基于流量演化感知的服务功能链在线弹性编排策略

doi:10.3969/j.issn.0372-2112.2019.10.023

电子学报 ›› 2019, Vol. 47 ›› Issue (10): 2192-2201.DOI: 10.3969/j.issn.0372-2112.2019.10.023

基于流量演化感知的服务功能链在线弹性编排策略

谷允捷, 胡宇翔, 丁悦航, 谢记超

国家数字交换系统工程技术研究中心, 河南郑州 450002

收稿日期:2018-12-04 修回日期:2019-03-13 出版日期:2019-10-25
- 通讯作者:
- 谷允捷
- 作者简介:
- 胡宇翔 男,1982生,河南周口人.国家数字交换系统工程技术研究中心副研究员、博士生导师,研究方向为新型网络体系结构与核心技术;丁悦航 女,1995年生,山东济南人.国家数字交换系统工程技术研究中心硕士研究生,研究方向为知识图谱;谢记超 男,1993年生,河北石家庄人.国家数字交换系统工程技术研究中心硕士研究生,研究方向为网络安全与虚拟化技术.
- 基金资助:
- 国家自然科学基金 (No.61521003，No.61872382）; 国家重点研发计划课题 (No.2017YFB0803204）

Online Elastic Orchestration Policy of Service Function Chain Based on Flow Evolution Perception

GU Yun-jie, HU Yu-xiang, DING Yue-hang, XIE Ji-chao

National Digital Switching System Engineering and Technological R & D Center, Zhengzhou, Henan 450002, China

Received:2018-12-04 Revised:2019-03-13 Online:2019-10-25 Published:2019-10-25
- Corresponding author:
- GU Yun-jie
- Supported by:
- National Natural Science Foundation of China (No.61521003, No.61872382); National Key Research and Development Program of China (No.2017YFB0803204)

摘要/Abstract

摘要： 随着网络功能虚拟化（NFV）的引入，运营商能够提供更为灵活的网络服务.然而现有服务功能链（SFC）编排局限于静态反应式策略，业务流量发生变化时网络资源供应量难以匹配负载需求，虚拟网络功能（VNF）频繁部署与迁移，运营开销增大.针对上述问题，该文提出一种基于流量演化感知的服务功能链在线弹性编排策略（OEOP），该策略将在线学习引入到SFC流量演化感知的过程，预先确定细粒度的VNF弹性需求.此外，以实时更新的SFC路径与节点负载两因子为导向，完成新增VNF的在线弹性部署，代替VNF迁移应对系统负载变化.仿真表明，该策略明显增强了虚拟资源供应量与负载需求的匹配特性，VNF吞吐量利用率提高10.2%~24.8%，运营开销平均降低26.7%.

关键词: 网络功能虚拟化, 虚拟网络功能, 运营开销, 流量演化感知, 在线凸优化

Abstract: With the introduction of network function virtualization (NFV), operators can provide more flexible network service. However, most existing orchestration schemes of service function chain (SFC) are limited to the static or reactive policy where the virtual network functions (VNFs) need to be deployed or migrated frequently, and will easily lead to the mismatch of service supplement and high operational expenditure under time-varying workload. This paper proposes an online elastic orchestration policy (OEOP) based on the evolution perception of flow rate to solve the above mentioned problem. OEOP introduces online learning into the evolution perception of flow rate, which helps to predetermine the fine-grained VNF scaling demands. In addition, the online elastic deployment is achieved according to the real-time update information of SFC paths and the load of nodes. The newly deployed VNF instances can respond to the time-varying workload by taking place of the mission of VNF migration. The simulation results demonstrate that OEOP can significantly enhance the matching between virtual resource supply and workload demand. The throughput of VNF is improved by 10.2%~24.8%, and the operational expenditure can be reduced by 26.7% on average compared with other solutions.

Key words: network function virtualization, virtual network functions, operational expenditure, flow evolution perception, online convex optimization

中图分类号:

TP393.0

谷允捷, 胡宇翔, 丁悦航, 等. 基于流量演化感知的服务功能链在线弹性编排策略[J]. 电子学报, 2019, 47(10): 2192-2201.

GU Yun-jie, HU Yu-xiang, DING Yue-hang, et al. Online Elastic Orchestration Policy of Service Function Chain Based on Flow Evolution Perception[J]. Acta Electronica Sinica, 2019, 47(10): 2192-2201.

参考文献

[1] GEMBER-J A,VISWANATHAN R,PRAKASH C,et al.OpenNF:Enabling innovation in network function control[A].ACM Conference on Sigcomm[C].Chicago,Illinois:ACM,2014.163-174.
[2] QUINN.E.P,NADEAU.E.T,Problem Statement for Service Function Chaining[R].New York:IETF,RFC,2015.8-10.
[3] MOENS H,TURCK F D.VNF-P:A model for efficient placement of virtualized network functions[A].International Conference on Network & Service Management(CNSM)[C].Rio de Janeiro,Brazil:IEEE,2014.418-423.
[4] BARI F,CHOWDHURY S R,AHMED R,et al.Orchestrating virtualized network functions[J].IEEE Transactions on Network & Service Management,2016,13(4):725-739.
[5] JANG I,SUH D,PACK S,et al.Joint optimization of service function placement and flow distribution for service function chaining[J].IEEE Journal on Selected Areas in Communications,2017,35(11):2532-2541.
[6] GHAZNAVI M,SHAHRIAR N,KAMALI S,et al.Distributed service function chaining[J].IEEE Journal on Selected Areas in Communications,2017,35(11):2479-2489.
[7] COHEN R,LEWIN E.L,NAOR J S,et al.Near optimal placement of virtual network functions[A].IEEE Conference on Computer Communications (INFOCOM)[C].Hong Kong,China:IEEE,2015.1346-1354.
[8] WANG X,WU C,LE F,et al.Online VNF Scaling in Datacenters[A].IEEE International Conference on Cloud Computing[C].San Francisco,USA:IEEE,2016.140-147.
[9] ARTEAGA C H T,RISSOI F,RENDON OMC.An adaptive scaling mechanism for managing performance variations in network functions virtualization:Acase study in an NFV-based EPC[A].International Conference on Network and Service Management (CNSM)[C].Tokyo,Japan:IEEE,2017.1-7.
[10] ZHANG X,WU C,Li Z,et al.Proactive VNF provisioning with multi-timescale cloud resources:Fusing online learning and online optimization[A].IEEE Conference on Computer Communications(INFOCOM)[C].Atlanta,USA:IEEE,2017.1-9.
[11] FEI X,LIU F,XU H,et al.Adaptive VNF scaling and flow routing with proactive demand prediction[A]IEEE Conference on Computer Communications(INFOCOM)[C].Honolulu,USA:IEEE,2018.486-494.
[12] WANG M,MENG X,ZHANG L.Consolidating virtual machines with dynamic bandwidth demand in data centers[A].IEEE Conference on Computer Communications(INFOCOM)[C].Shanghai,China:IEEE,2011.71-75.
[13] Wen T,Yu H,Sun G,et al.Network function consolidation in service function chaining orchestration[A].IEEE International Conference on Communications (ICC)[C].Kuala Lumpur,Malaysia:IEEE,2016.1-6.
[14] MIJUMBI R,SERRAT J,GORRICHO J L,et al.Design and evaluation of algorithms for mapping and scheduling of virtual network functions[A].Proceedings of the First IEEE Conference on Network Softwarization[C].London,UK IEEE,2015.
[15] 陈卓,冯钢,刘蓓,等.运营商网络中面向时延优化的服务功能链迁移重配置策略[J].电子学报,2018,46(9):2229-2237. CHEN Z,FENG G,LIU B,et al.Delay optimization oriented service function chain migration and re-deployment in operator network[J].Acta Electronica Sinica,2018,46(9):2229-2237.(in Chinese)
[16] JIA Y,WU C,LI Z,et al.Online scaling of nfv service chains across geo-distributed datacenters[J].IEEE/ACM Transactions on Networking,2016,26(2):699-710.
[17] CHAPARADZA R,CIAVAGLIA L,WǚDCZAK M,et al.ETSI Industry Specification Group on Autonomic Network Engineering for the Self-managing Future Internet (ETSI ISG AFI)[M].Poznan Poland:Web Information Systems Engineering (WISE) 2009.622-638.
[18] ETSI GS,Network Functions Virtualisation (NFV),Pre-deployment Testing[R].London:ETSI,2012.15-22.
[19] MCMAHAN H B,Holt G,SCULLEY D,et al.Ad click prediction:a view from the trenches[A].International Conference on Knowledge Discovery and Data mining[C].Chicago,USA:ACM,2013.1222-1230.
[20] CHEN N,AGARWAL A,WIERMAN A,et al.Online convex optimization using predictions[J].ACM Sigmetrics Performance Evaluation Review,2015,43(1):191-204.
[21] SHALEV-SHWARTZ S.Online learning and online convex optimization[J].Foundations & Trends in Machine Learning,2012,4(2):107-194.
[22] MCMAHAN H B.A survey of algorithms and analysis for adaptive online learning[J].The Journal of Machine Learning Research,2017,18(1):3117-3166.
[23] KARLIN A R,MANASSE M S,MCGEOCH L A,et al.Competitive randomized algorithms for nonuniform problems[J].Algorithmica,1994,11(6):542-571.
[24] LIN M,WIERMAN A,ANDREW L L H,et al.Dynamic right-sizing for power-proportional data centers[J].IEEE/ACM Transactions on Networking (TON),2013,21(5):1378-1391.
[25] ZINK M,SUH K,GU Y,et al.Characteristics of YouTube network traffic at a campus network-measurements,models,and implications[J].Computer Networks,2009,53(4):501-514.

基于流量演化感知的服务功能链在线弹性编排策略

Online Elastic Orchestration Policy of Service Function Chain Based on Flow Evolution Perception

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

[1]	覃剑, 石昌伟, 张媛, 贾云健, 胡浩星. 边缘视频处理的细粒度划分与重组部署算法[J]. 电子学报, 2021, 49(11): 2152-2159.
[2]	陈卓, 冯钢, 刘蓓, 周杨. 运营商网络中面向时延优化的服务功能链迁移重配置策略[J]. 电子学报, 2018, 46(9): 2229-2237.
[3]	兰天翼, 郭云飞, 范宏伟, 兰巨龙. 基于可编程硬件的有状态网络功能硬件加速架构[J]. 电子学报, 2018, 46(7): 1609-1616.
[4]	兰天翼, 郭云飞, 兰巨龙, 段通. 基于可编程硬件的NFV数据包加速处理结构[J]. 电子学报, 2017, 45(12): 3076-3080.