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，车联网中无处不在的电磁干扰使组成SFC的虚拟网络功能（VNFs）极易受损，且以软件形式存在的VNFs本身存在一定故障概率，这使SFC部署过程的可靠性受到威胁。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，构建了一个基于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；设计了基于可靠成本效益比的可靠性增强算法SFC-RA，通过创建与VNFs具有相同功能的备份虚拟网络功能（BVNFs）增强SFC可靠性；提出了一种基于策略梯度算法的在线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，该算法能够降低5-7个单位冗余成本，平均提高13.9%的可靠性水平，降低平均时延7%左右。

Abstract: In the face of the challenges of diverse requests and massive data in the Internet of Vehicles (IoV), edge-cloud collaboration architecture supported by Software Defined Networking (SDN) and Network Function Virtualisation (NFV) technologies has become an effective method for the Service Function Chain (SFC) deployment problem. However, the ubiquitous electromagnetic interference makes the Virtual Network Functions (VNFs) that comprise the SFC extremely vulnerable in IoV, and the VNFs have a certain failure probability because they are software, which puts the reliability of the SFC deployment process at risk. In order to achieve reliable deployment of vehicle requests with minimum cost, a reliable edge-cloud collaboration vehicle computing architecture is built based on SDN/NFV, which trains deployment models by centralized training and distributed inference. Then, the SFC reliability enhancement algorithm SFC-RA was designed based on the reliable-cost-benefit ratio, and this algorithm enhances SFC reliability by creating Backup Virtual Network Functions (BVNFs) with the same functionality as VNFs. Finally, the online SFC reliable deployment algorithm PG-RA is proposed based on the policy gradient, and we adopt the sequence-to-sequence model as an agent to provide highly reliable and low-cost services that satisfy user requirements while meeting resource constraints. The simulation results show that, compared to other redundancy methods and deployment algorithms, this algorithm can reduce the redundancy cost by 5-7 units, increase the reliability level on average by 13.9%, and reduce the average latency by about 7%.

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, doi: 10.19678/j.issn.1000-3428.0069052.

Yanrui Song, Lei Zhuang, Zexi Xu, Xu Feng, Wenshuai Mo. Reliable Service Function Chain Deployment Algorithm Based on Edge-Cloud Collaboration[J]. Computer Engineering, doi: 10.19678/j.issn.1000-3428.0069052.

参考文献

[1] Zhuang W, Ye Q, Feng L, et al.SDNNFV-Empowered Future IoV With Enhanced Communication, Computing, and Caching[J].Proceedings of the IEEE, 2020, 108(2):274-291.
[2] 江恺; 曹越; 周欢; 任学锋; 朱永东; 林海.车联网边缘智能：概念、架构、问题、实施和展望[J].物联网学报, 2023, 7(01):37-48. Jiang K, Cao Y, Zhou H, et al.Edge intelligence empowered internet of vehicles: concept, framework, issues, implementation, and prospect[J].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[J].计算机工程, 2022, 48(12):156-164. Yu J, Lu L, Li X.Edge-Cloud Collaborative Task Offloading Mechanism Based on DDQN in Vehicular Networks[J].Computer Engineering, 2022,48(12):156- 164.
[4] Cao B, Sun Z, Zhang J, et al.Resource Allocation in 5G IoV Architecture Based on SDN and Fog-Cloud Computing[J].IEEE Transactions on Intelligent Transportation Systems, 2021, 22(6):3832-3840.
[5] Li J, Shi W, Wu H, et al.Cost-Aware Dynamic SFC Mapping and Scheduling in SDNNFV-Enabled Space-Air-Ground-Integrated Networks for Internet of Vehicles[J].IEEE Internet of Things Journal, 2022, 9(8):5824-5838.
[6] Qiu Y, Liang J, Leung V, et al.Online Reliability Enhanced Virtual Network Services Provisioning in Fault-Prone Mobile Edge Cloud[J].IEEE Transactions on Wireless Communications, 2022, 21(9):7299-7313.
[7] Guo J, Ding X, Wu W, et al.Reliable Traffic Monitoring Mechanisms Based on Blockchain in Vehicular Networks[J].IEEE Transactions on Reliability, 2021, 71(3):1-11.
[8] Li B, Deng X, Chen X, et al.Mobile-edge computing-based delay minimization controller placement in SDN-IoV[J].Computer Networks, 2021, 193(1):108049.
[9] Li B, Deng X, Chen X, et al.MEC-Based Dynamic Controller Placement in SD-IoV: A Deep Reinforcement Learning Approach[J].IEEE Transactions on Vehicular Technology, 2022, 71(9):1-15.
[10] Liu Y, Lu H, Li X, et al.Dynamic Service Function Chain Orchestration for NFVMEC-Enabled IoT Networks: A Deep Reinforcement Learning Approach[J].IEEE INTERNET OF THINGS JOURNAL, 2021, 8(9):7450-7465.
[11] Zhang Q, Liu F, Zeng C, et al.Online Adaptive Interference-Aware VNF Deployment and Migration for 5G Network Slice[J].IEEE ACM Transactions on Networking, 2021, 29(5):2115-2128.
[12] Tram T, Murali M, Gurusamy, M.Service Chain Embedding for Diversified 5G Slices With Virtual Network Function Sharing[J].IEEE Communications Letters, 2019, 23(5):826-829.
[13] Fan J, Ye Z, Guan C, et al. GREP: Guaranteeing reliability with enhanced protection in NFV[C]. Proceedings of the 2015 ACM SIGCOMM Workshop on Hot Topics in Middleboxes and Network Function Virtualization. London, 2015.
[14] Huang M, Liang W, Shen X, et al.Reliability Aware Virtualized Network Function Services Provisioning in Mobile Edge Computing[J].IEEE Transactions on Mobile Computing, 2020, 19(11):2699-2713.
[15] Liang W, Ma Y, Xu W, et al.Request Reliability Augmentation With Service Function Chain Requirements in Mobile Edge Computing[J].IEEE Transactions on Mobile Computing, 2022, 21(12):4541-4554.
[16] Prabhu K, Abhishek C, Abin M, et al.Reliable Placement of Service Function Chains and Virtual Monitoring Functions With Minimal Cost in Softwarized 5G Networks[J].IEEE Transactions on Network and Service Management, 2021, 18(2):1491-1507.
[17] Yang L, Jia J, Lin H, et al.Reliable Dynamic Service Chain Scheduling in 5G Networks[J].IEEE Transactions on Mobile Computing, 2023, 22(8):4898-4911.
[18] Hazarika B, Singh K, Biswas S, et al. DRL-Based Resource Allocation for Computation Offloading in IoV Networks[J]. IEEE Transactions on Industrial Informatics,2022,18(11):8027-8038.
[19] Li G, Zhou H, Feng B, et al.Efficient Provision of Service Function Chains in Overlay Networks using Reinforcement Learning[J].IEEE Transactions on Cloud Computing, 2022, 10(1):383-395.
[20] Bai H, Zhang Y, Zhang Z, et al.Latency Equalization Policy of End-to-End Network Slicing Based on Reinforcement Learning[J].IEEE Transactions on Network and Service Management, 2023, 20(1):88-103.
[21] Li B, Lu W, Zhu Z. Deep-NFVOrch: leveraging deep reinforcement learning to achieve adaptive VNF service chaining in DCI-EONs[J]. IEEE Transactions on Cloud Computing,2020,12(1):A18-A27.
[22] Sutskever I, Vinyals O, Le V Q. Sequence to Sequence Learning with Neural Networks[J]. Advances in neural information processing systems,2014.
[23] Chien W, Weng H, Lai C, et al.A SFC-based access point switching mechanism for Software-Defined Wireless Network in IoV[J].Future Generation Computer Systems, 2019, 98(0):577-585.
[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[J].通信学报, 2022, 43(08):41-51. Xu Z, Zhuang L, Zhang K, et al.An Online Placement Algorithm of Service Function Chain Based on Knowledge Graph[J]. Journal on Communications, 2022, 43(08):41-51.
[25] József B,György D,Gábor G. A first Fit type algorithm for the coupled task scheduling problem with unit execution time and two exact delays[J]. European Journal of Operational Research,2022,297(3):844-852.
[26] Lina M, Sokratis B, Ioannis S, et al.A genetic algorithm approach for service function chain placement in 5G and beyond, virtualized edge networks[J].Computer Networks, 2021, 195(9):108157.

选择文件类型/文献管理软件名称

选择包含的内容