(INVITED)Reconfigurable topology testbeds: A new approach to optical system experiments

Akinrintoyo, Emmanuel; Wang, Zehao; Lantz, Bob; Chen, Tingjun; Kilper, Dan

doi:10.1016/j.yofte.2023.103243

Cited by 9 publications

(2 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1. Using the space switching and WDM switching capabilities, different topologies in the optical physical layer that emulate varying metro networks can be constructed [6,23].…”

Section: A the Pawr Cosmos Testbedmentioning

confidence: 99%

Open EDFA gain spectrum dataset and its applications in data-driven EDFA gain modeling

Wang

Kilper²,

Chen

2023

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

Optical networks satisfy high bandwidth and low latency requirements for telecommunication networks and data center interconnection. To improve network resource utilization, machine learning (ML) is used to accurately model optical amplifiers such as erbium-doped fiber amplifiers (EDFAs), which impact end-to-end system performance such as quality of transmission. However, a comprehensive measurement dataset is required for ML to accurately predict an EDFA’s wavelength-dependent gain. We present an open dataset consisting of 202,752 gain spectrum measurements collected from 16 commercial-grade reconfigurable optical add–drop multiplexer (ROADM) booster and pre-amplifier EDFAs under varying gain settings and diverse channel-loading configurations over 2,785 hours in total, with a total dataset size of 3.1 GB. With this EDFA dataset, we implemented component-level deep-neural-network-based EDFA models and use transfer learning (TL) to transfer the EDFA model among 16 ROADM EDFAs, which achieve less than 0.18/0.24 dB mean absolute error for booster/pre-amplifier gain prediction using only 0.5% of the full target training set. We also showed that TL reduces the EDFA data collection requirements on a new gain setting or a different type of EDFA on the same ROADM.

show abstract

“…1. Using the space switching and WDM switching capabilities, different topologies in the optical physical layer that emulate varying metro networks can be constructed [6,23].…”

Section: A the Pawr Cosmos Testbedmentioning

confidence: 99%

Open EDFA gain spectrum dataset and its applications in data-driven EDFA gain modeling

Wang

Kilper²,

Chen

2023

J. Opt. Commun. Netw.

Self Cite

View full text Add to dashboard Cite

show abstract

“…1. Using the space switching and WDM switching capabilities, different topologies in the optical physical layer that emulate varying metro networks can be constructed [6,23].…”

Section: A the Pawr Cosmos Testbedmentioning

confidence: 99%

An Open EDFA Gain Spectrum Dataset and Its Applications in Data-driven EDFA Gain Modeling

Wang¹,

Kilper²,

Chen³

2023

Preprint

View full text Add to dashboard Cite

Optical networks satisfy high bandwidth and low latency requirements for telecommunication networks and data center interconnection. To improve the network resource utilization, machine learning (ML) is used to accurately model optical amplifiers such as erbium-doped fiber amplifiers (EDFAs) which impact end-to-end system performance such as quality of transmission (QoT). However, a comprehensive measurement dataset is required for ML to accurately predict an EDFA’s wavelength-dependent gain. We present an open dataset consisting of 202,752 gain spectrum measurements collected from 16 commercial-grade ROADM booster and pre-amplifier EDFAs under varying gain settings and diverse channel loading configurations over 2,785 hours in total, with a total dataset size of 3.1 GB. With this EDFA dataset, we implemented component-level deep neural network (DNN) based EDFA models and use transfer learning (TL) to transfer the EDFA model among 16 ROADM EDFAs, which achieve less than 0.18/0.24 dB mean absolute error for booster/pre-amplifier gain prediction using only 0.5% of the full target training set. We also showed that TL reduces the EDFA data collection requirements on a new gain setting or a different type of EDFA on the same ROADM.

show abstract

Enhancing fault detection and classification in optical fiber networks with deep learning algorithms

Kaushik,

Garg,

Verma

et al. 2024

AIP Conference Proceedings

View full text Add to dashboard Cite

(INVITED)Reconfigurable topology testbeds: A new approach to optical system experiments

Cited by 9 publications

References 51 publications

Open EDFA gain spectrum dataset and its applications in data-driven EDFA gain modeling

Open EDFA gain spectrum dataset and its applications in data-driven EDFA gain modeling

An Open EDFA Gain Spectrum Dataset and Its Applications in Data-driven EDFA Gain Modeling

Enhancing fault detection and classification in optical fiber networks with deep learning algorithms

Contact Info

Product

Resources

About