Quality of Transmission Estimation and Short-Term Performance Forecast of Lightpaths

Abstract

With ever-increasing traffic, the need more dynamic, flexible and autonomous optical networks is more important than ever. The availability of performance monitoring data makes it possible to leverage machine learning (ML) for fast quality of transmission (QoT) estimation and performance prediction of lightpaths in complex optical networks. In this work, we explore classifiers based on support vector machine (SVM) and artificial neural network (ANN) for QoT estimation of unestablished lightpaths. Using a synthetic knowledge base (KB), the classification accuracy of the ANN and SVM models decreased from 99%, with a complete feature set, to 85.03% and 88.52%, respectively, with a reduced feature set. We also propose a Long Short-Term Memory (LSTM), an Encoder-Decoder LSTM and a Gated Recurrent Unit (GRU) models, trained with 13-month field performance data, for lightpath signal-to-noise (SNR) prediction over forecast horizons up to 4 days. Positive R 2 values combined with low ( 0.285 dB) root mean square error (RMSE) indicated that the GRU model achieved slightly better predictions than the naive method for forecast horizons ranging from 1 to 96 hours, whereas the LSTM performed better over 24 to 96-hour forecast horizons. The Encoder-Decoder LSTM model achieved the lowest R 2 and the highest RMSE values (0.296 dB). Additional input data will be needed to improve the prediction accuracy of the LSTM and GRU models trained with single lightpath data.

Multivariate Machine Learning Models for Short-Term Forecast of Lightpath Performance

“…ML models have been explored for quality of transmission (QoT) estimation before lightpath establishment. Various supervised learning models trained with synthetic data have been proposed predicting the probability that the bit error rate (BER) will not exceed a predefined performance threshold [1,[6][7][8]. In [1], Artificial Neural Network (ANN) and Support Vector Machine (SVM) algorithms with different feature sets have been used to estimate the QoT of unestablished lightpaths.…”

“…Various supervised learning models trained with synthetic data have been proposed predicting the probability that the bit error rate (BER) will not exceed a predefined performance threshold [1,[6][7][8]. In [1], Artificial Neural Network (ANN) and Support Vector Machine (SVM) algorithms with different feature sets have been used to estimate the QoT of unestablished lightpaths. Random Forest (RF), linear and nonlinear regression models have been used to predict the actual BER value of a new lightpath to be established.…”

“…In this paper, we propose two new multivariate QoT prediction models, expanding on the univariate LSTM and GRU models presented in [1], in order to forecast the QoT of an established lightpath. The two multivariate forecast models proposed in this study are trained using a database, herein referred to as KB-1.…”

“…The two multivariate forecast models proposed in this study are trained using a database, herein referred to as KB-1. It consists of the historical BER data presented in [1], the channel received optical power (P RX ), the differential group delay (DGD) for one lightpath (hereafter called lightpath-1) carried on a 1300-km route in the CANARIE network, and the outside temperature and period of the day as additional features. Moreover, an analysis of the aforementioned features is carried out to study their impact on the performance of the multivariate models.…”

ARMONIA: A Unified Access and Metro Network Architecture

“…One is to leverage QoT data (e.g., from OPMs) to train an agnostic (in terms of the transmission model) ML algorithm. The algorithm can either estimate a raw QoT value (regression) [22], or estimate whether a lightpath has acceptable QoT (classification) [23]. Another approach is to leverage QoT data to improve the accuracy of the parameters' values of an existing QoT model based on theoretical formulas [22,24].…”