计算机科学 ›› 2020, Vol. 47 ›› Issue (4): 262-269.doi: 10.11896/jsjkx.190300111

• 计算机网络 • 上一篇    下一篇

空间信息网络任务智能识别方法

杨力1,2, 李欣宇1,2, 石怀峰1,2,3, 潘成胜1   

  1. 1 大连大学通信与网络实验室 辽宁 大连116622;
    2 大连大学信息工程学院 辽宁 大连116622;
    3 南京理工大学自动化学院 南京 210094
  • 收稿日期:2019-03-22 出版日期:2020-04-15 发布日期:2020-04-15
  • 通讯作者: 石怀峰(shihuaifeng314@126.com)
  • 基金资助:
    自然科学基金项目(61722105,61801073);装备预研领域基金项目(6140449050116JW61001)

Task Intelligent Identification Method for Spatial Information Network

YANG Li1,2, LI Xin-yu1,2, SHI Huai-feng1,2,3, PAN Cheng-sheng1   

  1. 1 Communication and Network Lab,Dalian University,Dalian,Liaoning 116622,China;
    2 College of Information Engineering,Dalian University,Dalian,Liaoning 116622,China;
    3 Automated Institute,Nanjing University of Science and Technology,Nanjing 210094,China
  • Received:2019-03-22 Online:2020-04-15 Published:2020-04-15
  • Contact: SHI Huai-feng,born in 1989,master,lecturer,is a member of China Compu-ter Federation (CCF).His main researchinterests include space-ground integra-ted network technology and heterogeneous link aggregation methods in wireless networks.
  • About author:YANG Li,born in 1982,Ph.D,professor,is member of China Computer Fe-deration(CCF).Her main research intere-sts include spatial information network transmission technology and wireless communication network protocol theory and methods.
  • Supported by:
    This work was supported by the National Natural Science Foundation of China (61722105,61801073) and Equipment Pre-research Foundation(6140449050116JW61001)

摘要: 随着星间链路技术的不断发展和星上处理技术的日益成熟,空间信息网络传输的任务类型不断增加并呈现多样化的趋势,这对空间信息网络的多业务协同传输、网络资源全局调度等能力提出了新的挑战。然而,传统的空间信息网络资源调度大多以单一业务为驱动,忽略了任务与业务之间一对多的关系,导致某些低优先级任务抢占高优先级任务的网络资源,致使由多业务构成的空间信息网络任务的服务质量较低。此外,空间信息网络传输环境具有拓扑高动态变化、节点资源有限等特点,将传统的业务识别方法直接迁移到任务识别中存在任务识别效率低和开销大的缺陷。鉴于此,文中设计了部署于空间信息网络边缘的任务服务支持站,该支持站由识别标记模块、路由控制模块和数据通信模块组成,用以完成对任务类型的识别,以及基于任务服务质量需求的路由选择和数据传输。文中通过对流自身特征项的降维处理和基于高斯核函数的特征空间映射,设计了基于支持向量机的业务识别算法,进一步地,在引入网络传输环境相关特征项的基础上,将业务类型、业务数量和环境特征项相结合,设计了基于梯度下降法的任务识别算法。仿真结果表明,设计的任务识别算法具有很好的识别精准率和召回率,且消耗较短的识别时间和较少的识别开销,对空间信息网络任务流量识别的平均准确率达到95%以上,提高了1%以上,相比未经过特征降维的平均训练时间缩短了15%以上。

关键词: 空间信息网络, 任务识别, 特征降维, 梯度下降法, 支持向量机

Abstract: With the continuous development of inter-satellite link technology and the maturity of on-board processing technology,the types of tasks transmitted by spatial information networks are growing and diversifying.It presents a new challenge to the multi-service coordinated transmission of spatial information networks and the global scheduling of network resources.However,traditional spatial information network resource scheduling is mostly driven by a single service,ignoring the one-to-many relationship between tasks and services.This causes some low-priority tasks to preempt network resources of high-priority tasks,resulting in lower quality of service for spatial information network tasks composed of multiple services.In addition,the spatial information network transmission environment has the characteristics of high dynamic topology change and limited node resources.The traditional task identification method cannot identify the spatial information network task with high efficiency and low cost.Therefore,this paper designed a task service support station and deployed it at the edge of the spatial information network.The support station is composed of an recognition tag module,a route control module and a data communication module,which completes the task type identification and routing and data transmission based on the task quality of service requirements.On this basis,the existing identification methods only identify the single sub-service of the task,ignoring the one-to-many relationship between the task and the service,and can not meet the service quality requirement of the task.By introducing the feature space mapping based on Gaussian kernel function,the service recognition algorithm based on support vector machine was designed.Further,based on the introduction of environmental feature items,the business type,quantity and environmental feature items were combined to design a task identification algorithm based on gradient descent method.The simulation results show that the proposed task identification algorithm has good recognition accuracy and recall rate,and has less recognition time and recognition overhead.The average accuracy of task information recognition for spatial information network reaches 95%,which is increased by 1%.The average training time for feature dimension reduction is reduced by 15%.

Key words: Feature dimension reduction, Gradient descent method, Spatial information network, Support vector machines, Task identification

中图分类号: 

  • TP391
[1]MOORE A W,PAPAGIANNAKI K.Toward the Accurate Identification of Network Applications[C]//Passive and Active Network Measurement,6th International Workshop(PAM 2005).Boston,USA:2005(1):41-54.
[2]KARAGIANNIS T,PAPAGIANNAKI K,FALOUTSO M,et al.BLINC:multilevel traffic classification in the dark[C]//Proceedings of the Special Interest Group on Data Communication Conference(SIGCOMM).Philadelphia(USA),2005:221-227.
[3]XIONG G,MENG J,CAO Z G,et al.Progress and Prospects of Network Traffic Classification Research[J].Integrated techno-logy,2012,1(1):32-42.
[4]PAN W B,CHENG G,GUO X J,et al.Survey and Prospect of Network Encrypted Traffic Identification Research[J].Journal of Communications,2016,37(9):154-167.
[5]ZUEV D.Traffic classification using a statistical approach[C]//International Conference on Passive & Active Network Mea-surement.Springer-Verlag,2005.3431:321-324.
[6]GEORGE H J,PAT L.Estimating Continuous Distributions in Bayesian Classifiers[C]//UAI’95 Proceedings of the Eleventh conference on Uncertainty in artificial intelligence,2013.11:338-345.
[7]MCGREGOR A,HALL M,LORIER P,et al.Flow clustering using machine learning techniques[C]//Antibes Juan-les-Pins(France).PAM2004,2004:32-37.
[8]MA Y L,QIAN Z Y,TAO G C,et al.Machine Learning forNetwork Traffic Identification[J].Journal of Beijing University of Posts and Telecommunications,2009,32(1):65-68.
[9]DING R,LI W.A hybrid method for service identification ofSSL/TLS encrypted traffic[C]//IEEE International Conference on Computer & Communications.IEEE,2017:250-253.
[10]ZHANG L C.Research and Implementation of Satellite Network Routing Protocol[D].Xi’an:Xidian University of Electronic Technology,2017.
[11]MIN S Q.Further Discussion on the Conception of Integrated Information Network of Space and Earth Integration in China[C]//Proceedings of the 12th Annual Conference on Satellite Communications.2016:12-30.
[12]GU C J,ZHANG S Y,SUN Y F.Qos Adaptive Control Technology for Cognitive Network Based on Service Perception[J].ZTE Technology,2011,17(1):49-52.
[13]NIKOUEI S Y,CHEN Y,SONG S,et al.Smart Surveillance as an Edge Network Service:from Harr-Cascade,SVM to a Lightweight CNN[J].2018 IEEE 4th International Conference on Collaboration and Internet Computing,2018:256-265.
[14]UCS Satellite database[DB].2018.Https://www.ucsusa.org/nuclear-weapons/space-weapons/satellite-database.
[15]HAMIDZADEH J,MOSLEMNEJAD S.Identification of uncertainty and decision boundary for SVM classification training using belief function[J].Applied Intelligence,2018.5:2030-2045.
[16]ZHANG H R,HAN Z Z,LI C G.Support Vector Machines[J].Computer Science,2002,29(12):135-137.
[17]LI D R,SHEN X,GONG J Y,et al.On Construction of China’s Space Information Network[J].Geomatics and Information Science of Wuhan Univers,2015,40(6):711-715.
[18]ZHU H.P2P Traffic Identification Based on Machine Learning[D].Beijing:Journal of Beijing University of Posts and Telecommunications,2010.
[19]NETRAPALLI P,NIRANJAN U N,SANGHAVI S,et al.Non-convex Robust PCA[J].Computer Science,2014,10:1107-1115.
[20]LIN H M.Analysis of Ten Problems in the Application of Principal Component Analysis[J].Statistics and Decision,2007,16(7):16-18.
[21]LI H.Statistical Learning Method [M].Beijing:Tsinghua University Press,2012:195-124.
[22]ZHU H L.Research on Traffic Awareness Technology for Service Awareness[D].Beijing:Journal of Beijing University of Posts and Telecommunications,2010.
[1] 单晓英, 任迎春.
基于改进麻雀搜索优化支持向量机的渔船捕捞方式识别
Fishing Type Identification of Marine Fishing Vessels Based on Support Vector Machine Optimized by Improved Sparrow Search Algorithm
计算机科学, 2022, 49(6A): 211-216. https://doi.org/10.11896/jsjkx.220300216
[2] 陈景年.
一种适于多分类问题的支持向量机加速方法
Acceleration of SVM for Multi-class Classification
计算机科学, 2022, 49(6A): 297-300. https://doi.org/10.11896/jsjkx.210400149
[3] 侯夏晔, 陈海燕, 张兵, 袁立罡, 贾亦真.
一种基于支持向量机的主动度量学习算法
Active Metric Learning Based on Support Vector Machines
计算机科学, 2022, 49(6A): 113-118. https://doi.org/10.11896/jsjkx.210500034
[4] 邢云冰, 龙广玉, 胡春雨, 忽丽莎.
基于SVM的类别增量人体活动识别方法
Human Activity Recognition Method Based on Class Increment SVM
计算机科学, 2022, 49(5): 78-83. https://doi.org/10.11896/jsjkx.210400024
[5] 武玉坤, 李伟, 倪敏雅, 许志骋.
单类支持向量机融合深度自编码器的异常检测模型
Anomaly Detection Model Based on One-class Support Vector Machine Fused Deep Auto-encoder
计算机科学, 2022, 49(3): 144-151. https://doi.org/10.11896/jsjkx.210100142
[6] 侯春萍, 赵春月, 王致芃.
基于自反馈最优子类挖掘的视频异常检测算法
Video Abnormal Event Detection Algorithm Based on Self-feedback Optimal Subclass Mining
计算机科学, 2021, 48(7): 199-205. https://doi.org/10.11896/jsjkx.200800146
[7] 胡艳梅, 杨波, 多滨.
基于网络结构的正则化逻辑回归
Logistic Regression with Regularization Based on Network Structure
计算机科学, 2021, 48(7): 281-291. https://doi.org/10.11896/jsjkx.201100106
[8] 郭福民, 张华, 胡瑢华, 宋岩.
一种基于表面肌电信号的腕部肌力估计方法研究
Study on Method for Estimating Wrist Muscle Force Based on Surface EMG Signals
计算机科学, 2021, 48(6A): 317-320. https://doi.org/10.11896/jsjkx.200600021
[9] 卓雅倩, 欧博.
噪声环境下的人脸防伪识别算法研究
Face Anti-spoofing Algorithm for Noisy Environment
计算机科学, 2021, 48(6A): 443-447. https://doi.org/10.11896/jsjkx.200900207
[10] 雷剑梅, 曾令秋, 牟洁, 陈立东, 王淙, 柴勇.
基于整车EMC标准测试和机器学习的反向诊断方法
Reverse Diagnostic Method Based on Vehicle EMC Standard Test and Machine Learning
计算机科学, 2021, 48(6): 190-195. https://doi.org/10.11896/jsjkx.200700204
[11] 王友卫, 朱晨, 朱建明, 李洋, 凤丽洲, 刘江淳.
基于用户兴趣词典和LSTM的个性化情感分类方法
User Interest Dictionary and LSTM Based Method for Personalized Emotion Classification
计算机科学, 2021, 48(11A): 251-257. https://doi.org/10.11896/jsjkx.201200202
[12] 曹素娥, 杨泽民.
基于聚类分析算法和优化支持向量机的无线网络流量预测
Prediction of Wireless Network Traffic Based on Clustering Analysis and Optimized Support Vector Machine
计算机科学, 2020, 47(8): 319-322. https://doi.org/10.11896/jsjkx.190800075
[13] 徐翔燕, 侯瑞环.
基于GM(1,1)-SVM组合模型的中长期人口预测研究
Medium and Long-term Population Prediction Based on GM(1,1)-SVM Combination Model
计算机科学, 2020, 47(6A): 485-487. https://doi.org/10.11896/JsJkx.190900168
[14] 马创, 吕孝飞, 梁炎明.
基于GA-SVM的农产品质量分类
Agricultural Product Quality Classification Based on GA-SVM
计算机科学, 2020, 47(6A): 517-520. https://doi.org/10.11896/JsJkx.190900184
[15] 宋岩, 胡瑢华, 郭福民, 袁新亮, 熊睿洋.
基于sEMG的改进SVM+BP肌力预测分层算法
Improved SVM+BP Algorithm for Muscle Force Prediction Based on sEMG
计算机科学, 2020, 47(6A): 75-78. https://doi.org/10.11896/JsJkx.190900143
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!