基于AdaBoost的链路质量预测机制研究

doi:10.11959/j.issn.1000-436x.2017233

摘要/Abstract

摘要：

在无线传感器网络中，节点所在环境复杂多变导致其通信链路质量的不可靠，若能提前感知链路质量信息，则能很大程度上降低网络中节点的额外能量消耗。在分析现有链路质量预测方法的基础上，提出基于AdaBoost的链路质量预测机制。通过收集多个实验场景下的链路质量样本，采用基于密度的无监督聚类算法对训练样本划分链路质量等级；采用以支持向量机为弱分类器的 AdaBoost 算法，构建链路质量预测机制。实验结果表明，所提预测机制具有较高的预测精度。

关键词: 无线传感网络, 链路质量预测, AdaBoost, 链路质量等级划分

Abstract:

The link quality was vulnerable to the complexity environment in wireless sensor network.Obtaining link quality information in advance could reduce energy consumption of nodes.After analyzing the existing link quality prediction methods,AdaBoost-based link quality prediction mechanism was put forward.Link quality samples in deferent scenarios were collected.Density-based unsupervised clustering algorithm was employed to classify training samples into deferent link quality levels.The AdaBoost with SVM-based component classifiers was adopted to build link quality prediction mechanism.Experimental results show that the proposed mechanism has better prediction precision.

Key words: wireless sensor network, link quality prediction, AdaBoost, classification for link quality

中图分类号:

TP393

舒坚,刘满兰,郑巍. 基于AdaBoost的链路质量预测机制研究[J]. 通信学报, 2017, 38(Z1): 39-45.

Jian SHU,Man-lan LIU,Wei ZHENG. Study on AdaBoost-based link quality prediction mechanism[J]. Journal on Communications, 2017, 38(Z1): 39-45.

图/表 12

图1

图2

图3

图4

图5

图6

图7

表1

图8

图9

图10

图11

参考文献 28

[3]	HU C , WANG Y , WANG H . Survey on charging programming in wireless rechargeable sensor networks[J]. Journal of Software, 2016,27(1): 72-95.
[4]	SRINIVASAN K , DUTTA P , TAVAKOLI A ,et al. Understanding the causes of packet delivery success and failure in dense wireless sensor networks[C]// The 4th Int Conf on Embedded Networked Sensor Systems. ACM, 2006: 419-420.
[5]	ZHAO J , GOVINDAN R . Understanding packet delivery performance in dense wireless sensor networks[C]// The 1st Int Conf on Embedded Networked Sensor Systems, 2003: 1-13.
[6]	ALIZAI M H , LANDSIEDEL O , WEHRLE K . Bursty traffic over bursty links[C]// International Conference on Embedded Networked Sensor Systems. 2009: 71-84.
[7]	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.
[8]	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.
[9]	WOO A , TONG T , CULLER D . Taming the underlying challenges of reliable multihop routing in sensor networks[C]// International Conference on Embedded Networked Sensor Systems. 2003: 14-27.
[1]	李建中, 高宏 . 无线传感器网络的研究进展[J]. 计算机研究与发展, 2008,45(1): 1-15.
	LI J Z , GAO H . Survey on sensor network research[J]. Journal of Computer Research and Development, 2008,45(1): 1-15.
[10]	BACCOUR N , KOUBAA A , YOUSSEF H ,et al. Reliable link quality estimation in low-power wireless networks and its impact on tree-routing[J]. Ad Hoc Networks, 2015,27(C): 1-25.
[11]	REKIK S , BACCOUR N , JMAIEL M ,et al. Low-power link quality estimation in smart grid environments[C]// Wireless Communications and Mobile Computing Conference. 2015: 1211-1216.
[2]	田贤忠, 阳胜 . 基于网络编码的无线传感器网络瓶颈区域生存时间优化策略[J]. 计算机学报, 2016,39(5): 1039-1050.
	TIAN X Z , YANG S . Optimization strategy of lifetime for bottleneck zone in wireless sensor networks based on network coding[J]. Chinese Journal of Computers, 2016,39(5): 1039-1050.
[12]	AFZAL S R , STUIJK S , NABI M ,et al. Effective link quality estimation as means to improved end-to-end packet delivery in high traffic mobile ad hoc networks[J]. Digital Communications and Networks, 2016,3(3): 150-163.
[13]	SENEL M , CHINTALAPUDI K , LAL D ,et al. A Kalman filter based link quality estimation scheme for wireless sensor networks[C]// Global Telecommunications Conference,GLOBECOM '07. 2007: 875-880.
[14]	BECHER A , LANDSIEDEL O , WEHRLE K . Towards short-term wireless link quality estimation[C]// Hot Emnets. 2008: 1-5.
[15]	SRINIVASAN K , KAZANDJIEVA M A , AGARWAL S ,et al. The β-factor:measuring wireless link burstiness[C]// The 6th ACM Conference on Embedded Network Sensor Systems. 2008: 29-42.
[16]	LIU T , CERPA A E . Foresee(4C):Wireless link prediction using link features[C]// International Conference on Information Processing in Sensor Networks. 2011: 294-305.
[17]	CERPA A , WONG J L , POTKONJAK M ,et al. Temporal properties of low power wireless links:modeling and implications on multi-hop routing[C]// ACM International Symposium on Mobile Ad Hoc Networking ＆ Computing. 2005: 414-425.
[18]	ZHAO Y , LI S , HOU J . Link quality prediction via a neighborhood-based nonnegative matrix factorization model for wireless sensor networks[J]. International Journal of Distributed Sensor Networks. 2015,2015(1): 1-8.
[19]	FREUND Y , SCHAPIRE R E . A decision-theoretic generalization of on-line learning and an application to boosting[J]. Journal of Computer ＆ System Sciences, 1997,55(1): 119-139.
[20]	FREUND Y , SCHAPIRE R E . Experiments with a new boosting algorithm[C]// Thirteenth International Conference on International Conference on Machine Learning. 1996: 148-156.
[21]	赵传君, 王素格, 李德玉 ,等. 基于分组提升集成的跨领域文本情感分类[J]. 计算机研究与发展, 2015,52(3): 629-638.
	ZHAO C J , WANG S G , LI D Y ,et al. Cross-domain text sentiment classification based on grouping-adaboost ensemble[J]. Journal of Computer Research and Development, 2015,52(3): 629-638.
[22]	惠国保, 童一飞, 李东波 . 基于改进的图像局部区域相似度学习架构的图像特征匹配技术研究[J]. 计算机学报, 2015,38(6): 1148-1161.
	HUI G B , TONG Y F , LI D B . Image features matching based on improved patch similarity learning framework[J]. Chinese Journal of Computers, 2015,38(6): 1148-1161.
[23]	葛启发, 冯夏庭 . 基于AdaBoost组合学习方法的岩爆分类预测研究[J]. 岩土力学, 2008,29(4): 943-948.
	GE Q F , FENG X T . Classification and prediction of rockburst using AdaBoost combination learning method[J]. Rock and Soil Mechanics, 2008,29(4): 943-948.
[24]	LI X , WANG L , SUNG E . AdaBoost with SVM-based component classifiers[J]. Engineering Applications of Artificial Intelligence, 2008,21(5): 785-795.
[25]	张震, 汪斌强, 梁宁宁 ,等. 一种基于 AdaBoost-SVM 的流量分类方法[J]. 计算机应用研究, 2013,30(5): 1481-1485.
	ZHANG Z , WANG B Q , LIANG N N ,et al. Internet traffic classification based on AdaBoost-SVM[J]. Application Research of Computers, 2013,30(5): 1481-1485.
[26]	SRINIVASAN K , LEVIS P . RSSI is under appreciated[C]// IEEE the Third workshop on Embedded Networkd Sensors (EmNets). 2006: 239-243.
[27]	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.
[28]	李宗林, 罗可 . DBSCAN 算法中参数的自适应确定[J]. 计算机工程与应用, 2016,52(3): 70-73.
[3]	胡诚, 汪芸, 王辉 . 无线可充电传感器网络中充电规划研究进展[J]. 软件学报, 2016,27(1): 72-95.
[28]	LI Z L , LUO K . Research on adaptive parameters determination in DBSCAN algorithm[J]. Computer Engineering and Applications, 2016,52(3): 70-73.

实验场景	AUC	个数
校园小树林10 m东	0.738 805 970 149	32
校园小树林10 m南	0.731 767 180 926	22
校园小树林10 m西	0.864 352 298 296	5
校园小树林10 m北	0.901 743 478 848	4
校园小树林15 m东	0.562 934 027 778	44
校园小树林15 m南	0.699 579 831 93	28
校园小树林15 m西	0.864 352 298 29	3
校园小树林15 m北	0.901 743 478 84	4
办公室内南6 m	0.996 658 312 448	9
办公室内东6 m	0.823 915 463 621	8
办公室内南3 m	0.941 257 203 33	35
办公室内东3 m	0.818 468 597 648	33
室外停车场6 m	0.767 001 114 827	25
室外停车场10 m	0.655 172 413 793	28