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.

 

As video tra!c continues to dominate the Internet, interest in nearsecond low-latency streaming has increased. Existing low-latency streaming platforms rely on using tens of seconds of video in the bu"er to o"er a seamless experience. Striving for near-second latency requires the receiver to make quick decisions regarding the download bitrate and the playback speed. To cope with the challenges, we design a new adaptive bitrate (ABR) scheme, Stallion, for STAndard Low-LAtency vIdeo cONtrol. Stallion uses a sliding window to measure the mean and standard deviation of both the bandwidth and latency. We evaluate Stallion and compare it to the standard DASH DYNAMIC algorithm over a variety of networking conditions. Stallion shows 1.8x increase in bitrate, and 4.3x reduction in the number of stalls. 

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: We investigate dynamic network resource allocation using software-defined networking optical controller with software-defined radios on the COSMOS testbed. 10 Gb/s capacity, deterministic low latency are maintained through user equipment wireless handover via optical switching. 

We investigate dynamic network resource allocation using software-defined networking optical controller with software-defined radios on the COSMOS testbed. 10 Gb/s capacity, deterministic low latency are maintained through user equipment wireless handover via optical switching. © 2020 The Author(s) OCIS codes: 060.4256, 060.0060. 

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.