Data-driven Optical Fiber Channel Modeling: A Deep Learning Approach

Wang, Danshi; Song, Yuchen; Li, Jin; Qin, Jun; Yang, Tao; Zhang, Min; Chen, Xue; Boucouvalas, Anthony C.

doi:10.1109/jlt.2020.2993271

Cited by 97 publications

(20 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, a major drawback hindering practical implementation is that a differentiable channel model is necessary to execute parameter adjustment through backpropagation. Accordingly, a DL-based fiber channel modeling scheme was proposed (Wang et al, 2020). In theory, DL can approximate any function to solve both linear and nonlinear problems.…”

Section: End-to-end Learning For Joint Optimization With Dl-based Chamentioning

confidence: 99%

Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

Wang

Zhang

2021

Front. Comms. Net.

Self Cite

View full text Add to dashboard Cite

Techniques from artificial intelligence have been widely applied in optical communication and networks, evolving from early machine learning (ML) to the recent deep learning (DL). This paper focuses on state-of-the-art DL algorithms and aims to highlight the contributions of DL to optical communications. Considering the characteristics of different DL algorithms and data types, we review multiple DL-enabled solutions to optical communication. First, a convolutional neural network (CNN) is used for image recognition and a recurrent neural network (RNN) is applied for sequential data analysis. A variety of functions can be achieved by the corresponding DL algorithms through processing the different image data and sequential data collected from optical communication. A data-driven channel modeling method is also proposed to replace the conventional block-based modeling method and improve the end-to-end learning performance. Additionally, a generative adversarial network (GAN) is introduced for data augmentation to expand the training dataset from rare experimental data. Finally, deep reinforcement learning (DRL) is applied to perform self-configuration and adaptive allocation for optical networks.

show abstract

Section: End-to-end Learning For Joint Optimization With Dl-based Chamentioning

confidence: 99%

Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

Wang

Zhang

2021

Front. Comms. Net.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning algorithms have already been exploited by the optical communications community and, in particular, the free space optical communications community. For example, in [30], a data-driven fiber channel deep learning (DL) modeling method was introduced in an optical communication system. Specifically, a bidirectional long shortterm memory was selected to perform fiber channel modeling for on-off keying (OOK) and pulse amplitude modulation 4 signals.…”

Section: Machine Learning Based Fso Research Backgroundmentioning

confidence: 99%

Using Machine Learning Algorithms for Accurate Received Optical Power Prediction of an FSO Link over a Maritime Environment

et al. 2021

View full text Add to dashboard Cite

The performance prediction of an optical communications link over maritime environments has been extensively researched over the last two decades. The various atmospheric phenomena and turbulence effects have been thoroughly explored, and long-term measurements have allowed for the construction of simple empirical models. The aim of this work is to demonstrate the prediction accuracy of various machine learning (ML) algorithms for a free-space optical communication (FSO) link performance, with respect to real time, non-linear atmospheric conditions. A large data set of received signal strength indicators (RSSI) for a laser communications link has been collected and analyzed against seven local atmospheric parameters (i.e., wind speed, pressure, temperature, humidity, dew point, solar flux and air-sea temperature difference). The k-nearest-neighbors (KNN), tree-based methods-decision trees, random forest and gradient boosting- and artificial neural networks (ANN) have been employed and compared among each other using the root mean square error (RMSE) and the coefficient of determination (R2) of each model as the primary performance indices. The regression analysis revealed an excellent fit for all ML models, indicative of their ability to offer a significant improvement in FSO performance modeling as compared to traditional regression models. The best-performing R2 model found to be the ANN approach (0.94867), while random forests achieved the most optimal RMSE result (7.37).

show abstract

“…3) Training Without a Channel Model: In case the channel is unknown or not differentiable, e.g., an experimental channel, the transmitter optimization becomes challenging due to the fact that the gradient of the instantaneous channel transfer function is unknown, thus hindering the numerical computation of the transmitter gradients. One way to circumvent this limitation is to first learn a surrogate channel model, e.g., through supervised learning [39], [40] or an adversarial process [11], [41], and use the surrogate model to train the transmitter. However, the performance of the resulting system severely degrades if the surrogate model deviates from the real channel.…”

Section: B End-to-end Ae Learning-based Communication Systems 1) Ae-b...mentioning

confidence: 99%

Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware Impairments

Song¹,

Häger²,

Schröder³

et al. 2021

Preprint

View full text Add to dashboard Cite

We propose an autoencoder (AE)-based transceiver for a wavelength division multiplexing (WDM) system impaired by hardware imperfections. We design our AE following the architecture of conventional communication systems. This enables to initialize the AE-based transceiver to have similar performance to its conventional counterpart prior to training and improves the training convergence rate. We first train the AE in a singlechannel system, and show that it achieves performance improvements by putting energy outside the desired bandwidth, and therefore cannot be used for a WDM system. We then train the AE in a WDM setup. Simulation results show that the proposed AE significantly outperforms the conventional approach. More specifically, it increases the spectral efficiency of the considered system by reducing the guard band by 37% and 50% for a rootraised-cosine filter-based matched filter with 10% and 1% roll-off, respectively. An ablation study indicates that the performance gain can be ascribed to the optimization of the symbol mapper, the pulse-shaping filter, and the symbol demapper. Finally, we use reinforcement learning to learn the pulse-shaping filter under the assumption that the channel model is unknown. Simulation results show that the reinforcement-learning-based algorithm achieves similar performance to the standard supervised endto-end learning approach assuming perfect channel knowledge.

show abstract

Data-driven Optical Fiber Channel Modeling: A Deep Learning Approach

Cited by 97 publications

References 25 publications

Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

Artificial Intelligence in Optical Communications: From Machine Learning to Deep Learning

Using Machine Learning Algorithms for Accurate Received Optical Power Prediction of an FSO Link over a Maritime Environment

Model-Based End-to-End Learning for WDM Systems With Transceiver Hardware Impairments

Contact Info

Product

Resources

About