Modeling EDFA Gain Ripple and Filter Penalties With Machine Learning for Accurate QoT Estimation

Modeling EDFA Gain Ripple and Filter Penalties With Machine Learning for Accurate QoT Estimation
复制标题

通过机器学习对 EDFA 增益纹波和滤波器惩罚进行建模,以实现准确的 QoT 估计

DOI:
--
复制
发表时间:
2020
影响因子:
4.7
通讯作者:
R. Muñoz
R. Muñoz
中科院分区:
工程技术2区
文献类型:
--
作者:
Ankush Mahajan;K. Christodoulopoulos;R. Martínez;S. Spadaro;R. Muñoz

文献摘要

参考文献

被引文献

相似文献

为了实现可靠、高效的网络规划和运行,在建立或重新配置连接之前,必须准确估计传输质量(QoT)。在光网络中,设计余量通常包含在QoT估计工具(Qtool)中,以考虑建模和参数的不准确性,确保可接受的性能。在本文中,我们使用来自运行网络的监控信息,并结合监督机器学习(ML)技术来了解网络状况。特别地,我们模拟了由于i)掺铒光纤放大器(EDFA)增益纹波效应和ii)可重构光加丢复用器(ROADM)节点的滤波器光谱形状不确定性而产生的惩罚。使用提议的ML回归模型增强Qtool,可以对考虑这两种影响的新连接或重新配置的连接进行估计,从而获得更准确的QoT估计并减少设计余量。我们最初提出了两个有监督的ML回归模型,用支持向量机回归(SVMR)实现,来估计两种效应的个体惩罚,然后是一个组合模型。在具有12个节点和40条双向链路的德国电信(DT)网络拓扑结构上,我们实现了新连接请求的设计余量减少约1 dB。
For reliable and efficient network planning and operation, accurate estimation of Quality of Transmission (QoT) before establishing or reconfiguring the connection is necessary. In optical networks, a design margin is generally included in a QoT estimation tool (Qtool) to account for modeling and parameter inaccuracies, ensuring the acceptable performance. In this article, we use monitoring information from an operating network combined with supervised machine learning (ML) techniques to understand the network conditions. In particular, we model the penalties generated due to i) Erbium Doped Fiber Amplifier (EDFA) gain ripple effect, and ii) filter spectral shape uncertainties at Reconfigurable Optical Add and Drop Multiplexer (ROADM) nodes. Enhancing the Qtool with the proposed ML regression models yields estimates for new or reconfigured connections that account for these two effects, resulting in more accurate QoT estimation and a reduced design margin. We initially propose two supervised ML regression models, implemented with Support Vector Machine Regression (SVMR), to estimate the individual penalties of the two effects and then a combined model. On Deutsche Telekom (DT) network topology with 12 nodes and 40 bidirectional links, we achieve a design margin reduction of ∼1 dB for new connection requests.
非线性区域中低裕度弹性光网络的设计考虑 [邀请]
DOI: 10.1364/jocn.11.000c76
发表时间: 2019
影响因子: 5
作者:
Savory S
通讯作者: Savory S
DOI: 10.1109/ecoc.2018.8535323
发表时间: 2018-09
期刊: 2018 European Conference on Optical Communication (ECOC)
影响因子: --
作者:
Shengxiang Zhu;Craig L. Gutterman;W. Mo;Yao Li;G. Zussman;D. Kilper
通讯作者: Shengxiang Zhu;Craig L. Gutterman;W. Mo;Yao Li;G. Zussman;D. Kilper
混合机器学习 EDFA 模型
DOI: 10.1364/ofc.2020.t4b.4
发表时间: 2020
期刊: California United States
影响因子: --
作者:
Zhu, Shengxiang;Gutterman, Craig;Montiel, Alan Diaz;Yu, Jiakai;Ruffini, Marco;Zussman, Gil;Kilper, Daniel
通讯作者: Kilper, Daniel