[1]张 攀,来风刚,周 逸,等.基于多通道注意力图卷积网络的微服务分解[J].计算机技术与发展,2023,33(08):66-73.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 010]
 ZHANG Pan,LAI Feng-gang,ZHOU Yi,et al.Multi-channel Attentional Graph Convolutional Networks for Microservice Extraction[J].,2023,33(08):66-73.[doi:10. 3969 / j. issn. 1673-629X. 2023. 08. 010]
点击复制

基于多通道注意力图卷积网络的微服务分解()
分享到:

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年08期
页码:
66-73
栏目:
软件技术与工程
出版日期:
2023-08-10

文章信息/Info

Title:
Multi-channel Attentional Graph Convolutional Networks for Microservice Extraction
文章编号:
1673-629X(2023)08-0066-08
作者:
张 攀1 来风刚1 周 逸1 羊麟威2 钱李烽2 刘 昕2 李 静2
1. 国家电网有限公司信息通信分公司,北京 100053;
2. 南京航空航天大学 计算机科学与技术学院 / 人工智能学院,江苏 南京 211106
Author(s):
ZHANG Pan1 LAI Feng-gang1 ZHOU Yi1 YANG Lin-wei2 QIAN Li-feng2 LIU Xin2 LI Jing2
1. Information and Communication Branch of State Grid Corporation of China,Beijing 100053,China;
2. School of Computer Science and Technology/School of Artificial Intelligence,Nanjing University of Aeronautics and Astronautics,Nanjing 211106,China
关键词:
微服务架构微服务分解图神经网络多通道注意力机制
Keywords:
microservice architecturemicroservice decompositiongraph neural networkmulti-channelattention mechanism
分类号:
TP311. 5
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 08. 010
摘要:
为了解决功能、规模和复杂性不断增长的软件系统可能面临的可维护性和可扩展性等一系列软件开发和运维问题,微服务分解成为了目前研究的热点。 现有的微服务分解主要是通过微服务的聚类,将单体系统划分为潜在的微服务候选。 在微服务的自动化聚类中,基于图卷积网络( Graph Convolutional Network,GCN) 的深度学习方法在特征学习方面取得了较好的效果,但是现有模型中缺乏对多通道信息的处理。 针对该问题,提出一种基于多通道注意力图卷积网络的微服务分解方法 MAGEMP。 该方法使用多通道图注意力网络来学习不同强度的属性图和结构图节点之间的特征嵌入表示,再通过注意力机制获取不同通道嵌入表示的融合信息,最后综合聚类信息的联合学习框架获得高质量的微服务分解。在四个公开数据集上多角度验证该模型的有效性。 与同类方法相比,MAGEMP 方法提高了嵌入特征学习能力,在单体程序公开数据集上测试的功能性、模块性等性能方面取得了显著提升。
Abstract:
In order to solve a series of software development and operation and maintenance problems, such as maintainability andscalability,which may be faced?
by software systems with increasing functions, scale and complexity, microservice extraction is a hotproblem currently. The existing work of microservice extraction is mainly to divide the monolithic program into potential microservicecandidates through the clustering of microservices. The graph convolutional network ( GCN) for automatic microservice extraction hasbeen obtained potential results,but being lack of taking full advantage of multi - channel information. To solve the above problems,amonolith decomposition method using deep learning clustering based on multi-channel attention map neural network ( MAGEMP) is proposed. Multiple independent graph convolutional networks are used to learn different interactions between topological graph and attributegraph nodes of different modal, and then the fusion of different embedding representations is further obtained through the attentionmechanism,finally the joint learning framework integrating clustering information obtains high - quality microservice division. Thevalidity of the model is verified from multiple angles on four public data sets. Compared with similar methods,MAGEMP improves thelearning ability of embedded features,and significantly improves the performance of testing on the open data set of monomer programs,such as functionality and modularity.
更新日期/Last Update: 2023-08-10