基于云边协同的可靠服务功能链部署算法

doi:10.19678/j.issn.1000-3428.0069052

摘要/Abstract

摘要：

在应对车联网(IoV)系统中请求类型多样化及数据海量化挑战时, 软件定义网络(SDN)和网络功能虚拟化(NFV)技术支持的云边协同架构已成为服务功能链(SFC)部署的有效手段。然而, IoV中无处不在的电磁干扰使组成SFC的虚拟网络功能(VNF)极易受损, 且以软件形式存在的VNF本身存在一定故障概率, 这使SFC部署过程的可靠性受到了威胁。为了在最小化成本前提下实现云边协同架构中车载请求的可靠部署, 构建一个基于SDN/NFV的可靠云边协同车载计算架构, 采用集中式训练-分布式推断方式训练部署模型。设计基于可靠成本效益比的可靠性增强算法SFC-RA, 通过创建与VNF具有相同功能的备份虚拟网络功能(BVNF)增强SFC的可靠性。提出一种基于策略梯度(PG)算法的在线SFC可靠部署算法PG_RA, 采用序列到序列模型作为学习代理, 以保障在满足资源约束的前提下能够提供满足用户需求的高可靠低成本服务。仿真结果表明, 相对于其他冗余方式和部署算法, SFC-RA算法能够降低2.78~6.33个单位的冗余成本, PG_RA算法能够平均提高12.88个百分点的可靠性水平及降低约6.7%的平均时延。

关键词: 车联网, 云边协同, 可靠性, 服务功能链, 深度强化学习, 网络功能虚拟化

Abstract:

In response to the challenges of diverse requests and massive data in the Internet of Vehicle (IoV), the edge-cloud collaboration architecture supported by Software Defined Networking (SDN) and Network Function Virtualization (NFV) technologies has emerged as an effective solution to the Service Function Chain (SFC) deployment problem. However, ubiquitous electromagnetic interference renders the Virtual Network Functions (VNFs) that comprise the SFC highly vulnerable within the IoV. As VNFs are software-based, they are susceptible to failure, which compromises the reliability of the SFC deployment process. To ensure reliable deployment of vehicle requests at minimal cost, a reliable edge-cloud collaboration vehicle-computing architecture is built based on SDN/NFV, which trains deployment models using centralized training and distributed inference. Furthermore, the SFC reliability enhancement algorithm SFC-RA is designed to enhance SFC reliability by introducing a Backup Virtual Network Function (BVNF) that mirrors the functionality of the original VNF. Finally, an online SFC reliable deployment algorithm PG_RA is proposed based on the Policy Gradient (PG) approach, and a sequence-to-sequence model is employed as an agent to provide highly reliable and cost-efficient services while adhering to resource constraints. Simulation results demonstrate that, compared to other redundancy methods and deployment algorithms, the SFC-RA algorithm reduces the redundancy cost by 2.78 to 6.33 units, and the PG_RA algorithm enhances reliability by an average of 12.88 percentage points, and decreases average latency by approximately 6.7%.

Key words: Internet of Vehicle (IoV), edge-cloud collaboration, reliability, Service Function Chain (SFC), Deep Reinforcement Learning (DRL), Network Function Virtualization (NFV)

宋艳蕊, 庄雷, 徐泽汐, 冯旭, 莫文帅. 基于云边协同的可靠服务功能链部署算法[J]. 计算机工程, 2024, 50(12): 184-193.

SONG Yanrui, ZHUANG Lei, XU Zexi, FENG Xu, MO Wenshuai. Reliable Service Function Chain Deployment Algorithm Based on Edge-Cloud Collaboration[J]. Computer Engineering, 2024, 50(12): 184-193.

https://www.ecice06.com/CN/Y2024/V50/I12/184

图/表 9

图1 基于SDN/NFV的可靠云边协同车载计算架构

Fig.1 Reliable edge-cloud collaboration vehicle computing architecture based on SDN/NFV

图2 云边协同架构下SFC可靠部署问题描述

Fig.2 SFC reliable deployment problem description under edge-cloud collaboration architecture

图3 基于PG_RA算法的SFC可靠部署模型

Fig.3 SFC reliable deployment model based on PG_RA algorithm

图4 不同学习率下收敛过程对比

Fig.4 Comparison of convergence process with different learning rates

图5 不同冗余算法BVNF成本对比

Fig.5 Comparison of BVNF cost of different redundancy algorithms

图6 不同算法请求接受率对比

Fig.6 Comparison of request acceptance rates of different algorithms

图7 不同算法平均时延对比

Fig.7 Comparison of average delay of different algorithms

参考文献 26

1	ZHUANG W H, YE Q, LYU F, et al. SDN/NFV-empowered future IoV with enhanced communication, computing, and caching. Proceedings of the IEEE, 2020, 108(2): 274- 291. doi: 10.1109/JPROC.2019.2951169
2	江恺, 曹越, 周欢, 等. 车联网边缘智能: 概念、架构、问题、实施和展望. 物联网学报, 2023, 7(1): 37- 48.
	JIANG K, CAO Y, ZHOU H, et al. Edge intelligence empowered Internet of Vehicles: concept, framework, issues, implementation, and prospect. Chinese Journal on Internet of Things, 2023, 7(1): 37- 48.
3	于晶, 鲁凌云, 李翔. 车联网中基于DDQN的边云协作任务卸载机制. 计算机工程, 2022, 48(12): 156- 164. doi: 10.19678/j.issn.1000-3428.0063739
	YU J, LU L Y, LI X. Edge-cloud collaborative task offloading mechanism based on DDQN in vehicular networks. Computer Engineering, 2022, 48(12): 156- 164. doi: 10.19678/j.issn.1000-3428.0063739
4	CAO B, SUN Z H, ZHANG J T, et al. Resource allocation in 5G IoV architecture based on SDN and fog-cloud computing. IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6): 3832- 3840. doi: 10.1109/TITS.2020.3048844
5	LI J L, SHI W S, WU H Q, et al. Cost-aware dynamic SFC mapping and scheduling in SDN/NFV-enabled space-air-ground-integrated networks for Internet of vehicles. IEEE Internet of Things Journal, 2022, 9(8): 5824- 5838. doi: 10.1109/JIOT.2021.3058250
6	QIU Y, LIANG J B, LEUNG V C M, et al. Online reliability-enhanced virtual network services provisioning in fault-prone mobile edge cloud. IEEE Transactions on Wireless Communications, 2022, 21(9): 7299- 7313. doi: 10.1109/TWC.2022.3157606
7	GUO J X, DING X J, WU W L. Reliable traffic monitoring mechanisms based on blockchain in vehicular networks. IEEE Transactions on Reliability, 2022, 71(3): 1219- 1229. doi: 10.1109/TR.2020.3046556
8	LI B, DENG X H, DENG Y Q. Mobile-edge computing-based delay minimization controller placement in SDN-IoV. Computer Networks, 2021, 193, 108049. doi: 10.1016/j.comnet.2021.108049
9	LI B, DENG X H, CHEN X C, et al. MEC-based dynamic controller placement in SD-IoV: a deep reinforcement learning approach. IEEE Transactions on Vehicular Technology, 2022, 71(9): 10044- 10058. doi: 10.1109/TVT.2022.3182048
10	LIU Y C, LU H, LI X, et al. Dynamic service function chain orchestration for NFV/MEC-enabled IoT networks: a deep reinforcement learning approach. IEEE Internet of Things Journal, 2021, 8(9): 7450- 7465. doi: 10.1109/JIOT.2020.3038793
11	ZHANG Q X, LIU F M, ZENG C B. Online adaptive interference-aware VNF deployment and migration for 5G network slice. IEEE/ACM Transactions on Networking, 2021, 29(5): 2115- 2128. doi: 10.1109/TNET.2021.3080197
12	TRUONG-HUU T, MURALI MOHAN P, GURUSAMY M. Service chain embedding for diversified 5G slices with virtual network function sharing. IEEE Communications Letters, 2019, 23(5): 826- 829. doi: 10.1109/LCOMM.2019.2900888
13	FAN J Y, YE Z L, GUAN C W, et al. GREP: guaranteeing reliability with enhanced protection in NFV[EB/OL]. [2023-11-17]. https://www.semanticscholar.org/paper/GREP%3A-Guaranteeing-Reliability-with-Enhanced-in-NFV-Fan-Ye/e38ca7fd3f6eb70e384780378de935554d7847a4.
14	HUANG M T, LIANG W F, SHEN X J, et al. Reliability-aware virtualized network function services provisioning in mobile edge computing. IEEE Transactions on Mobile Computing, 2020, 19(11): 2699- 2713. doi: 10.1109/TMC.2019.2927214
15	LIANG W F, MA Y, XU W Z, et al. Request reliability augmentation with service function chain requirements in mobile edge computing. IEEE Transactions on Mobile Computing, 2022, 21(12): 4541- 4554. doi: 10.1109/TMC.2021.3081681
16	THIRUVASAGAM P K, CHAKRABORTY A, MATHEW A, et al. Reliable placement of service function chains and virtual monitoring functions with minimal cost in softwarized 5G networks. IEEE Transactions on Network and Service Management, 2021, 18(2): 1491- 1507. doi: 10.1109/TNSM.2021.3056917
17	YANG L, JIA J Z, LIN H C, et al. Reliable dynamic service chain scheduling in 5G networks. IEEE Transactions on Mobile Computing, 2023, 22(8): 4898- 4911. doi: 10.1109/TMC.2022.3157312
18	HAZARIKA B, SINGH K, BISWAS S, et al. DRL-based resource allocation for computation offloading in IoV networks. IEEE Transactions on Industrial Informatics, 2022, 18(11): 8027- 8038. doi: 10.1109/TII.2022.3168292
19	LI G L, ZHOU H C, FENG B H, et al. Efficient provision of service function chains in overlay networks using reinforcement learning. IEEE Transactions on Cloud Computing, 2022, 10(1): 383- 395. doi: 10.1109/TCC.2019.2961093
20	BAI H N, ZHANG Y, ZHANG Z Y, et al. Latency equalization policy of end-to-end network slicing based on reinforcement learning. IEEE Transactions on Network and Service Management, 2023, 20(1): 88- 103. doi: 10.1109/TNSM.2022.3210012
21	LI B J, LU W, ZHU Z Q. Deep-NFVOrch: leveraging deep reinforcement learning to achieve adaptive VNF service chaining in DCI-EONs. Journal of Optical Communications and Networking, 2020, 12(1): 18- 27. doi: 10.1364/JOCN.12.000A18
22	SUTSKEVER I, VINYALS O, LE Q V. Sequence to sequence learning with neural networks. Advances in Neural Information Processing Systems, 2014, 4, 3104- 3112.
23	CHIEN W C, WENG H Y, LAI C F, et al. A SFC-based access point switching mechanism for software-defined wireless network in IoV. Future Generation Computer Systems, 2019, 98, 577- 585. doi: 10.1016/j.future.2019.01.030
24	徐泽汐, 庄雷, 张坤丽, 等. 基于知识图谱的服务功能链在线部署算法. 通信学报, 2022, 43(8): 41- 51.
	XU Z X, ZHUANG L, ZHANG K L, et al. Online placement algorithm of service function chain based on knowledge graph. Journal on Communications, 2022, 43(8): 41- 51.
25	BÉKÉSI J, DÓSA G, GALAMBOS G. A first fit type algorithm for the coupled task scheduling problem with unit execution time and two exact delays. European Journal of Operational Research, 2022, 297(3): 844- 852. doi: 10.1016/j.ejor.2021.06.002
26	MAGOULA L, BARMPOUNAKIS S, STAVRAKAKIS I, et al. A genetic algorithm approach for service function chain placement in 5G and beyond, virtualized edge networks. Computer Networks, 2021, 195, 108157. doi: 10.1016/j.comnet.2021.108157

[1]	石琼, 段辉, 师智斌. 基于深度强化学习的可信任务卸载方案[J]. 计算机工程, 2024, 50(8): 142-152.
[2]	张冀, 龚雯雯, 朵春红, 齐国梁. 面向多智能体与双层卸载的车联网卸载算法[J]. 计算机工程, 2024, 50(8): 182-197.
[3]	杨小东, 李沐紫, 马国祖, 李松谕, 王彩芬. 车联网中支持非法签名定位的无证书匿名认证方案[J]. 计算机工程, 2024, 50(6): 157-165.
[4]	孙文洁, 李宗民, 孙浩淼. 基于图神经网络的多智能体强化学习值函数分解方法[J]. 计算机工程, 2024, 50(5): 62-70.
[5]	傅明建, 郭福强. 基于深度强化学习的无信号灯路口决策研究[J]. 计算机工程, 2024, 50(5): 91-99.
[6]	关明晓, 刘嘉堃, 张鸿锐, 何安平. 基于FPGA误差可控的浮点运算加速器研究[J]. 计算机工程, 2024, 50(5): 291-297.
[7]	杜海军, 余粟. 基于时空图注意力网络的服务机器人动态避障[J]. 计算机工程, 2024, 50(2): 105-112.
[8]	倪苏婕, 陈兵, 石优. 一种联合V2I和V2V的任务卸载优化方案[J]. 计算机工程, 2024, 50(12): 174-183.
[9]	何杰, 马强. 基于深度强化学习的C-V2X任务卸载研究[J]. 计算机工程, 2024, 50(12): 200-212.
[10]	江敏, 陈飞, 程航, 王美清. 基于逐像素强化学习的边缘保持图像复原[J]. 计算机工程, 2024, 50(12): 224-232.
[11]	毕千, 钱程, 张可, 王成. 基于深度强化学习的多智能体角度跟踪方法设计[J]. 计算机工程, 2024, 50(11): 10-17.
[12]	王腾, 黄俊松, 王乐庭, 张才坤, 李枭扬. 基于MADDPG的多阵面相控阵雷达引导搜索资源优化算法[J]. 计算机工程, 2024, 50(11): 38-48.
[13]	郭瑞, 胡国梁, 王俊茗. 车联网中可匿名的无证书聚合签名方案[J]. 计算机工程, 2024, 50(11): 207-222.
[14]	邢丹丹, 曹素珍, 赵晓, 周大伟, 王正. 车联网环境下多接收者匿名签密方案[J]. 计算机工程, 2024, 50(10): 205-215.
[15]	蔡梓越, 谭北海, 余荣, 黄旭民, 王思明. 面向6G物联网设备协同的区块链动态分片[J]. 计算机工程, 2024, 50(1): 50-59.

选择文件类型/文献管理软件名称

选择包含的内容