广东工业大学学报

• •    下一篇

基于模糊图神经网络的工业互联网服务组件编排方法

刘岸鑫1, 程良伦1, 王涛2   

  1. 1. 广东工业大学 计算机学院, 广东 广州 510006;
    2. 广东工业大学 自动化学院, 广东 广州 510006
  • 收稿日期:2024-05-15 出版日期:2024-10-08 发布日期:2024-10-08
  • 通信作者: 程良伦(1964–)，男，教授，博士，主要研究方向为信息物理融合系统，E-mail：llcheng@gdut.edu.cn
  • 作者简介:刘岸鑫(1997–)，男，硕士研究生，主要研究方向为工业软件，E-mail：liuanxin10337@163.com
  • 基金资助:
    国家自然科学基金联合基金资助集成项目(U20A6003)

Fuzzy Graph Neural Network-based Industrial Internet Service Component Orchestration Method

Liu An-xin1, Cheng Liang-lun1, Wang Tao2   

  1. 1. School of Computer Science and Technology, Guangdong University of Technology, Guangzhou 510006, China;
    2. School of Automation, Guangdong University of Technology, Guangzhou 510006, China
  • Received:2024-05-15 Online:2024-10-08 Published:2024-10-08

HTML

PDF (PC)

86

摘要： 工业互联网环境工业软件系统具有规模庞大、涵盖的软件组件与设备实体繁杂异构等特点，在异构设备与软件对象统一的服务化组件化封装基础上，通过服务组件编排可实现多样化应用工业软件系统灵活敏捷构建，但对服务编排效率与服务质量保障方面具有较高要求。为提升工业互联网环境服务组件编排效率并保障服务质量，本文提出基于图神经网络与模糊理论的服务组件编排方法FGraphSAGE_GA，将工业互联网服务组件编排问题形式化建模为图结构中的链路预测问题，并采用监督学习方法实现预测模型训练。针对新的服务组件编排问题，训练后的模型进行概率预测缩小候选空间，随后使用遗传算法优化服务组件编排方案。在两个不同的数据集上，针对3种规模的服务组件编排问题开展实验与分析，证明了所提出的FGraphSAGE_GA算法在服务质量和编排效率方面具有良好性能。

关键词: 工业互联网, 服务组件编排, 图神经网络, 模糊系统, 遗传算法

Abstract: In industrial internet environments, industrial software systems are usually large-scale and with a complex and heterogeneous array of software systems and physical devices. Based on the unified service-oriented and component-based encapsulation of heterogeneous devices and software objects, diverse applications of industrial software systems can be flexibly constructed through the orchestration of service components. However, it usually requires high efficiency of service orchestration and the assurance of service quality. To enhance the efficiency of service component orchestration and ensure service quality in industrial internet environments, this paper proposes a service component orchestration method called FGraphSAGE_GA, which formalizes the convert the component orchestration problem in industrial internet environments into a link prediction problem within a graph structure. It employs a supervised learning approach to train the prediction model. For the new service component orchestration problem, the trained model performs probabilistic predictions to narrow down the candidate space, followed by the optimization of the service component orchestration plan using a genetic algorithm. Experiments were conducted on two different datasets for service component orchestration problems of three different scales, and experimental results show that the proposed FGraphSAGE_GA algorithm has good performance in terms of service quality and orchestration efficiency.

Key words: industrial internet, service component orchestration, graph neural network, fuzzy system, genetic algorithm

中图分类号: 

  • TP393
[1] GHOSH S, UGWUANYI E, DAGIUKLAS A, et al. BlueArch-an implementation of 5G testbed[J]. Journal of Communication, 2019, 14: 1110-1118 .
[2] MUñOZ R, NADAL L, CASELLAS R, et al. The ADRENALINE testbed: an SDN/NFV packet/optical transport network and edge/core cloud platform for end-to-end 5G and IoT services[C]//2017 European Conference on Networks and Communications (EuCNC). Oulu, Finland: IEEE, 2017: 1-5.
[3] SHEKHAR S, CHHOKRA A, SUN H, et al. Supporting fog/edge-based cognitive assistance IoT services for the visually impaired[C]//Proceedings of the International Conference on Internet of Things Design and Implementation. Montreal Quebec. Montreal: ACM, 2019: 275-276.
[4] KHANSARI M E, SHARIFIAN S, MOTAMEDI S A . Virtual sensor as a service: a new multicriteria QoS-aware cloud service composition for IoT applications[J]. The Journal of Supercomputing, 2018, 74(10): 5485-5512.
[5] WHITE G, PALADE A, SIOBHÁN CLARKE. QoS prediction for reliable service composition in IoT[C]//International Conference on Service-Oriented Computing. Hangzhou, China: Springer, 2018: 149-160.
[6] LI C, LI J, CHEN H, et al. Memetic harris hawks optimization: developments and perspectives on project scheduling and QoS-aware web service composition[J]. Expert Systems with Applications, 2021, 171: 114529.
[7] DAHAN F. An effective multi-agent ant colony optimization algorithm for QoS-aware cloud service composition[J]. IEEE Access, 2021, 9: 17196-17207.
[8] ETCHIALI A, HADJILA F, BEKKOUCHE A. An intelligent bat algorithm for web service selection with QoS uncertainty[J]. Big Data and Cognitive Computing, 2023, 7(3): 140.
[9] WANG H, ZHOU X, ZHOU X, et al. Adaptive service composition based on reinforce-ment learning[C]//International conference on service-oriented computing. Francisco, CA, USA: Springer, 2010: 92-107.
[10] WANG H, GU M, YU Q, et al. Large-scale and adaptive service composition using deep reinforcement learning[C]//International Conference on Service-Oriented Computing. Malaga, Spain: Springer, 2017: 383-391.
[11] ELSAYED D H, NASR E S, ALAA EL DIN M, et al. A new hybrid approach using genetic algorithm and Q-learning for QoS-aware web service composition[C]//International Conference on Advanced Intelligent Systems and Informatics. Cairo, Egypt: Springer, 2017: 537-554
[12] YI K, YANG J, WANG S, et al. PPDRL: a pretraining-and-policy-based deep reinforcement learning approach for QoS-aware service composition[J]. Security and Communication Networks, 2022, 2022: 8264423.
[13] WANG X, XU H, WANG X, et al. A graph neural network and pointer network-based approach for QoS-aware service composition[J]. IEEE Transactions on Services Computing, 2022, 16(3): 1589-1603
[14] WEI T, HOU J, FENG R. Fuzzy graph neural network for few-shot learning[C]//2020 International Joint Conference on Neural Networks (IJCNN) . Glasgow, UK: IEEE, 2020: 1-8.
[15] XU K, HU W, LESKOVEC J, et al. How powerful are graph neural networks?[J]. arXiv: 1810.00826(2019-02-22) [2024-05-01]. https://arxiv.org/pdf/1810.00826.
[16] 任笑. 基于图神经网络的服务组合方法的研究与实现[D]. 西安: 西安电子科技大学, 2022.
[17] GAVVALA S K, JATOTH C, GANGADHARAN G, et al. QoS-aware cloud service composition using eagle strategy[J]. Future Generation Computer Systems, 2019, 90: 273-290.
[1] 郑侠聪, 程良伦, 黄国恒, 王敬超. 嵌入拓扑特征的自然场景文本检测方法[J]. 广东工业大学学报, 2024, 41(03): 102-109.
[2] 胡晓敏, 许万森, 段宇晖, 李敏. 基于智能优化的协作治疗调度算法[J]. 广东工业大学学报, 2023, 40(05): 21-33.
[3] Gary Yen, 栗波, 谢胜利. 地球流体动力学模型恢复的长短期记忆网络渐进优化方法[J]. 广东工业大学学报, 2021, 38(06): 1-8.
[4] 王美林, 曾俊杰, 成克强, 陈晓航. 改进遗传算法求解基于MPN混流制造车间调度问题[J]. 广东工业大学学报, 2021, 38(05): 24-32.
[5] 杨兴雨, 刘伟龙, 井明月, 张永. 基于模糊收益率的分散化投资组合调整策略[J]. 广东工业大学学报, 2020, 37(05): 13-21.
[6] 赵晓健. 基于遗传算法的多约束叠合梁斜拉桥钢梁维护策略优化[J]. 广东工业大学学报, 2018, 35(04): 75-80.
[7] 李云, 王志红, 王琦, 漆文光, 李斌, 吉瑞博, 龙志宏. 改进NSGA-Ⅱ算法在水质监测点多目标优化研究中的应用[J]. 广东工业大学学报, 2018, 35(02): 35-40.
[8] 许青林, 徐峰, 肖红, 刘沧生, 熊梦琪, 王志. 网络运维中现场作业任务调度的研究[J]. 广东工业大学学报, 2016, 33(04): 18-22.
[9] 何勇，温洁嫦，黄美华. 基于遗传算法的三层大规模应急救援物资配置策略[J]. 广东工业大学学报, 2016, 33(02): 37-41.
[10] 李松芳, 刘伟. 基于万有引力思想的遗传算子[J]. 广东工业大学学报, 2015, 32(1): 121-127.
[11] 韩广, 刘海林. 多约束的应用层组播算法研究[J]. 广东工业大学学报, 2015, 32(04): 118-122.
[12] 李松芳, 刘伟, 徐怀祥. 一种基于漂移和波动思想的遗传算法[J]. 广东工业大学学报, 2014, 31(1): 40-45.
[13] 汤雅连，蔡延光，郭帅，乐峰. 单车场关联物流运输调度问题的混沌遗传算法[J]. 广东工业大学学报, 2013, 30(3): 53-57.
[14] 郭佩珍，胡刚，傅惠. 基于随机时间的车辆导航路径规划研究[J]. 广东工业大学学报, 2012, 29(1): 35-38.
[15] 涂井先,刘伟. 基于辅助种群分类的遗传算法[J]. 广东工业大学学报, 2012, 29(1): 39-42.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
版权所有 © 2017 《广东工业大学学报》编辑部
地址：广州市东风东路729号广东工业大学 邮编：510090
电话：020-37626653,020-37626139,020-37626396
邮箱：xbzrb@gdut.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发