摘要
网络性能预测是实现软件定义光网络(SDON)高效网络管理的关键,但目前亟需一种能够以较低成本准确预测关键指标的网络性能预测模型。提出一种基于图神经网络的SDON性能预测模型,该模型将Bi GRU和Self-Attention机制相结合,能够学习网络拓扑、路由和流量矩阵之间的复杂关系,从而准确地估计网络中源/目的地的分组延迟、抖动以及丢包率,并且可以应用于训练中未遇到的网络。实验结果表明,在不同流量模型测试中,所提模型相较于基线模型的平均绝对百分比误差(MAPE)性能有明显提升。
Network performance prediction is the key to achieving efficient network management of software defined optical net-works(SDON),but there is an urgent need for a network performance prediction model that can accurately predict key indicators at limited cost.A graph neural network-based SDON performance prediction model is proposed,which combines BiGRU and Self-Attention mechanisms to learn the complex relationships between network topology,routing,and traffic matrices,accurately estimating the packet delay,jitter,and packet loss rate of the source/destination in the network.This model can be applied to net-works that have not been encountered during training.The experimental results show that in different traffic model tests,the pro-posed model has a significant improvement in average absolute percentage error(MAPE)performance compared to the baseline model.
作者
王星宇
张慧
蔡安亮
沈建华
WANG Xingyu;ZHANG Hui;CAI Anliang;SHEN Jianhua(School of Communication and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;CypressTel SHENZHEN Communication Technology Company,Shenzhen Guangdong 518000,China)
出处
《光通信技术》
北大核心
2024年第3期38-44,共7页
Optical Communication Technology
基金
国家自然科学青年基金项目(62301284)资助
南京邮电大学企业委托研发重点课题(KH0020322072)资助。
关键词
图神经网络
网络性能预测
软件定义光网络
自注意力机制
光通信
graph neural networks
network performance prediction
software-defined optical network
Self-Attention mecha-nisms
optical communication
作者简介
王星宇(1999-),男,硕士研究生,现就读于南京邮电大学通信与信息工程学院电子信息专业,主要研究方向为光网络、软件定义网络,参与了南京邮电大学横向科研课题野新一代智能SD-WAN体系架构及其关键技术冶研发;通信作者:沈建华(1972-),男,工学博士,教授,硕士生导师,主要研究方向为高速率大容量光纤通信系统、智能光网络、软件定义网络等。
