Recurrent Neural Networks for Short-Term Forecast of Lightpath Performance

Aladin, Sandra; Allogba, Stephanie; Tran, Anh Vu Stephan; Tremblay, Christine

doi:10.1364/ofc.2020.w2a.24

Cited by 6 publications

(15 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…LSTM and GRU models provided better performance over very short horizons (8 hours and 12 hours) [11]. On the other hand, in [1,10], LSTM and GRU models exhibited better performance for longer horizons (from 24 to 96 hours).…”

Section: Short-term Snr Forecast Problemmentioning

confidence: 93%

“…In the wireless domain, LSTM and GRU variants of deep recurrent neural networks (RNNs) have been proposed for link quality prediction [9]. In the optical domain, ML methods have also been used to predict lightpath performance using historical performance data [1,[10][11][12]. Two NN variants, namely GRU and LSTM algorithms, have been trained using monitored field data to predict signal-to-noise ratio (SNR) for an existing lightpath over forecast horizons of up to 24 hours [1,[10][11][12].…”

Section: Short-term Snr Forecast Problemmentioning

confidence: 99%

“…from February 2017 to July 2017) and 18 months for lightpath-3 (i.e. from February 2017 to August 2018) [11]. Next, the SNR time series is computed from the raw pre-FEC BER data extracted from the PM data.…”

Section: A Databases Descriptionmentioning

confidence: 99%

See 2 more Smart Citations

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

Allogba

Aladin

Tremblay

2021

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

Machine Learning (ML) is emerging as a promising solution for managing the physical layer complexity of heterogeneous dynamic optical networks transporting multiple applications in a software defined network (SDN) context, namely for performance prediction. We propose two multivariate neural network models based on Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM) methods, trained with field performance data and features, for predicting lightpath signal-to-noise ratio (SNR) over forecast horizons of up to 4 days. The best performance is achieved by using a 5-feature LSTM multivariate model over forecast horizons of up to 96 hours, with an absolute maximum error (AME) of 0.90 dB, compared to 0.91 dB and 0.97 dB for the GRU and LSTM univariate models, respectively, and 1.21 dB for a persistence model. The 2-feature multivariate models obtained through feature engineering perform better than their univariate counterparts for forecast horizons of up to 40 hours. Lastly, we explore the concept of transfer learning (TL) by testing the trained multivariate LSTM and univariate GRU models on field data from two lightpaths carried on the same route. The TL models underperform the naive model for the lightpath carried in a different optical fiber. However, for the lightpath carried in the same optical fiber on a portion of the same route, the LSTM-based TL model outperforms the naive model with a difference of up to 0.11 dB at a 96-hour forecast horizon, compared to 0.30 dB for the lightpath in the source domain, while using 3 times less training data.

show abstract

Section: Short-term Snr Forecast Problemmentioning

confidence: 93%

Section: Short-term Snr Forecast Problemmentioning

confidence: 99%

See 1 more Smart Citation

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

Allogba

Aladin

Tremblay

2021

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…As in [7], the size of the observation window (i.e. the size of the SNR sequence used by the model to determine the next SNR value for a given forecast horizon) has a significant impact on the model performance.…”

Section: Evaluation Of the Snr Prediction Modelsmentioning

confidence: 99%

“…A long short-term memory (LSTM) algorithm has been proposed to predict reconfigurable optical add-drop multiplexer (ROADM) network resource requirements 30 minutes in advance [6]. The proposed LSTM and Gated Recurrent Unit (GRU) models trained with field lightpath data for short-term SNR forecasting have produced promising results [7].…”

Section: Introductionmentioning

confidence: 99%

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

Aladin

Tran

Allogba

et al. 2020

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Uncertainty-Aware QoT Forecasting in Optical Networks with Bayesian Recurrent Neural Networks

Di Cicco,

Talpini,

Ibrahimi

et al. 2023

ICC 2023 - IEEE International Conference on Communications

View full text Add to dashboard Cite

We consider the problem of forecasting the Qualityof-Transmission (QoT) of deployed lightpaths in a Wavelength Division Multiplexing (WDM) optical network. QoT forecasting plays a determinant role in network management and planning, as it allows network operators to proactively plan maintenance or detect anomalies in a lightpath. To this end, we leverage Bayesian Recurrent Neural Networks for learning uncertaintyaware probabilistic QoT forecasts, i.e., for modelling a probability distribution of the QoT over a time horizon. We evaluate our proposed approach on the open-source Microsoft Wide Area Network (WAN) optical backbone dataset. Our illustrative numerical results show that our approach not only outperforms state-of-theart models from literature, but also predicts intervals providing near-optimal empirical coverage. As such, we demonstrate that uncertainty-aware probabilistic modelling enables the application of QoT forecasting in risk-sensitive application scenarios.

show abstract

Recurrent Neural Networks for Short-Term Forecast of Lightpath Performance

Abstract: We show how the Recurrent Neural Networks can be used for performance prediction of lightpaths using field bit error rate data. Moreover, we illustrate how the forecast horizons and observation windows affect the forecast accuracy.

Cited by 6 publications

References 2 publications

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

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

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

Uncertainty-Aware QoT Forecasting in Optical Networks with Bayesian Recurrent Neural Networks

Contact Info

Product

Resources

About