计算机科学 ›› 2020, Vol. 47 ›› Issue (9): 246-251.doi: 10.11896/jsjkx.190800008

• 计算机网络 • 上一篇    下一篇

面向5G通信网络的NFV内存资源管理方法

苏畅, 张定权, 谢显中, 谭娅   

  1. 重庆邮电大学重庆市计算机网络与通信技术重点实验室 重庆400065
  • 收稿日期:2019-08-02 发布日期:2020-09-10
  • 通讯作者: 谢显中(xiexzh@cqupt.edu.cn)
  • 作者简介:changsu@cqupt.edu.cn
  • 基金资助:
    重庆市教委科学技术研究重点项目(KJZD-K201800603)

NFV Memory Resource Management in 5G Communication Network

SU Chang, ZHANG Ding-quan, XIE Xian-zhong, TAN Ya   

  1. Chongqing Key Laboratory of Computer Network and Communication Technology,Chongqing University of Posts and
    Telecommunications,Chongqing 400000,China
  • Received:2019-08-02 Published:2020-09-10
  • About author:SU Chang,born in 1979,Ph.D,professor,is a member of China Computer Federation (CCF).Her main research interests include QoS prediction,resource management,recommendation and prediction in location-based social network.
    XIE Xian-zhong,born in 1966,Ph.D,professor.His main research interests include cognitive radio network,interference cancellation and MIMO techno-logy,green communication network.
  • Supported by:
    Scientific and Technological Research Program of Chongqing Municipal Education Commission (KJZD-K201800603).

摘要: 随着5G研究的深入和商用的推进,出现了各式各样的挑战,其中,5G通信系统的资源管理对于5G网络的研究来说是一个关键性的挑战。网络功能虚拟化技术为5G的实现提供了关键支撑,同时也为5G的资源管理问题引入了新的研究方向,但是网络功能虚拟化场景中的资源管理是一个比较复杂问题。特别地,虚拟网络功能的不同放置位置会为其性能带来不同的影响。文中首先对网络功能虚拟化的资源分配方法及放置对性能的影响进行了分析和研究,在此基础上,主要根据知识定义网络所提出的范例,探讨了将机器学习技术应用于虚拟网络功能内存资源管理的研究,构建神经网络学习模型,预测内存资源消耗。其次,重点对输入流量的特征进行提取,流量主要由一组特征表示,这些特征代表了从数据链路层到传输层的小批次信息,其中的内存消耗是从虚拟机管理程序的性能监测工具上得出的批量的平均内存消耗。最后,利用神经网络模型预测内存资源消耗,从而达到对内存资源进行管理的目的。

关键词: 5G通信网络, 资源管理, 网络功能虚拟化, 机器学习, 内存消耗

Abstract: ith the deepening of 5G research and the advancement of commercialization,it also brings various challenges.Among them,the resource management of 5G communication system is a key challenge for the research of 5G network.Network Function Virtualization (NFV) technology provides key support for 5G implementation,and it also introduces new research directions for 5G resource management issues.However,resource management in network function virtualization scenarios is a more complex issue.In particular,different placements of virtual network functions have different effects on their performance.Firstly,this paper analyzed and studied the impact of NFV resource allocation methods and NFV placement on performance.On this basis,this paper mainly discussed machine learning based on the example proposed by Knowledge Definition Network (KDN).The technology is applied to the study of virtual network function memory resource management,constructing a neural network learning model,and predicting memory resource consumption.Secondly,the focus of this paper is on the extraction of the characteristics of the input traffic.The traffic is mainly represented by a set of features,which represent small batches of information from the data link layer to the transport layer,where the memory consumption is from the hypervisor.The average memory consumption of the batch is obtained on the performance monitoring tool.Finally,this paper aimed to manage memory resources by using neural networks to predict memory resource consumption.

Key words: 5G Communication network, Resource management, Network function virtualization, Machine learning, Memory consumption

中图分类号: 

  • TP183
[1] NGMN A.5G White Paper[OL].NGMN Industry Conferenceand Exhibition.https://www.ngmn.org/work-programme/5g-white-paper.html.
[2] GARNER J,MESTRES A,ALARCON E,et al.Machine learning-based network modeling:An artificial neural network model vs a theoretical inspired model[C]//Ninth International Conference on Ubiquitous & Future Networks.IEEE,2017:522-524.
[3] LIOTOU E,ELSHAER H,SCHATZ R,et al.Shaping QoE in the 5G ecosystem[C]//7th International Workshop on Quality of Multimedia Experience (IEEE QoMEX).IEEE,2015:1-6.
[4] ZHANG X X,WU C,LI Z P,et al.Proactive VNF Provisioning with Multi-timescale Cloud Resources:Fusing Online Learning and Online Optimization[C]//IEEE Conference on Computer Communications.IEEE,2017.
[5] AKYILDIZ I F,NIE S,LIN S C,et al.5G Roadmap:10 Key Enabling Technologies[J].Computer Networks,2016,106:17-48.
[6] MESTRES A,HIBBETT M J,ESTRADA G,et al.Knowledge-Defined Networking[J].ACM SIGCOMM Computer Communication Review,2017,47(3):2-10.
[7] NGUYEN T M,FDIDA S,PHAM T M.A comprehensive resource management and placement for network function virtualization[C]//Network Softwarization.IEEE,2017:1-9.
[8] MOENS H,TURCK F D.VNF-P:A model for efficient placement of virtualized network functions[C]//2014 10th International Conference on Network and Service Management (CNSM).IEEE Computer Society,2014:418-423.
[9] COHEN R,LEWIN-EYTAN L,NAOR J S,et al.Near optimal placement of virtual network functions[C]//IEEE Conference on Computer Communications.IEEE,2015:1346-1354.
[10] MENG X,PAPPAS V,ZHANG L.Improving the Scalability of Data Center Networks with Traffic-aware Virtual Machine Placement[C]//2010 Proceedings IEEE on INFOCOM.IEEE,2010:1154-1162.
[11] MAO H,ALIZADEH M,ISHAIMENACHE,et al.ResourceManagement with Deep Reinforcement Learning[C]//15th ACM Workshop.ACM,2016:50-56.
[12] GHAZNAVI M,KHAN A,SHAHRIAR N,et al.Elastic virtual network function placement[C]//IEEE International Conference on Cloud Networking.IEEE,2015:255-260.
[13] KULKARNI S G,ZHANG W,HWANG J H,et al.NFVnice:Dynamic Backpressure and Scheduling for NFV Service Chains[C]//the Conference of the ACM Special Interest Group.ACM,2015:71-84.
[14] SUBRAMANYA T,RIGGIO R,RASHEED T.Intent-basedmobile backhauling for 5G networks[C]//International Conference on Network & Service Management.IEEE,2017:348-352.
[15] TSUZAKI Y,OKABE Y.Reactive configuration updating forIntent-Based Networking[C]//2017 International Conference on Information Networking (ICOIN).IEEE,2017:97-102.
[16] HYUN J,HONG J.Knowledge-defined networking using in-band network telemetry[C]//Asia-Pacific Network Operations and Management Symposium (APNOMS).2017:54-57.
[17] RUELAS A M R,ROTHENBERG C E.A Load BalancingMethod based on Artificial Neural Networks for Knowledge-defined Data Center Networking[C]//ACM Press the 10th Latin America Networking Conference.ACM,2018:106-109.
[18] RIOS L M,SAHINIDIS N V.Derivative-free optimization:a review of algorithms and comparison of software implementations[J].Journal of Global Optimization,2013,56(3):1247-1293.
[19] NAWI N M,KHAN A,REHMAN M Z.A New LevenbergMarquardt based Back Propagation Algorithm Trained with Cuckoo Search[J].Procedia Technology,2013,11:18-23.
[20] CHO K,MITSUYA K,KATO A.Traffic data repository at the WIDE Project[C]//Project Usenix Freenix Track.2000:263-270.
[1] 李吟, 李必信. 基于脚本预测和重组的内存泄漏测试加速技术[J]. 计算机科学, 2020, 47(9): 31-39.
[2] 丁钰, 魏浩, 潘志松, 刘鑫. 网络表示学习算法综述[J]. 计算机科学, 2020, 47(9): 52-59.
[3] 王慧, 乐孜纯, 龚轩, 武玉坤, 左浩. 基于特征分类的链路预测方法综述[J]. 计算机科学, 2020, 47(8): 302-312.
[4] 袁野, 和晓歌, 朱定坤, 王富利, 谢浩然, 汪俊, 魏明强, 郭延文. 视觉图像显著性检测综述[J]. 计算机科学, 2020, 47(7): 84-91.
[5] 彭伟, 胡宁, 胡璟璟. 图像隐写分析算法研究概述[J]. 计算机科学, 2020, 47(6A): 325-331.
[6] 黄梅根, 汪涛, 刘亮, 庞瑞琴, 杜欢. 基于软件定义网络资源优化的虚拟网络功能部署策略[J]. 计算机科学, 2020, 47(6A): 404-408.
[7] 包振山, 郭俊南, 谢源, 张文博. 基于LSTM-GA的股票价格涨跌预测模型[J]. 计算机科学, 2020, 47(6A): 467-473.
[8] 徐江峰谭玉龙. 基于机器学习的HBase配置参数优化研究[J]. 计算机科学, 2020, 47(6A): 474-479.
[9] 金小敏, 滑文强. 移动云计算中面向能耗优化的资源管理[J]. 计算机科学, 2020, 47(6): 247-251.
[10] 朱林立, 华钢, 高炜. 决定图框架下本体学习算法的稳定性分析[J]. 计算机科学, 2020, 47(5): 43-50.
[11] 蹇松雷, 卢凯. 复杂异构数据的表征学习综述[J]. 计算机科学, 2020, 47(2): 1-9.
[12] 刘苗苗,扈庆翠,郭景峰,陈晶. 符号网络链接预测算法研究综述[J]. 计算机科学, 2020, 47(2): 21-30.
[13] 刘云,尹传环,胡迪,赵田,梁宇. 基于循环神经网络的通信卫星故障检测[J]. 计算机科学, 2020, 47(2): 227-232.
[14] 杨立, 马佳佳, 江华禧, 马肖肖, 梁赓, 左春. 面向机器学习系统的需求建模与决策选择[J]. 计算机科学, 2020, 47(12): 42-49.
[15] 王莹, 郑丽伟, 张禹尧, 张晓妘. 面向中文APP用户评论数据的软件需求挖掘方法[J]. 计算机科学, 2020, 47(12): 56-64.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 伍建辉,黄中祥,李武,吴健辉,彭鑫,张生. 城市道路建设时序决策的鲁棒优化[J]. 计算机科学, 2018, 45(4): 89 -93 .
[2] 耿海军,施新刚,王之梁,尹霞,尹少平. 基于有向无环图的互联网域内节能路由算法[J]. 计算机科学, 2018, 45(4): 112 -116 .
[3] 庞博,金乾坤,合尼古力·吾买尔,齐兴斌. 软件定义网络中基于网络切片和ILP模型的路由方案[J]. 计算机科学, 2018, 45(4): 143 -147 .
[4] 夏庆勋,庄毅. 一种基于局部性原理的远程验证机制[J]. 计算机科学, 2018, 45(4): 148 -151 .
[5] 吴姝,周安民,左政. PDiOS:iOS应用程序中私有API的调用检测[J]. 计算机科学, 2018, 45(4): 163 -168 .
[6] 罗霄阳,霍宏涛,王梦思,陈亚飞. 基于多残差马尔科夫模型的图像拼接检测[J]. 计算机科学, 2018, 45(4): 173 -177 .
[7] 朱淑芹,王文宏,李俊青. 针对基于感知器模型的混沌图像加密算法的选择明文攻击[J]. 计算机科学, 2018, 45(4): 178 -181 .
[8] 翁理国,孔维斌,夏旻,仇学飞. 基于深度极限学习机的卫星云图云量计算[J]. 计算机科学, 2018, 45(4): 227 -232 .
[9] 丁舒阳,黎冰,侍洪波. 基于改进的离散PSO算法的FJSP的研究[J]. 计算机科学, 2018, 45(4): 233 -239 .
[10] 侯彦娥,孔云峰,党兰学. 求解多车型校车路径问题的混合集合划分的GRASP算法[J]. 计算机科学, 2018, 45(4): 240 -246 .