An Overview on Machine Learning-Based Solutions to Improve Lightpath QoT Estimation

Ayassi, Reda; Triki, Ahmed; Laye, Maxime; Crespi, Noël; Minerva, Roberto; Catanese, Clara

doi:10.1109/icton51198.2020.9203755

Cited by 12 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Light path quality estimation using the optical signal-to-noise ratio (OSNR) and bit error rate (BER). We can assess the light path based on a quality factor by using a neural network [38], [39]. The machine learning-based estimator of the parameters that assesses SNR value.…”

Section: Logistic Regressionmentioning

confidence: 99%

Machine learning-based QoT estimation over optical wireless communication

Sahu

Clement

2023

Preprint

View full text Add to dashboard Cite

Fiber-optic communication and networks play an important role in communications technology. According to the last few decades, in this area, research development is growing rapidly. Machine learning (ML) algorithms for optical communications (OC) are certainly a hot topic in the current generation. To overcome the current limitation and different issues of fiber-optic communication and network, a machine learning (ML) algorithm is essential for us. Machine learning techniques are proof that it has superiority in solving complex problems. Machine learning algorithms generally focused on the education field, business organization, and health sectors. Currently, many researchers work in the optical communications area by using machine learning algorithms techniques. A machine learning algorithm is an emerging technology because it helps in the optical communication field for a better quality of service (QoS). According, to the first time, this work reviews machine learning for optical communication literature from a machine learning viewpoint. Only fiber-optic communication and network experts work on machine learning for optical networks, and they are not ML algorithms experts. This paper uses machine learning algorithms for calculating the quality of transmission (QoT) of light paths in optical 1 Springer Nature 2021 L A T E X template Article Title networks link. For better quality of transmission (QoT) estimation tools, it can show the performance analysis of machine learning-based algorithms by using such as bit error rate (BER), optical signal to noise ratio (OSNR), quality factor (Q-factor), blocking probability, and signal to noise ratio (SNR) data. This paper presents a novel concept of quality of transmission (QoT) based on the machine learning algorithm.

show abstract

Section: Logistic Regressionmentioning

confidence: 99%

Machine learning-based QoT estimation over optical wireless communication

Sahu

Clement

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Similarly, by extending a heterogeneous ANN method, Yu et al [10] proposed a transfer learning model to improve the accuracy of lightpath QoT prediction at a low complexity. Other studies on the ML-based lightpath QoT prediction can also be found in [11][12][13][14].…”

Section: A Ml-based Qot Predictionmentioning

confidence: 99%

“…Although the ML-based models can predict lightpath QoT more accurately and therefore help reduce reserved QoT margins, the datasets used by these models are mainly from two sources, i.e., laboratory datasets and synthetic datasets [14]. For example, Gao et al [9] collected datasets for ML from a 563.4-km field-trial testbed.…”

Section: A Ml-based Qot Predictionmentioning

confidence: 99%

Protection against failure of machine-learning-based QoT prediction

Guo

Mukherjee

et al. 2022

J. Opt. Commun. Netw.

View full text Add to dashboard Cite

Machine learning (ML)-based methods are being widely explored to predict the quality of transmission (QoT) of a lightpath. They are expected to reduce the signal-to-noise ratio margin reserved for the lightpath, thus improving the spectrum efficiency of an optical network. However, many studies on this prediction are often based on synthetic datasets or datasets obtained from laboratories. As such, these datasets may not accurately represent the entire state space of a practical optical network, which is exposed in harsh environments. There are risks of failure when using these ML-based QoT prediction models. Thus, it is necessary to develop a mechanism that can guarantee the reliability of lightpath service even if the prediction model fails. For this scenario, we propose to employ the conventional network protection techniques that are usually implemented to protect against network node/link failures to also protect against the failure of QoT prediction. Based on the two representative protection techniques, i.e., 1 + 1 dedicated path protection and shared backup path protection (SBPP), the performance of the proposed protection mechanism is evaluated by reserving different margins for the working and protection lightpaths. For 1 + 1 path protection, we find that the proposed mechanism can achieve a zero design margin (D-margin) for a working lightpath, thereby significantly improving network spectrum efficiency, while not sacrificing the availability of lightpath services. For SBPP, we find that an optimal D-margin should be identified to balance the spectrum efficiency and service availability; the proposed mechanism can save up to 0.5-dB D-margin for a working lightpath, while guaranteeing service availability.

show abstract

“…Several ML-based QoT estimators have been proposed in the literature [11][12][13][14][15][16][17][18][19]. Good overviews of the most recent ML models and tools developed for lightpath QoT estimation can be found in [20][21][22]. The methodology consists in predicting whether the QoT of the candidate lightpath is above or below a predefined threshold.…”

Section: B Qot Estimation: Do We Need Neural Network?mentioning

confidence: 99%

Machine-Learning-Based Lightpath QoT Estimation and Forecasting

Allogba

Aladin

Tremblay

2022

J. Lightwave Technol.

View full text Add to dashboard Cite

Machine learning (ML) is more and more used to address the challenges of managing the physical layer of increasingly heterogeneous and complex optical networks. In this tutorial, we illustrate how simple and more sophisticated machine learning methods can be used in lightpath quality of transmission (QoT) estimation and forecast tasks. We also discuss data processing strategies with the aim to determine relevant features to feed the ML classifiers and predictors. We then introduce a preliminary study on the application of transfer learning to try to overcome the scarcity of field data.

show abstract

An Overview on Machine Learning-Based Solutions to Improve Lightpath QoT Estimation

Cited by 12 publications

References 13 publications

Machine learning-based QoT estimation over optical wireless communication

Machine learning-based QoT estimation over optical wireless communication

Protection against failure of machine-learning-based QoT prediction

Machine-Learning-Based Lightpath QoT Estimation and Forecasting

Contact Info

Product

Resources

About