一种基于自适应KLMS的卫星网络流量预测算法

doi:10.13190/j.jbupt.2017-144

北京邮电大学学报 ›› 2018, Vol. 41 ›› Issue (3): 51-55.doi: 10.13190/j.jbupt.2017-144

一种基于自适应KLMS的卫星网络流量预测算法

赵季红^1,2, 王明欣¹, 曲桦², 谢志勇¹, 刘熙²

1. 西安邮电大学通信与信息工程学院, 西安 710121;
2. 西安交通大学电子与信息工程学院, 西安 710049

收稿日期:2017-07-17 出版日期:2018-06-28 发布日期:2018-06-04
作者简介:王明欣(1991-),男,硕士生,E-mail:wmx0513@163.com;赵季红(1963-),女,教授,博士生导师.
基金资助:
国家高技术研究发展计划（863计划）项目（2015AA015702）；国家自然科学基金项目（61531013，61371087）

An Adaptive KLMS Traffic Prediction Algorithm for Satellite Network

ZHAO Ji-hong^1,2, WANG Ming-xin¹, QU Hua², XIE Zhi-yong¹, LIU Xi²

1. School of Communications and Information Engineering, Xi'an University of Posts & Telecommunications, Xi'an 710121, China;
2. School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China

Received:2017-07-17 Online:2018-06-28 Published:2018-06-04

摘要/Abstract

摘要： 针对传统预测模型已不再适用于卫星网络的问题，提出了一种自适应步长和自适应核宽度的核最小均方算法（AKLMS）.通过核函数将非线性数据从低维输入空间映射到高维特征空间进行操作，并且在迭代过程中根据瞬时误差自适应地调整步长和核宽度.仿真结果证明，与核最小均方算法（KLMS）和最小均方算法（LMS）相比，AKLMS算法在收敛速度和预测流量精度方面都有大幅提升，为卫星网络的流量规划和路由设计提供了强有力的决策支持.

关键词: 卫星网络, 核最小均方算法, 自适应步长, 自适应核宽度, 网络流量预测

Abstract: Due to the resource limitation and topology change in satellite network, the article puts forward higher requirements for the accuracy and efficiency of the network traffic prediction algorithm, and the traditional prediction model is no longer suitable for the satellite network. The author presents a kernel least mean square algorithm (KLMS) with adaptive step length and adaptive kernel width, namely AKLMS, which maps the nonlinear data from low dimensional input space to high dimensional feature space through kernel function, and the algorithm will adaptively adjust the step length and kernel width based on the instantaneous error in the iterative process. Simulations show that the AKLMS algorithm has great improvement on the convergence speed and prediction accuracy of the flow compared with the KLMS and least mean square (LMS), which will provide strong decision support for traffic planning and routing design in satellite network.

Key words: satellite network, kernel least mean square, adaptive step length, adaptive kernel width, network traffic prediction

中图分类号:

TN927

赵季红, 王明欣, 曲桦, 谢志勇, 刘熙. 一种基于自适应KLMS的卫星网络流量预测算法[J]. 北京邮电大学学报, 2018, 41(3): 51-55.

ZHAO Ji-hong, WANG Ming-xin, QU Hua, XIE Zhi-yong, LIU Xi. An Adaptive KLMS Traffic Prediction Algorithm for Satellite Network[J]. JOURNAL OF BEIJING UNIVERSITY OF POSTS AND TELECOM, 2018, 41(3): 51-55.

参考文献

[1] Gamvros I, Raghavan S. Multi-period traffic routing in satellite networks[J]. European Journal of Operational Research, 2012, 219(3):738-750.
[2] Gao Zihe, Guo Qing, Na Zhenyu. A distributed routing algorithm with traffic prediction in LEO satellite networks[J]. Information Technology Journal, 2011, 10(2):285-292.
[3] Yan Dong, Wang Luyuan. TPDR:traffic prediction based dynamic routing for LEO&GEO satellite networks[C]//International Conference on Electronics Information and Emergency Communication. Beijing:IEEE, 2015:104-107.
[4] Qu Hua, Ma Wentao, Zhao Jihong, et al. Prediction method for network traffic based on maximum correntropy criterion[J]. China Communications, 2013, 10(1):134-145.
[5] Ma Wentao, Qu Hua, Zhao Jihong. Estimator with forgetting factor of correntropy and recursive algorithm for traffic network prediction[C]//2013 25^th Chinese on Control and Decision Conference (CCDC). Guiyang:IEEE, 2013:490-494.
[6] 秦红祥, 杨飞. 一种新的卫星通信网流量预测算法[J]. 电讯技术, 2013, 53(7):835-839. Qin Hongxiang, Yang Fei. A new traffic flow prediction algorithm for satellite network[J]. Telecommunication Engineering, 2013, 53(7):835-839.
[7] 杜巍. 卫星互联网自相似业务预测方法的研究[D]. 哈尔滨:哈尔滨工业大学, 2014.
[8] Liu Weifei, Pokharel P P, Principe J C. The kernel least-mean-square algorithm[J]. IEEE Transactions on Signal Processing, 2008, 56(2):543-554.
[9] Zhao Jihong, Wang Tao, Ma Wentao, et al. The kernel-LMS based network traffic prediction[C]//IET International Conference on Information Science and Control Engineering. Shenzhen:IET, 2012:62-66.
[10] Liu Xi, Qu Hua, Zhao Jihong, et al. Maximum correntropy unscented Kalman filter for spacecraft relative state estimation[J]. Sensors, 2016, 16(9):1530.
[11] Chen Badong, Xing Lei, Zhao Haiquan, et al. Generalized correntropy for robust adaptive filtering[J]. IEEE Transactions on Signal Processing, 2016, 64(13):3376-3387.
[12] Liu Xi, Qu Hua, Zhao Jihong, et al. State space maximum correntropy filter[J]. Signal Processing, 2017(130):152-158.
[13] Wang Weihua, Zhao Jihong, Qu Hua, et al. Convergence performance analysis of an adaptive kernel width MCC algorithm[J]. AEU-International Journal of Electronics and Communications, 2017(76):71-76.
[14] 覃景繁, 欧阳景正. 一种新的变步长LMS自适应滤波算法[J]. 数据采集与处理, 1997(3):171-174. Qin Jingfan, Ouyang Jingzheng. A novel variable step size LMS adaptive filtering algorithm based on sigmoid function[J]. Journal of Data Acquisition & Processing, 1997(3):171-174.
[15] 150 Megabit Ethernet anonymized packet traces without payload:WIDE-TRANSIT link[DB/OL]. (2009-04-03)[2017-07-06]. http://mawi.wide.ad.jp/mawi/ditl/ditl2009/.

一种基于自适应KLMS的卫星网络流量预测算法

An Adaptive KLMS Traffic Prediction Algorithm for Satellite Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价

[1]	牟晓惠, 李丽香. Dropout回声状态网络的网络流量预测[J]. 北京邮电大学学报, 2021, 44(5): 10-13,20.
[2]	王璇, 侯蓉晖, 徐伟琳. 低轨卫星网络动态路径切换技术[J]. 北京邮电大学学报, 2020, 43(2): 80-86,109.
[3]	吴兆峰, 胡谷雨, 金凤林. 移动卫星网络中卫星切换调度研究[J]. 北京邮电大学学报, 2015, 38(s1): 37-40.
[4]	孙韩林，金跃辉，崔毅东，程时端. 粗粒度网络流量的灰色模型预测[J]. 北京邮电大学学报, 2010, 33(1): 7-11.