基于集成学习的广域光骨干网多信道传输质量预测方法  

Multi-channel QoT prediction method in wide-area optical backbone network based on ensemble learning

作　　者：孙晓川 李志刚 张明辉 桂冠[1] SUN Xiaochuan;LI Zhigang;ZHANG Minghui;GUI Guan(College of Telecommunications and Information Engineering,Nanjing University of Posts and Telecommunications,Nanjing 210003,China;College of Artificial Intelligence,North China University of Science and Technology,Tangshan 063210,China;School of Electronics and Information Engineering,Hebei University of Technology,Tianjin 300401,China)

机构地区：[1]南京邮电大学通信与信息工程学院,江苏南京210003 [2]华北理工大学人工智能学院,河北唐山063210 [3]河北工业大学电子信息工程学院,天津300401

出　　处：《通信学报》2020年第9期1-7,共7页Journal on Communications

基　　金：河北省自然科学基金资助项目(No.F2018209181);河北省高等学校科学技术研究基金资助项目(No.QN2018115);国家科技部科技重大基金资助项目(No.2017YFE0135700);唐山市科技计划基金资助项目(No.19150230E)。

摘　　要：针对动态广域光骨干网中光信道传输质量预测方法精确度不足的问题,以集成学习理论为基础提出一种光信道传输质量预测方法。首先,在堆栈集成学习框架下构建了由5个多层感知器模型组成的基学习器,通过并行组合的方式实现了样本数据的同态集成学习。然后,融合基学习器的预测结果形成新的训练集,用于训练由单一多层感知器组成的元学习器。仿真结果表明,对比深度神经网络,所提方法在单信道和多信道QoT预测场景下具有更优秀的非线性逼近性能,预测精度分别提高了1.93%和3.82%。Due to the fact that in dynamic wide-area optical backbone network the accuracies of the existing prediction methods were insufficient,a novel prediction method on quality of transmission(QoT)of optical channel was proposed based on ensemble learning theory.Firstly,under the framework of stacked ensemble learning,a base-learner including five multilayer perceptron(MLP)model was built,which could achieve homomorphic ensemble learning of sample data through parallel combination.Subsequently,the new training set fused from the predicted results of the preceding base-learner was used to training the meta-learner composed of a single MLP.The simulation results show that compared with the used deep neural network,the proposed method can obtain a more excellent nonlinear approximation in the scenarios of the single-channel and multi-channels,and the prediction accuracies have the improvements of 1.93%and 3.82%respectively.

关 键 词：光骨干网 多信道 传输质量预测 集成学习 

分 类 号：TN91[电子电信—通信与信息系统]