基于图神经网络的OMCI模型相似性计算  

OMCI model similarity computation based on graph neural networks

作　　者：袁佳伟 赵进[1] YUAN Jia-wei;ZHAO Jin(School of Computer Science,Fudan University,Shanghai 200438,China)

机构地区：[1]复旦大学计算机科学技术学院,上海200438

出　　处：《计算机工程与科学》2024年第9期1576-1586,共11页Computer Engineering & Science

摘　　要：光网络单元管理和控制接口OMCI,是千兆无源光网络GPON系统中光线路终端OLT与光网络单元ONU之间进行互联互通的重要协议。在解决OMCI互通问题的过程中,经常需要开发人员对OMCI业务模型进行异常分析,但由于OMCI领域知识的复杂性,对于缺乏经验的开发人员直接分析OMCI业务模型是非常困难的,并且耗时耗力。因此,针对上述实际问题中的挑战,提出了一种基于图神经网络进行OMCI模型异常分析的方法,通过图相似性计算算法,从数据库中查找相似的OMCI模型作为参考,然后比较差异性,找到异常点。首先将真实的OMCI数据构建成图数据,然后结合图同构网络与自注意力池化改进快速计算图相似性模型(SimGNN),最后计算OMCI图数据库中每个图与异常图数据的相似性得分,根据得分排名推荐出最相似的若干OMCI业务模型图。实验结果表明,改进的图相似性计算模型与基准模型相比,在OMCI数据集上性能有所提升,并且在实际应用中也是有效的,对OMCI互通问题的分析起到了一定的帮助作用。The optical network unit management and control interface(OMCI)is a crucial protocol for interconnectivity between the optical line terminal(OLT)and optical network unit(ONU)in Gigabit-capable passive optical networks(GPON)systems.When addressing OMCI interoperability issues,developers often need to conduct exception analysis on OMCI service models.However,due to the complexity of OMCI domain knowledge,directly analyzing OMCI service models can be extremely challenging,time-consuming,and laborious for inexperienced developers.To address these challenges,the OMCI model exception analysis method based on graph neural networks(GNNs)is proposed.This method leverages graph similarity computation algorithms to search for similar OMCI models from a database as references,compares the differences,and identifies anomalies.Firstly,real OMCI data is structured into graph data.Subsequently,the similarity graph neural network(SimGNN)is improved by integrating graph isomorphism networks and self-attention pooling for fast graph similarity computation.Finally,the similarity scores between each graph in the OMCI graph database and the anomalous graph data are calculated,and the most similar OMCI service model graphs are recommended based on the score ranking.Experimental results show that the improved graph similarity computation model outperforms the baseline model on the OMCI dataset used in this study.Moreover,it proves effective in practical applications,offering valuable assistance in analyzing OMCI interoperability issues.

关 键 词：光网络 OMCI 异常分析 图神经网络 图相似性计算 图同构网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]