): 24-27.
	TIAN M , LI IU S F , BU Z K . Research summarry of grey relationnal model[J]. Sta atistics and Decisioon, 2008,2008(1): 224-27.
[33]	万良勇, 刘开云 . 公路隧道交通量预测的粒子群高斯过程耦合模型[J]. 北京交通大学学报, 2015,39(1): 33-39.
	WAN L Y , LIU K Y . Traffic flo ow prediction model of highway tunnnel based on PSO-Gaussian processs coupled algorithm[J]. Journal of Be eijing Jiaotongg University, 2015,39(1): 33-39.
[34]	崔玮, 吴成东, 张云洲 ,等. 基于高斯混合模型的非视距定位算法[J]. 通信学报, 2014,35(1): 99-106.
	CUI W , WU C D , ZHANG Y Z ,et al. GMM-bassed localization alg gorithm under NLOS conditions[J]. Journal on Communications, 2014,35(1): 99-1066.

预测模型	稳定场景	不稳定场景
C-GPR	0.043 1	0.121 4
3-C-GPR	0.045 1	0.144 7

预测模型	稳定场景	不稳定场景
C-GPR	0.043 1	0.121 4
SE-GPR	0.056 4	0.149 6

预测模型	稳定场景	不稳定场景
C-GPR	0.043 1	0.121 4
DBN	0.094 3	0.323 4

基于高斯过程回归的链路质量预测模型

Link quality prediction model based on Gaussian process regression

在线阅读

PDF下载

可视化

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 34

相关文章 15

Metrics

推荐阅读 0

[1]	赵越, 李赞, 李冰, 郝本建. TDoA定位盲区分析与节点部署策略研究[J]. 通信学报, 2023, 44(1): 1-13.
[2]	李翠然, 王雪洁, 谢健骊, 吕安琪. 基于改进PSO的铁路监测线性无线传感器网络路由算法[J]. 通信学报, 2022, 43(5): 155-165.
[3]	杜秀娟, 王丽娟, 刘静萍, 金龙. 基于归零神经动力学的水下无线传感器网络节点测距定位方法[J]. 通信学报, 2022, 43(10): 177-185.
[4]	孙爱晶, 李世昌, 张艺才. 基于PSO优化模糊C均值的WSN分簇路由算法[J]. 通信学报, 2021, 42(3): 91-99.
[5]	王天荆,李秀琴,白光伟,沈航. 无线传感器网络中基于自适应网格的多目标定位算法[J]. 通信学报, 2019, 40(7): 197-207.
[6]	郝晓辰,姚宁,解力霞,王姣姣,王立元. 联合功率与信道的WSN生命期优化博弈算法[J]. 通信学报, 2019, 40(4): 62-70.
[7]	刘琳岚,高声荣,舒坚. 基于随机森林的链路质量预测[J]. 通信学报, 2019, 40(4): 202-211.
[8]	武小年,张楚芸,张润莲,孙亚平. WSN中基于改进粒子群优化算法的分簇路由协议[J]. 通信学报, 2019, 40(12): 114-123.
[9]	刘浩然,赵赫瑶,邓玉静,王星淇,尹荣荣. 基于非合作博弈的无线传感器网络覆盖控制算法[J]. 通信学报, 2019, 40(1): 71-78.
[10]	乐燕芬,汤卓,盛存宝,施伟斌. 基于多分布密度位置指纹的高效室内定位算法研究[J]. 通信学报, 2019, 40(1): 172-179.
[11]	郝晓辰,王立元,刘金硕,解力霞,张文焕. WSN中基于双群体差分进化的资源分配优化算法[J]. 通信学报, 2018, 39(4): 68-75.
[12]	蒋婵,李陶深,梁俊斌. 移动低占空比无线传感器网络中低时延的数据持续性提高算法[J]. 通信学报, 2018, 39(3): 53-62.
[13]	王继红,石文孝. 认知无线传感器网络分簇路由协议综述[J]. 通信学报, 2018, 39(11): 156-169.
[14]	张晓莹,彭辉,陈红. 无线传感器网络隐私保护数据聚集技术[J]. 通信学报, 2018, 39(10): 130-142.
[15]	刘琳岚,许江波,李越,杨志勇. 基于深度信念网络的WSN链路质量预测[J]. 通信学报, 2017, 38(Z2): 17-25.