Search for: All records

Optical transmission systems with high spectral efficiency require accurate quality of transmission estimation for optical channel provisioning. However, the wavelength-dependent gain effects of erbium-doped fiber amplifiers (EDFAs) complicate precise optical channel power prediction and low-margin operation. In this work, we examine supervised machine learning methods using multiple artificial neural networks (ANNs) to build models for gain spectra prediction of optical transmission line EDFAs under different operating conditions. Channel-loading configurations and channel input power spectra are used as an a posteriori knowledge data feature for model training. In a hybrid learning approach, estimated gain spectra calculated by an analytical model are added as an a priori input data feature to further improve the EDFA ANN model performance in terms of prediction accuracy, training time, and quantity of training data. Using these methods, the root mean square error and maximum absolute error of the predicted channel output power can be as low as 0.144 dB and 1.6 dB, respectively.

 

A hybrid machine learning (HML) model combining a-priori and a-posteriori knowledge is implemented and tested, which is shown to reduce the prediction error and training complexity, compared to an analytical or neural network learning model. 

Abstract: A hybrid machine learning (HML) model combining a-priori and a-posteriori knowledge is implemented and tested, which is shown to reduce the prediction error and training complexity, compared to an analytical or neural network learning model. 

An SDN controller is developed for both testbed management and experimentation for the optical x-haul network in the COSMOS testbed providing a service-on-demand and reconfigurable platform for 5G wireless experiments coupled with edge cloud services. 

Abstract: An SDN controller is developed for both testbed management and experimentation for the optical x-haul network in the COSMOS testbed providing a service-on-demand and reconfigurable platform for 5G wireless experiments coupled with edge cloud services. 

The Cloud-Enhanced Open Software Defined Mobile Wireless Testbed for City-Scale Deployment (COSMOS) platform is a programmable city-scale shared multi-user advanced wireless testbed that is being deployed in West Harlem of New York City [1]. To keep pace with the significantly increased wireless link bandwidth and to effectively integrate the emerging C-RANs, COSMOS is designed to incorporate a fast programmable core network for providing connections across different computing layers. A key feature of COSMOS is its dark fiber based optical x-haul network that enables both highly flexible, user defined network topologies and experimentation directly in the optical physical layer. The optical architecture of COSMOS was presented in [2]. In this abstract, we present the tools and services designed to configure and monitor the performance of optical paths and topologies of the COSMOS testbed. In particular, we present the SDN framework that allows testbed users to implement experiments with application-driven control of optical and data networking functionalities. 

The COSMOS testbed provides an open-access and programmable multi-layer beyond 5G wireless platform built on an advanced optical x-haul network supporting mobile edge cloud base band processing and applications. OCIS codes: (060.4250) Networks; (060.2330) Fiber optics communications. 

Disaggregating optical communication systems can impact physical layer control. Recent progress on multi-domain transmission control and machine-learning provide capabilities for adaptation and development of engineering rules in the field with potential benefits for disaggregated systems.