Research on Greedy Backup Method of Service Function Chain Based on Genetic Algorithm

YANG Xue; CHEN Zhuo

doi:10.11907/rjdk.251100

您当前的位置：

首页 >

文章列表页 >

Research on Greedy Backup Method of Service Function Chain Based on Genetic Algorithm

Computer Software and Theory | 更新时间：2026-04-30

- Research on Greedy Backup Method of Service Function Chain Based on Genetic Algorithm
- Software Guide Vol. 25, Issue 4, Pages: 140-147(2026)
- 作者机构：
  
  重庆理工大学计算机科学与工程学院，重庆 400054
- 作者简介：
- 基金信息：
- DOI：10.11907/rjdk.251100
  CLC： TP393
- Received：11 March 2025，
  
  Published：15 April 2026
- 稿件说明：
移动端阅览
杨雪,陈卓.基于遗传算法的服务功能链贪心备份方法研究[J].软件导刊,2026,25(04):140-147.

YANG Xue,CHEN Zhuo.Research on Greedy Backup Method of Service Function Chain Based on Genetic Algorithm[J].Software Guide,2026,25(04):140-147.
杨雪,陈卓.基于遗传算法的服务功能链贪心备份方法研究[J].软件导刊,2026,25(04):140-147. DOI： 10.11907/rjdk.251100.

YANG Xue,CHEN Zhuo.Research on Greedy Backup Method of Service Function Chain Based on Genetic Algorithm[J].Software Guide,2026,25(04):140-147. DOI： 10.11907/rjdk.251100.

摘要

在网络功能虚拟化（NFV）环境中，虚拟网络功能及其基础设施的故障可能会严重损害服务功能链的可用性，并影响整体网络性能，成为NFV架构中的核心挑战之一。为了应对这一难题，提出一种基于遗传算法的服务功能链贪心备份方法。首先，提出一种基于生成对抗网络（GAN）的边缘节点故障预测模型，以预测节点的健康状况；其次，优先选择能够显著提升系统可用性的VNF作为备份对象，从而减少所需的备份VNF数量；最后，利用遗传算法的迭代优化，为需要备份的VNF部署最优的节点和链路，提出一种确保服务功能链高可用性的备份方法。仿真结果表明，相比KSP方法，该方案将资源消耗降低32%，服务链请求接受率提升11%，平均备份比例稳定维持在0.5。该方法通过“预测—筛选—优化”的闭环机制，显著提升了动态网络环境下服务链的鲁棒性与资源利用效率。

Abstract

In network function virtualization （NFV） environments， failures of virtual network functions （VNFs） and their infrastructure can severely compromise the availability of service function chains （SFCs） and degrade overall network performance， posing a critical challenge in NFV architectures. To address this issue， this paper proposes a genetic algorithm-based greedy backup method for SFCs. First， a Generative Adversarial Network （GAN）-enabled edge node fault prediction model is developed to assess node health status， thereby avoiding the use of high-risk nodes for backup. Second， a greedy strategy prioritizes VNF instances that maximize system availability improvements while minimizing resource consumption， ensuring efficient backup selection. Third， leveraging iterative optimization via genetic algorithms， the method optimally deploys backup VNFs across nodes and links to guarantee SFC high availability. Simulation results demonstrate that， compared to the K-Shortest Path （KSP） method， the proposed approach reduces resource consumption by 32%， increases SFC request acceptance rates by 11%， and maintains an average backup ratio of 0.5. By integrating a closed-loop "prediction-sifting-optimization" mechanism， this method significantly enhances SFC robustness and resource utilization efficiency in dynamic network environments.

关键词

Keywords

references

WANG J W ， ZHANG X L ， LI Q ， et al . Research progress on network function virtualization technology ［J］. Journal of Computer Science ， 2019 ， 42 （ 2 ）： 185 - 206 . doi: 10.11897/SP.J.1016.2019.00415 http://dx.doi.org/10.11897/SP.J.1016.2019.00415

王进文，张晓丽，李琦，等 . 网络功能虚拟化技术研究进展［J］. 计算机学报， 2019 ， 42 （ 2 ）： 185 - 206 . doi: 10.11897/SP.J.1016.2019.00415 http://dx.doi.org/10.11897/SP.J.1016.2019.00415

WANG P . Research on key technologies application of core network in fifth generation mobile communication ［J］. Electronic Communication and Computer Science ， 2023 ， 5 （ 9 ）： 125 - 127 .

王鹏 . 第五代移动通信中核心网关键技术应用研究［J］. 电子通信与计算机科学， 2023 ， 5 （ 9 ）： 125 - 127 .

GOU J G ， LYU G F ， SUN Z G ， et al . Overview of network function virtualization technology ［J］. Computer Engineering and Science ， 2019 ， 41 （ 2 ）： 260 - 267 .

苟建国，吕高锋，孙志刚，等 . 网络功能虚拟化技术综述［J］. 计算机工程与科学， 2019 ， 41 （ 2 ）： 260 - 267 .

DOE J ， SMITH J . A survey on virtual network functions reliability in nfv： challenges， solutions， and research directions ［J］. Journal of Network and Computer Applications ， 2022 ， 40 （ 3 ）： 221 - 235 .

LIU Y ， SHANG X ， MAO Y ， et al . Availability aware online virtual network function backup in edge environments ［J］. IEEE Transactions on Mobile Computing ， 2023 ， 23 （ 5 ）： 3909 - 3922 . doi: 10.1109/tmc.2023.3282156 http://dx.doi.org/10.1109/tmc.2023.3282156

ZHANG J ， WU W ， LUI J C S . On the theory of function placement and chaining for network function virtualization ［C］// Proceedings of the Eighteenth ACM International Symposium on Mobile Ad Hoc Networking and Computing ， 2018 ： 91 - 100 . doi: 10.1145/3209582.3209592 http://dx.doi.org/10.1145/3209582.3209592

LIU Y ， SHANG X ， YANG Y . Joint SFC deployment and resource management in heterogeneous edge for latency minimization ［J］. IEEE Transactions on Parallel and Distributed Systems ， 2021 ， 32 （ 8 ）： 2131 - 2143 . doi: 10.1109/tpds.2021.3062341 http://dx.doi.org/10.1109/tpds.2021.3062341

WANG C ， HU Q ， YU D ， et al . Proactive deployment of chain-based VNF backup at the edge using online bandit learning ［C］// 2021 IEEE 41st International Conference on Distributed Computing Systems （ICDCS）， 2021 ： 740 - 750 . doi: 10.1109/icdcs51616.2021.00076 http://dx.doi.org/10.1109/icdcs51616.2021.00076

WANG C ， HU Q ， YU D ， et al . Online learning for failure-aware edge backup of service function chains with the minimum latency ［J］. IEEE/ACM Transactions on Networking ， 2023 ， 31 （ 6 ）： 2730 - 2744 . doi: 10.1109/tnet.2023.3265127 http://dx.doi.org/10.1109/tnet.2023.3265127

LI J ， GUO D ， XIE J ， et al . Availability-aware provision of service function chains in mobile edge computing ［J］. ACM Transactions on Sensor Networks ， 2023 ， 19 （ 3 ）： 1 - 28 . doi: 10.1145/3565483 http://dx.doi.org/10.1145/3565483

LU S ， LUO B ， PATEL T ， et al . Making disk failure predictions SMARTer！［C］// 18th USENIX Conference on File and Storage Technologies ， 2020 ： 151 - 168 .

WEN M S ， LI J Q ， HAI T X ， et al . Failure prediction based VNF migration mechanism for multimedia services in power grid substation monitoring ［C］// 2022 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting （BMSB）， 2022 ： 1 - 6 . doi: 10.1109/bmsb55706.2022.9828707 http://dx.doi.org/10.1109/bmsb55706.2022.9828707

GUAN Y ， LIU Y ， ZHOU K ， et al . A disk failure prediction model for multiple issues ［J］. Frontiers of Information Technology & Electronic Engineering ， 2023 ， 24 （ 7 ）： 964 - 979 . doi: 10.1631/fitee.2200488 http://dx.doi.org/10.1631/fitee.2200488

GOODFELLOW I ， POUGET-ABADIE J ， MIRZA M ， et al . Generative adversarial nets ［C］// Proceedings of the 28th International Conference on Neural Information Processing Systems ， 2014 ： 2672 - 2680 . doi: 10.3156/JSOFT.29.5_177_2 http://dx.doi.org/10.3156/JSOFT.29.5_177_2

KLEIN A . What SMART hard disk errors actually tell Us ［EB/OL］. https：//www.backblaze.com/blog/what-smart-stats-indicate-hard-drive-failures/ https://www.backblaze.com/blog/what-smart-stats-indicate-hard-drive-failures/

EL-SHIMI A . Predicting storage failures ［C］// VAULT-Linux Storage and File Systems Conference ， 2017 ： 16 - 22 .

GE J K ， QIU Y H ， WU C M ， et al . A review of genetic algorithm research ［J］. Application Research of Computers ， 2008 ， 25 （ 10 ）： 2911 - 2916 . doi: 10.3969/j.issn.1001-3695.2008.10.008 http://dx.doi.org/10.3969/j.issn.1001-3695.2008.10.008

葛继科，邱玉辉，吴春明，等 . 遗传算法研究综述［J］. 计算机应用研究， 2008 ， 25 （ 10 ）： 2911 - 2916 . doi: 10.3969/j.issn.1001-3695.2008.10.008 http://dx.doi.org/10.3969/j.issn.1001-3695.2008.10.008

HOY A ， RAUSAND M . System reliability theory： models and satistical methods ［M］. Hoboken ： Wiley ， 2004 .

FAN J ， JIANG M ， QIAO C . Carrier-grade availability-aware mapping of service function chains with on-site backups ［C］// 2017 IEEE/ACM 25th International Symposium on Quality of Service ， 2017 ： 1 - 10 . doi: 10.1109/iwqos.2017.7969152 http://dx.doi.org/10.1109/iwqos.2017.7969152

WANG M ， CHENG B ， ZHAO S ， et al . Availability-aware service chain composition and mapping in NFV-enabled networks ［C］// 2019 IEEE International Conference on Web Services ， 2019 ： 107 - 115 . doi: 10.1109/icws.2019.00028 http://dx.doi.org/10.1109/icws.2019.00028

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Failure Prediction of Eccentric Cutterhead of Quasi-rectangular Shields Based on Optimized BP Network

Three-dimensional Connect Four System Based on Alpha-Beta Pruning

Pricing and Replenishment Decision-Making for Vegetable Products Based on Optimization Models

Flight Cockpit Human-Machine Interface Layout Optimization Based on Improved Genetic Algorithm

Components and Parts Picking Cluster Model Based on Improved K-means Algorithm

Related Author

LIU Gao-hong

WU En-qi

MIN Rui

HOU Tian-fan

WANG Xiao-hui

CHEN Bingyang

LIU Xiaotong

CHEN Haotian

Related Institution

Mechanical Engineering Company， Shanghai Tunnel Engineering Co. Ltd.

School of Mechanical Engineering， University of Shanghai for Science and Technology

Beijing Advanced Innovation Center for Materials Genome Engineering， Beijing Information Science and Technology University

School of Computer， Beijing Information Science and Technology University

School of Software， Yunnan University

⁰