工程科学学报，第37卷，第1期：132143,2015年1月 Chinese Journal of Engineering,Vol.37,No.1:132-143,January 2015 DOI:10.13374/j.issn2095-9389.2015.01.020:http://journals.ustb.edu.cn 基于带宽与往返时间联合预测的多路径并行传输性 能优化算法 李文12》区，王文博》，景晓军”，刘文)，张超) 1)北京邮电大学信息与通信工程学院，北京1008762)中国电子系统设备工程公司研究所，北京100000 3)北京邮电大学泛网无线通信教有部重点实验室，北京1008764)总参信息化部档案馆，北京100000 5)第二炮兵指挥学院通信系，武汉430012 ☒通信作者，E-mail:13811226834@139.com 摘要在流控传输协议(stream control transmission protocol,SCTP)中，多路径并行传输利用多家乡特性实现数据在关联的 多条端到端路径中的并行传输。然而，受不同路径性能差异的影响，多路径并行传输将带来接收端的数据乱序。为了减轻数 据乱序的程度并提高网络吞吐量性能，需要尽可能准确地估计每条路径的实时带宽与往返时间(round trip time,RTT).本文 利用扩展矢量卡尔曼滤波对多路径并行传输中每条路径的可用带宽与往返时间进行联合预测，同时提出了一种综合考虑发 送端未经接收端确认的数据的路径选择算法.仿真结果表明，通过实时准确地预测可用带宽和往返时间，路径选择算法能够 减轻接收端数据乱序的程度.对于带宽敏感的多路径应用场景而言，该算法的收敛速度比Kalman-CMT算法更快，对网络吞 吐量性能也有一定程度地提高：对时延和带宽都敏感的多路径应用场景来说，算法在收敛速度与吞吐量两方面优势明显 关键词网络协议：优化算法：性能优化：数据传输：带宽：往返时间：卡尔曼滤波 分类号TP393.4 CMT performance optimization algorithm based on union prediction of bandwidth and round trip time LI Wen',WANG Wen-bo,JING Xiao-jun,LIU Wen,ZHANG Chao 1)School of Information and Communication Engineering,Beijing University of Posts and Telecommunications,Beijing 100876,China 2)Institute of China Electronics System Engineering Company,Beijing 100000,China 3)Key Laboratory of Universal Wireless Communication(Ministry of Education),Beijing University of Posts and Telecommunications,Beijing 100876, China 4)The Archives of the Ministry of Information Technology,Beijing 100000,China 5)Department of Communication,The Second Artillery Command College,Wuhan 430012,China Corresponding author,E-mail:13811226834@139.com ABSTRACT Concurrent multipath transfer (CMT)uses the stream control transmission protocol's (SCTP)multihoming feature to distribute data across multiple end-to-end paths in a multihomed SCTP association.Due to the disparity of multipaths,it is facing a great challenge to solve the disorder of received data packets.In order to lighten the reordering degree and then to improve the through- put performance,we need to estimate the bandwidth and round trip time (RTT)of the real-time paths as exactly as possible.In this paper,we use the extended vector Kalman filter to predict the available bandwidth and RTT of each path simultaneously.Based on this,we propose a predictive path selection algorithm for CMT in SCTP.Simulation results show that the path selection algorithm can lessen the data packets disordering by correctly predicting each path's bandwidth and RTT in real time.To bandwidth sensitive scene, 收稿日期：2014-10-30 基金项目：解放军理工大学预先研究青年基金资助项目工程科学学报，第 37 卷，第 1 期: 132--143，2015 年 1 月 Chinese Journal of Engineering，Vol． 37，No． 1: 132--143，January 2015 DOI: 10． 13374 /j． issn2095--9389． 2015． 01． 020; http: / /journals． ustb． edu． cn 基于带宽与往返时间联合预测的多路径并行传输性 能优化算法 李 文1，2) ，王文博3) ，景晓军1) ，刘 文4) ，张 超5) 1) 北京邮电大学信息与通信工程学院，北京 100876 2) 中国电子系统设备工程公司研究所，北京 100000 3) 北京邮电大学泛网无线通信教育部重点实验室，北京 100876 4) 总参信息化部档案馆，北京 100000 5) 第二炮兵指挥学院通信系，武汉 430012  通信作者，E-mail: 13811226834@ 139． com 摘 要 在流控传输协议( stream control transmission protocol，SCTP) 中，多路径并行传输利用多家乡特性实现数据在关联的 多条端到端路径中的并行传输． 然而，受不同路径性能差异的影响，多路径并行传输将带来接收端的数据乱序． 为了减轻数 据乱序的程度并提高网络吞吐量性能，需要尽可能准确地估计每条路径的实时带宽与往返时间( round trip time，ＲTT) ． 本文 利用扩展矢量卡尔曼滤波对多路径并行传输中每条路径的可用带宽与往返时间进行联合预测，同时提出了一种综合考虑发 送端未经接收端确认的数据的路径选择算法． 仿真结果表明，通过实时准确地预测可用带宽和往返时间，路径选择算法能够 减轻接收端数据乱序的程度． 对于带宽敏感的多路径应用场景而言，该算法的收敛速度比 Kalman--CMT 算法更快，对网络吞 吐量性能也有一定程度地提高; 对时延和带宽都敏感的多路径应用场景来说，算法在收敛速度与吞吐量两方面优势明显． 关键词 网络协议; 优化算法; 性能优化; 数据传输; 带宽; 往返时间; 卡尔曼滤波 分类号 TP393. 4 CMT performance optimization algorithm based on union prediction of bandwidth and round trip time LI Wen1，2)  ，WANG Wen-bo3) ，JING Xiao-jun1) ，LIU Wen4) ，ZHANG Chao5) 1) School of Information and Communication Engineering，Beijing University of Posts and Telecommunications，Beijing 100876，China 2) Institute of China Electronics System Engineering Company，Beijing 100000，China 3) Key Laboratory of Universal Wireless Communication( Ministry of Education) ，Beijing University of Posts and Telecommunications，Beijing 100876， China 4) The Archives of the Ministry of Information Technology，Beijing 100000，China 5) Department of Communication，The Second Artillery Command College，Wuhan 430012，China  Corresponding author，E-mail: 13811226834@ 139． com 收稿日期: 2014--10--30 基金项目: 解放军理工大学预先研究青年基金资助项目 ABSTＲACT Concurrent multipath transfer ( CMT) uses the stream control transmission protocol’s ( SCTP) multihoming feature to distribute data across multiple end-to-end paths in a multihomed SCTP association． Due to the disparity of multipaths，it is facing a great challenge to solve the disorder of received data packets． In order to lighten the reordering degree and then to improve the through￾put performance，we need to estimate the bandwidth and round trip time ( ＲTT) of the real-time paths as exactly as possible． In this paper，we use the extended vector Kalman filter to predict the available bandwidth and ＲTT of each path simultaneously． Based on this，we propose a predictive path selection algorithm for CMT in SCTP． Simulation results show that the path selection algorithm can lessen the data packets disordering by correctly predicting each path’s bandwidth and ＲTT in real time． To bandwidth sensitive scene