Fast remodeling for nonlinear distortion mitigation based on transfer learning

Zhang, Jing; Xia, Le; Zhu, Mingyue; Hu, Shaohua; Xu, Bo; Qiu, Kun

doi:10.1364/ol.44.004243

Cited by 31 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When there is no all-optical regenerator in the transmission link, i.e., an un-regenerative case, the required input SNR becomes even higher with the increase of the loop number N due to the accumulation of ASE noise. For the loop number of 10, i.e., 800 km fiber transmission, we calculated the required input SNR of around 23 dB, close to the input SNR of 26dB demonstrated in a PAM-4 800 km-fiber transmission experiment [21]. After placing the proposed cascade-NOLM regenerator in each span, the amplitude noise is effectively suppressed in the regenerative range, and consequently a lower SNR is needed for the regenerative transmission link, see the red-circular mark in Figure 10a.…”

Section: Cascaded Nolm-based Regeneration Schemesupporting

confidence: 56%

Cascaded Nonlinear-Optical Loop Mirror-Based All-Optical PAM Regenerator

Guo

Wen

et al. 2019

Applied Sciences

Self Cite

View full text Add to dashboard Cite

An all-optical regeneration scheme based on cascaded nonlinear-optical loop mirrors (NOLMs) for pulse amplitude modulation (PAM) signals is proposed. The optimal working point (WP) of every NOLM can be set by means of the normalized power transfer function (NPTF) and normalized differential gain (NDG). As examples, the PAM-4 and PAM-8 regenerations based on cascaded two-NOLMs are demonstrated by optimizing the splitting ratios of the optical couplers and the gain coefficient of the inter-stage matching amplifier, achieving the Q-factor improvements of 25.32dB and 21.18dB, respectively. Compared to the conventional regenerator scheme, a 1.69dB signal-to-noise ratio (SNR) gain is achieved due to the flat power response within the regenerative range.

show abstract

Section: Cascaded Nolm-based Regeneration Schemesupporting

confidence: 56%

Cascaded Nonlinear-Optical Loop Mirror-Based All-Optical PAM Regenerator

Guo

Wen

et al. 2019

Applied Sciences

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent publications on the application of TL in optical communication focus on optical network tools [23][24][25][26][27][28]. A few works also addressed the nonlinearity mitigation issue [29][30][31].…”

Section: A Previous Applications Of Transfer Learning In Optical Fiber Communicationsmentioning

confidence: 99%

Transfer Learning for Neural Networks-Based Equalizers in Coherent Optical Systems

Freire

Abode

Prilepsky

et al. 2021

J. Lightwave Technol.

View full text Add to dashboard Cite

In this work, we address the question of the adaptability of artificial neural networks (NNs) used for impairments mitigation in optical transmission systems. We demonstrate that by using well-developed techniques based on the concept of transfer learning, we can efficaciously retrain NN-based equalizers to adapt to the changes in the transmission system, using just a fraction (down to 1%) of the initial training data or epochs. We evaluate the capability of transfer learning to adapt the NN to changes in the launch power, modulation format, symbol rate, or even fiber plants (different fiber types and lengths). The numerical examples utilize the recently introduced NN equalizer consisting of a convolutional layer coupled with bi-directional long-short term memory (biLSTM) recurrent NN element. Our analysis focuses on long-haul coherent optical transmission systems for two types of fibers: the standard single-mode fiber (SSMF) and the TrueWave Classic (TWC) fiber. We underline the specific peculiarities that occur when transferring the learning in coherent optical communication systems and draw the limits for the transfer learning efficiency. Our results demonstrate the effectiveness of transfer learning for the fast adaptation of NN architectures to different transmission regimes and scenarios, paving the way for engineering flexible and universal solutions for nonlinearity mitigation.

show abstract

“…One promising solution to solve this problem is the transfer learning principle [98,99], which can retain and apply the knowledge captured from a previous task to a new task. In the transfer learning scheme, the parameters of neural network that is trained are reused when the neural network needs to be retrained (e.g., caused by the wireless channel condition change).…”

Section: Open Questions and Possible Future Directions: Ml-based Signal Processing In Rof Systemsmentioning

confidence: 99%

“…The real-world dataset availability is even more challenging when the target is related with network failures, as practical networks normally have conservative designs to minimize the possibility of network faults. To solve the dataset availability challenge, one possible solution is the transfer learning principle discussed in Section 4 [98,99]. This approach can be useful if historical datasets are available and the network evolves relatively slowly over time.…”

Section: Open Questions and Possible Future Directionsmentioning

confidence: 99%

Machine Learning Techniques in Radio-over-Fiber Systems and Networks

Lee

Kandeepan

et al. 2020

Photonics

View full text Add to dashboard Cite

The radio-over-fiber (RoF) technology has been widely studied during the past decades to extend the wireless communication coverage by leveraging the low-loss and broad bandwidth advantages of the optical fiber. With the increasing need for wireless communications, using millimeter-waves (mm-wave) in wireless communications has become the recent trend and many attempts have been made to build high-throughput and robust mm-wave RoF systems during the past a few years. Whilst the RoF technology provides many benefits, it suffers from several fundamental limitations due to the analog optical link, including the fiber chromatic dispersion and nonlinear impairments. Various approaches have been proposed to address these limitations. In particular, machine learning (ML) algorithms have attracted intensive research attention as a promising candidate for handling the complicated physical layer impairments in RoF systems, especially the nonlinearity during signal modulation, transmission and detection. In this paper, we review recent advancements in ML techniques for RoF systems, especially those which utilize ML models as physical layer signal processors to mitigate various types of impairments and to improve the system performance. In addition, ML algorithms have also been widely adopted for highly efficient RoF network management and resource allocation, such as the dynamic bandwidth allocation and network fault detection. In this paper, we also review the recent works in these research domains. Finally, several key open questions that need to be addressed in the future and possible solutions of these questions are also discussed.

show abstract

Fast remodeling for nonlinear distortion mitigation based on transfer learning

Cited by 31 publications

References 14 publications

Cascaded Nonlinear-Optical Loop Mirror-Based All-Optical PAM Regenerator

Cascaded Nonlinear-Optical Loop Mirror-Based All-Optical PAM Regenerator

Transfer Learning for Neural Networks-Based Equalizers in Coherent Optical Systems

Machine Learning Techniques in Radio-over-Fiber Systems and Networks

Contact Info

Product

Resources

About