通信学报 ›› 2019, Vol. 40 ›› Issue (4): 202-211.doi: 10.11959/j.issn.1000-436x.2019025

• 学术通信 • 上一篇    下一篇

基于随机森林的链路质量预测

刘琳岚1,高声荣1,舒坚2()   

  1. 1 南昌航空大学信息工程学院,江西 南昌 330063
    2 南昌航空大学软件学院,江西 南昌 330063
  • 修回日期:2019-03-12 出版日期:2019-04-25 发布日期:2019-05-05
  • 作者简介:刘琳岚(1968-),女,湖南东安人,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、分布系统等。|高声荣(1994-),男,江西南康人,南昌航空大学硕士生,主要研究方向为无线传感器网络。|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。
  • 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);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(20171BBH80022);江西省教育厅科学技术重点基金资助项目(GJJ150702);江西省研究生创新专项资金资助项目(YC2017024)

Link quality prediction based on random forest

Linlan LIU1,Shengrong GAO1,Jian SHU2()   

  1. 1 School of Information Engineering,Nanchang Hangkong University,Nanchang 330063,China
    2 School of Software,Nanchang Hangkong University,Nanchang 330063,China
  • Revised:2019-03-12 Online:2019-04-25 Published:2019-05-05
  • Supported by:
    The National Natural Science Foundation of China(61762065);The National Natural Science Foundation of China(61363015);The Natural Science Foundation of Jiangxi Province(20171BAB202009);The Natural Science Foundation of Jiangxi Province(20171BBH80022);The Key Research Foundation of Education Bureau of Jiangxi Province(GJJ150702);The Innovation Foundation for Postgraduate Student of Jiangxi Province(YC2017024)

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。

关键词: 无线传感器网络, 链路质量预测, 随机森林, 链路质量等级

Abstract:

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.

Key words: wireless sensor network, link quality prediction, random forest, link quality level

中图分类号: 

No Suggested Reading articles found!