基于流量优化的可靠服务功能链部署方法

doi:10.12305/j.issn.1001-506X.2021.10.38

摘要/Abstract

摘要：

针对网络功能虚拟化环境中服务功能链部署的资源开销问题, 提出一种基于流量优化的可靠服务功能链部署方法。首先, 根据虚拟链路流量变化对虚拟网络功能进行聚合, 使带宽需求大的虚拟链路部署到底层网络后, 其流量变为服务器的内部流量。其次, 综合考虑可靠性、综合时延以及拓扑属性, 利用离差最大化的多指标决策算法对物理节点进行评价, 并使用链路约束降低流量的乒乓效应。最后, 采用k-最短路径算法将虚拟链路部署到满足带宽需求的物理链路上。仿真实验表明, 所提方法在保证服务功能链可靠性的基础上, 对长期收益开销比、映射成功率、端到端时延以及带宽开销有较大优化。

关键词: 网络功能虚拟化, 服务功能链部署, 资源开销, 乒乓效应, 拓扑与时延感知

Abstract:

Aiming at the problem of resource cost of service function chain deployment in network function virtualization environment, a reliable service function chain deployment method based on traffic optimization is proposed. Firstly, the virtual network function is aggregated according to the traffic change of virtual link. After the virtual link with high bandwidth demand is deployed to the underlying network, its traffic becomes the internal traffic of the server. Secondly, considering the reliability, delay and topology attributes comprehensively, the multi-index decision algorithm with maximum deviation is used to evaluate the physical nodes, and the distance constraint is used to reduce the ping-pong effect of traffic. Finally, k-shortest path algorithm is used to deploy the virtual link to the physical link that meets the bandwidth demand. Simulation experiments show that this method can optimize the long-term revenue overhead ratio, mapping success rate, end-to-end delay and bandwidth overhead on the basis of ensuring the reliability of service function chain.

Key words: network function virtualization, service function chain deployment, resource cost, ping pong effect, topology and delay awareness

中图分类号:

TP393

阳勇, 孟相如, 康巧燕, 赵文文. 基于流量优化的可靠服务功能链部署方法[J]. 系统工程与电子技术, 2021, 43(10): 3017-3025.

Yong YANG, Xiangru MENG, Qiaoyan KANG, Wenwen ZHAO. Reliable service function chain deployment method based on traffic optimization[J]. Systems Engineering and Electronics, 2021, 43(10): 3017-3025.

图/表 9

图1

图2

表1

图3

图4

图5

图6

图7

图8

参考文献 30

1	CHOWDHURY S R , ANTHONY B H , BAI T , et al. A disaggregated packet processing architecture for network function virtualization[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (6): 1075- 1088. doi: 10.1109/JSAC.2020.2986611
2	ZHENG J Q , TIAN C , DAI H P , et al. Optimizing NFV chain deployment in software-defined cellular core[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (2): 248- 262. doi: 10.1109/JSAC.2019.2959180
3	ALHUSSEIN O , ZHUANG W H . Robust online composition, routing and NF placement for NFV-enabled services[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (6): 1089- 1101. doi: 10.1109/JSAC.2020.2986612
4	LIN T C , ZHOU Z L . Robust network function virtualization[J]. Networks, 2020, 75 (4): 438- 462. doi: 10.1002/net.21935
5	BUYAKAR T V K, AGARWAL H, TAMMA B R, et al. Prototyping and load balancing the service based architecture of 5G core using NFV[C]//Proc. of the IEEE Conference on Network Softwarization, 2019: 228-232.
6	ERAMO V , MIUCCI E , AMMAR M , et al. An approach for ser-vice function chain routing and virtual function network instance migration in network function virtualization architectures[J]. IEEE/ACM Trans.on Networking, 2017, 25 (4): 2008- 2025. doi: 10.1109/TNET.2017.2668470
7	MANIAS D M , HAWILO H , JAMMAL M , et al. Depth-optimized delay-aware tree (DO-DAT) for virtual network function placement[J]. IEEE Networking Letters, 2020, 2 (3): 149- 153. doi: 10.1109/LNET.2020.2997320
8	OTOKURA M , LEIBNITZ K , KOIZUMI Y , et al. Evolvable virtual network function placement method: mechanism and performance evaluation[J]. IEEE Trans.on Network and Service Management, 2019, 16 (3): 27- 40.
9	QU L , ASSI C , KHABBAZ M J , et al. Reliability-aware service function chaining with function decomposition and multipath routing[J]. IEEE Trans.on Network and Service Management, 2020, 17 (2): 835- 848. doi: 10.1109/TNSM.2019.2961153
10	FARZAD T , MOHAMED F Z , BITA F , et al. CoDeC: a cost-effective and delay-aware SFC deployment[J]. IEEE Trans.on Network and Service Management, 2020, 17 (2): 793- 806. doi: 10.1109/TNSM.2019.2949753
11	FU X Y , YU R R , WANG J Y , et al. Performance optimization for blockchain-enabled distributed network function virtua-lization management and orchestration[J]. IEEE Trans.on Vehicular Technology, 2020, 69 (6): 6670- 6679. doi: 10.1109/TVT.2020.2985581
12	唐伦, 赵培培, 赵国繁, 等. 基于QoS保障的服务功能链动态部署算法[J]. 北京邮电大学学报, 2018, 41 (6): 90- 96.
	TANG L , ZHAO P P , ZHAO G F , et al. Dynamic deployment algorithm for service function chaining with QoS guarantee[J]. Journal of Beijing University of Posts and Telecommunications, 2018, 41 (6): 90- 96.
13	汤红波, 邱航, 游伟, 等. 基于联合备份的服务功能链可靠性保障的部署方法[J]. 电子与信息学报, 2019, 41 (12): 16- 24.
	TANG H B , QIU H , YOU W , et al. A reliability-guarantee method for service function chain deployment based on joint backup[J]. Journal of Electronics & Information Technology, 2019, 41 (12): 16- 24.
14	YUAN Q , TANG H B , YOU W , et al. Virtual network function scheduling via multilayer encoding genetic algorithm with distributed bandwidth allocation[J]. Science China Information Sciences, 2018, 61 (9): 92- 107.
15	邱航, 游伟, 汤红波, 等. 基于多路径的可靠性服务功能链部署方法[J]. 计算机工程, 2019, 45 (3): 101- 106, 112.
	QIU H , YOU W , TANG H B , et al. Deployment scheme of reliable service function chain based on multipath[J]. Computer Engineering, 2019, 45 (3): 101- 106, 112.
16	QU L , KHABBAZ M , ASSI C . Reliability-aware service chaining in carrier-grade softwarized networks[J]. IEEE Journal on Selected Areas in Communications, 2018, 36 (3): 558- 573. doi: 10.1109/JSAC.2018.2815338
17	陈卓, 冯钢, 刘怡静, 等. MEC中基于改进遗传模拟退火算法的虚拟网络功能部署策略[J]. 通信学报, 2020, 41 (4): 74- 84.
	CHEN Z , FENG G , LIU Y J , et al. Vitual network function deployment strategy based on improved genetics simulated annealing algorithm in MEC[J]. Journal on Communications, 2020, 41 (4): 74- 84.
18	HERKER S, AN X L, KIESS W, et al. Data-center architecture impacts on virtualized network functions service chain embedding with high availability requirements[C]//Proc. of the IEEE Globecom Workshops, 2015.
19	孙士清, 彭建华, 游伟, 等. 5G网络下资源感知的服务功能链协同构建和映射算法[J]. 西安交通大学报, 2020, 54 (8): 140- 148.
	SUN S Q , PENG J H , YOU W , et al. A resource-aware ser-vice function chain coordinated composition and mapping algorithm under 5G network[J]. Journal of Xi'an Jiaotong University, 2020, 54 (8): 140- 148.
20	RUIZ L , RAMÓN J , DURÁN B , et al. Genetic algorithm for holistic VNF-mapping and virtual topology design[J]. IEEE Access, 2020, 8, 55893- 55904. doi: 10.1109/ACCESS.2020.2982018
21	CARPIO F, DHAHRI S, JUKAN A. VNF placement with replication for load balancing in NFV networks[C]//Proc. of the IEEE International Conference on Communications, 2017.
22	SUN J , ZHU G Y , SUN G , et al. A reliability-aware approach for resource efficient virtual network function deployment[J]. IEEE Access, 2018, 5, 18238- 18250.
23	SOLOZABAL R , CEBERIO J , SANCHOYERTO A , et al. Virtual network function placement optimization with deep reinforcement learning[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (2): 292- 303. doi: 10.1109/JSAC.2019.2959183
24	PEI J N , HONG P L , XUE K P , et al. Two-phase virtual network function selection and chaining algorithm based on deep learning in SDN/NFV-enabled networks[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (6): 1102- 1117. doi: 10.1109/JSAC.2020.2986592
25	WEI D S L , XUE K , BRUSCHI R , et al. Guest editorial leveraging machine learning in SDN/NFV-based networks[J]. IEEE Journal on Selected Areas in Communications, 2020, 38 (2): 245- 247. doi: 10.1109/JSAC.2019.2959197
26	魏亮, 黄韬, 张娇, 等. 基于强化学习的服务链映射算法[J]. 通信学报, 2018, 39 (1): 90- 100.
	WEI L , HUANG T , ZHANG J , et al. Service chain mapping algorithmbased on reinforcement learning[J]. Journal on Communications, 2018, 39 (1): 90- 100.
27	MIJUMBI R , HASIJA S , DAVY S , et al. Topology-aware prediction of virtual network function resource requirements[J]. IEEE Trans.on Network and Service Management, 2017, 14 (1): 106- 120.
28	ZHAO D C , REN J , LIN R P , et al. On orchestrating service function chains in 5G mobile network[J]. IEEE Access, 2019, 7, 39402- 39416.
29	翟东, 孟相如, 康巧燕, 等. 面向时延与可靠性优化的服务功能链部署方法[J]. 电子与信息学报, 2020, 42 (10): 2386- 2393.
	ZHAI D , MENG X R , KANG Q Y , et al. Service function chain deployment method for delay and reliability optimization[J]. Journal of Electronics & Information Technology, 2020, 42 (10): 2386- 2393.
30	WANG Y Z, ZHU X R. A quick adaptive migration algorithm for virtual network function[C]//Proc. of the 10th EAI International Conference on Wireless and Satellite Systems, 2019: 333-347.

实验参数	参数值
节点计算资源	服从[70, 80]的均匀分布
节点存储资源	服从[70, 80]的均匀分布
节点转发资源	服从[70, 80]的均匀分布
节点产生时延	服从[2, 5]的均匀分布
节点可靠性	服从[0.95, 0.98]的均匀分布
链路带宽	服从[300, 500]的均匀分布
链路时延	服从[2, 5]的均匀分布
VNF计算资源需求	服从[10, 20]的均匀分布
VNF存储资源需求	服从[10, 20]的均匀分布
VNF转发资源需求	服从[10, 20]的均匀分布
VNF带宽改变因子	服从[0.7, 1.4]的均匀分布
初始带宽需求	服从[50, 60]的均匀分布
SFC中VNF个数	服从[3, 6]的均匀分布
SFC可靠性下限	服从[0.75, 0.8]的均匀分布
SFC端到端时延上限	服从[90, 100]的均匀分布