Soft-Failure Detection, Localization, Identification, and Severity Prediction by Estimating QoT Model Input Parameters

Abstract

The performance of optical devices can degrade because of aging and external causes like, for example, temperature variations. Such degradation might start with a low impact on the Quality of Transmission (QoT) of the supported lightpaths (soft-failure). However, it can degenerate into a hard-failure if the device itself is not repaired or replaced, or if an external cause responsible for the degradation is not properly addressed. In this work, we propose comparing the QoT measured in the transponders with the one estimated using a QoT tool. Those deviations can be explained by changes in the value of input parameters of the QoT model representing the optical devices, like noise figure in optical amplifiers and reduced Optical Signal to Noise Ratio in the Wavelength Selective Switches. By applying reverse engineering, the value of those modeling parameters can be estimated as a function of the observed QoT of the lightpaths. Experiments reveal high accuracy estimation of modeling parameters, and results obtained by simulation show large anticipation of soft-failure detection and localization, as well as accurate identification of degradations before they have a major impact on the network.

A review of machine learning-based failure management in optical networks

“…A lightpath is a path that carries the optical signal on a lightwave from the source to the destination node within optical domain. The optical signal is essentially transmitted from the transmitter, over multispan fiber, amplifier, filter, to the detector at the destination, which is a complete optical transmission process [8]. For a lightpath, the typical failure types are bit error rate (BER) degradation, optical signal to noise ratio (OSNR) degradation, generalized SNR (GSNR) degradation, optical power drop, channel crosstalk, etc.…”

Intent-based networking and its application to optical networks [Invited Tutorial]

“…4d, based on the GNPy tool [15] to estimate the expected Signal to Noise Ratio (SNR) of the optical connections. In this case, the dynamic configuration module finds the most likely value of modeling parameters based on the monitoring data received from the network (see [12]).…”

“…Examples include QoT degradation and connection rerouting [7], in-operation network planning [8], dynamic capacity allocation of virtual links supported by one or more optical connections [9] or even reconfigure a virtual network topology [10,11]. Finally, as a third category, degradation detection can be used also for failure localization [12,13]. Here, the performance to be achieved is related, e.g., to availability metrics.…”

Guest Editors’ Introduction: Special Section on Design and Management of Reliable Communication Networks

“…Specific solutions for protection in EON are investigated also in [12], where the authors investigate the concept of bandwidth squeezing (i.e., providing less data rate to backup paths) together with grooming capability to provide protection under multiple failure events. Finally, in [13], the authors investigate how to perform early soft-failure detection, identification and localization based on the observation of the temporal behavior of Quality of Transmission measures including noise figure in optical amplifiers and reduced signal to noise ratio in wavelength selective switches.…”