典型文献
LDM-Satellite:A New Scheme for Packet Loss Classification over LEO Satellite Network
文献摘要：
The packet loss classification has always been a hot and difficult issue in TCP congestion con-trol research.Compared with the terrestrial network,the probability of packet loss in LEO satellite net-work increases dramatically.What's more,the prob-lem of concept drifting is also more serious,which greatly affects the accuracy of the loss classification model.In this paper,we propose a new loss classifica-tion scheme based on concept drift detection and hy-brid integration learning for LEO satellite networks,named LDM-Satellite,which consists of three mod-ules:concept drift detection,lost packet cache and hy-brid integration classification.As far,this is the first paper to consider the influence of concept drift on the loss classification model in satellite networks.We also innovatively use multiple base classifiers and a naive Bayes classifier as the final hybrid classifier.And a new weight algorithm for these classifiers is given.In ns-2 simulation,LDM-Satellite has a better AUC(0.9885)than the single-model machine learning clas-sification algorithms.The accuracy of loss classifica-tion even exceeds 98％,higher than traditional TCP protocols.Moreover,compared with the existing pro-tocols used for satellite networks,LDM-Satellite not only improves the throughput rate but also has good fairness.
文献关键词：
中图分类号：
作者姓名：
Ning Li;Qiaodi Zhu;Zhongliang Deng
作者机构：
School of Electronic Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China
文献出处：
引用格式：
[1]Ning Li;Qiaodi Zhu;Zhongliang Deng-.LDM-Satellite:A New Scheme for Packet Loss Classification over LEO Satellite Network)[J].中国通信（英文版）,2022(12):207-215
A类：
tocols
B类：
LDM,Satellite,New,Scheme,Packet,Loss,Classification,LEO,Network,packet,loss,classification,has,always,been,hot,difficult,issue,TCP,congestion,trol,research,Compared,terrestrial,probability,satellite,increases,dramatically,What,more,lem,concept,drifting,also,serious,which,greatly,affects,accuracy,model,In,this,paper,propose,new,scheme,detection,integration,learning,networks,named,consists,three,ules,lost,cache,far,first,consider,influence,We,innovatively,multiple,classifiers,naive,Bayes,final,hybrid,And,weight,these,given,simulation,better,than,single,machine,algorithms,even,exceeds,higher,traditional,protocols,Moreover,compared,existing,used,not,only,improves,throughput,rate,but,good,fairness
AB值：
0.485365
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
