基于随机森林的链路质量预测
|
摘要
链路质量预测对无线传感器网络的上层协议设计至关重要,通过链路质量预测方法选择高质量的链路通信,可以提高数据传输的可靠性和网络通信的效率。基于无监督聚类的高斯混合模型划分链路质量等级,采用零相位分量分析白化法去除样本间的相关性,计算信噪比、链路质量指示及接收信号强度指示的均值和方差,并将其结果作为链路质量参数;基于随机森林分类算法构建链路质量评估模型,采用随机森林回归算法构建链路质量预测模型,预测下一时刻的链路质量等级。在不同的实验场景下,与指数加权移动平均、三角度量、支持向量回归机和线性回归预测模型相比,所提预测模型具有更高的预测准确率。
Link quality prediction is vital to the upper layer protocol design of wireless sensor networks. Selecting high quality links with the help of link quality prediction mechanisms can improve data transmission reliability and network communication efficiency. The Gaussian mixture model algorithm based on unsupervised clustering was employed to divide the link quality level. Zero-phase component analysis(ZCA) whitening was applied to remove the correlation between samples. The mean and variance of signal to noise ratio, link quality indicator, and received signal strength indicator were taken as the estimation parameters of link quality, and a link quality estimation model was constructed by using a random forest classification algorithm. The random forest regression algorithm was used to build a link quality prediction model, which predicted the link quality level at the next moment. In different scenarios, comparing with exponentially weighted moving average, triangle metric, support vector regression and linear regression prediction models, the proposed prediction model has higher prediction accuracy.
Link quality prediction is vital to the upper layer protocol design of wireless sensor networks. Selecting high quality links with the help of link quality prediction mechanisms can improve data transmission reliability and network communication efficiency. The Gaussian mixture model algorithm based on unsupervised clustering was employed to divide the link quality level. Zero-phase component analysis(ZCA) whitening was applied to remove the correlation between samples. The mean and variance of signal to noise ratio, link quality indicator, and received signal strength indicator were taken as the estimation parameters of link quality, and a link quality estimation model was constructed by using a random forest classification algorithm. The random forest regression algorithm was used to build a link quality prediction model, which predicted the link quality level at the next moment. In different scenarios, comparing with exponentially weighted moving average, triangle metric, support vector regression and linear regression prediction models, the proposed prediction model has higher prediction accuracy.
引文
[1]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.JIANG C,LI T S,LIANG J B.Low-latency algorithm for improving data persistence in mobile low-duty-cycle wireless sensor network[J].Journal on Communications,2018,39(3):53-62.
[2]张策,张霞,李鸥,等.不可靠链路下基于压缩感知的WSN数据收集算法[J].通信学报,2016,37(9):131-141.ZHANG C,ZHANG X,LI O,et al.Compressive sensing based data gathering algorithm over unreliable links in WSN[J].Journal on Communications,2016,37(9):131-141.
[3]NOUHA B,LUCA M,HABIB Y,et al.Radio link quality estimation in wireless sensor networks:a survey[J].ACM Transactions on Sensor Networks,2012,8(4):688-722.
[4]TANG Q,WEN H,ZHAO J,et al.Load balanced and efficient data collection protocol for wireless sensor networks[J].International Journal of High Performance Computing&Networking,2017,10(6):463-473.
[5]LIU D,CAO Z,ZHANG Y,et al.Achieving accurate and real-time link estimation for low power wireless sensor networks[J].IEEE/ACMTransactions on Networking,2017,25(4):2096-2109.
[6]LU J,ZHU Y P,XU Z Q,et al.A reliable wireless sensor network routing method for power transmission line monitoring[J].Power System Technology,2017,41(2):644-650.
[7]JAYASRI T,HEMALATHA M.Link quality estimation for adaptive data streaming in WSNs[J].Wireless Personal Communications,2017,94(3):1543-1562.
[8]BOANO C A,ZU??IGA M A,VOIGT T,et al.The triangle metric:fast link quality estimation for mobile wireless sensor net-works[C]//International Conference on Computer Communication and Networks.2010:1-7.
[9]SUN W,LU W,LI Q,et al.WNN-LQE:wavelet-neural-network-based link quality estimation for smart grid WSNs[J].IEEE Access,2017,5:12788-12797.
[10]MI X,ZHAO H,ZHU J.Research on EWMA based link quality evaluation algorithm for WSN[C]//Cross Strait Quad-Regional Radio Science and Wireless Technology Conference(CSQRWC).2011:757-759.
[11]FONSECA R,GNAWALI O,JAMIESON K,et al.Four bit wireless link estimation[C]//ACM HotNets.2007:1-6.
[12]GOMES R D,QUEIROZ D V,LIMAFILHO A C,et al.Real-time link quality estimation for industrial wireless sensor networks using dedicated nodes[J].Ad Hoc Networks,2017,59:116-133.
[13]SHU J,LIU S,LIU L,et al.Research on link quality estimation mechanism for wireless sensor networks based on support vector machine[J].Chinese Journal of Electronics,2017,26(2):377-384.
[14]FARKAS K,HOSSMANN T,LEGENDRE F,et al.Link quality prediction in mesh networks[J].Computer Communications,2008,31(8):1497-1512.
[15]SRINIVASAN K,DUTTA P,TAVAKOLI A,et al.Understanding the causes of packet delivery success and failure in dense wireless sensornetworks[C]//International Conference on Embedded Networked Sensor Systems.2006:419-433.
[16]BACCOUR N,PUCCINELLI D,VOIGT T,et al.Overview of link quality estimation[M].Berlin:Springer,2013.
[17]赵腾,王林童,张焰,等.采用互信息与随机森林算法的用户用电关联因素辨识及用电量预测方法[J].中国电机工程学报,2016,36(3):604-614.ZHAO T,WANG L T,ZHANG Y,et al.Relation factor identification of electricity consumption behavior of users and electricity demand forecasting based on mutual information and random forests[J].Proceedings of the CSEE,2016,36(3):604-614.
[2]张策,张霞,李鸥,等.不可靠链路下基于压缩感知的WSN数据收集算法[J].通信学报,2016,37(9):131-141.ZHANG C,ZHANG X,LI O,et al.Compressive sensing based data gathering algorithm over unreliable links in WSN[J].Journal on Communications,2016,37(9):131-141.
[3]NOUHA B,LUCA M,HABIB Y,et al.Radio link quality estimation in wireless sensor networks:a survey[J].ACM Transactions on Sensor Networks,2012,8(4):688-722.
[4]TANG Q,WEN H,ZHAO J,et al.Load balanced and efficient data collection protocol for wireless sensor networks[J].International Journal of High Performance Computing&Networking,2017,10(6):463-473.
[5]LIU D,CAO Z,ZHANG Y,et al.Achieving accurate and real-time link estimation for low power wireless sensor networks[J].IEEE/ACMTransactions on Networking,2017,25(4):2096-2109.
[6]LU J,ZHU Y P,XU Z Q,et al.A reliable wireless sensor network routing method for power transmission line monitoring[J].Power System Technology,2017,41(2):644-650.
[7]JAYASRI T,HEMALATHA M.Link quality estimation for adaptive data streaming in WSNs[J].Wireless Personal Communications,2017,94(3):1543-1562.
[8]BOANO C A,ZU??IGA M A,VOIGT T,et al.The triangle metric:fast link quality estimation for mobile wireless sensor net-works[C]//International Conference on Computer Communication and Networks.2010:1-7.
[9]SUN W,LU W,LI Q,et al.WNN-LQE:wavelet-neural-network-based link quality estimation for smart grid WSNs[J].IEEE Access,2017,5:12788-12797.
[10]MI X,ZHAO H,ZHU J.Research on EWMA based link quality evaluation algorithm for WSN[C]//Cross Strait Quad-Regional Radio Science and Wireless Technology Conference(CSQRWC).2011:757-759.
[11]FONSECA R,GNAWALI O,JAMIESON K,et al.Four bit wireless link estimation[C]//ACM HotNets.2007:1-6.
[12]GOMES R D,QUEIROZ D V,LIMAFILHO A C,et al.Real-time link quality estimation for industrial wireless sensor networks using dedicated nodes[J].Ad Hoc Networks,2017,59:116-133.
[13]SHU J,LIU S,LIU L,et al.Research on link quality estimation mechanism for wireless sensor networks based on support vector machine[J].Chinese Journal of Electronics,2017,26(2):377-384.
[14]FARKAS K,HOSSMANN T,LEGENDRE F,et al.Link quality prediction in mesh networks[J].Computer Communications,2008,31(8):1497-1512.
[15]SRINIVASAN K,DUTTA P,TAVAKOLI A,et al.Understanding the causes of packet delivery success and failure in dense wireless sensornetworks[C]//International Conference on Embedded Networked Sensor Systems.2006:419-433.
[16]BACCOUR N,PUCCINELLI D,VOIGT T,et al.Overview of link quality estimation[M].Berlin:Springer,2013.
[17]赵腾,王林童,张焰,等.采用互信息与随机森林算法的用户用电关联因素辨识及用电量预测方法[J].中国电机工程学报,2016,36(3):604-614.ZHAO T,WANG L T,ZHANG Y,et al.Relation factor identification of electricity consumption behavior of users and electricity demand forecasting based on mutual information and random forests[J].Proceedings of the CSEE,2016,36(3):604-614.