Learned Signal-to-Noise Ratio Estimation in Optical Fiber Communication Links

Al-Nahhal, Mohamed; Al-Nahhal, Ibrahim; Dobre, Octavia A.; Kumar, O. S. Sunish; Chang, Deyuan; Li, Chuandong

doi:10.1109/jphot.2022.3222264

Cited by 5 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the proposed ParNN and EParNN estimators are assessed and compared with the two scenarios described in Sections III-B1 and III-B2. Furthermore, the proposed estimators are compared with those in [15], [16], [18]- [21]. The comparison of the SNR estimators is performed in terms of the computational complexity and SNR components estimation accuracy.…”

Section: Numerical Results and Discussionmentioning

confidence: 99%

“…This section presents the computational complexity analysis of the proposed ParNN and EParNN estimators in comparison with the literature estimators in [15], [16], [18]- [21]. The computational complexity includes the cost of the input features generation from the received signal plus the NN structure cost utilized for the SNR L and SNR N estimation.…”

Section: Complexity Analysismentioning

confidence: 99%

“…In [21], the authors have employed a combination of the entropy and lower quartile-based input features, and the generation of these features implies 225K +377 real multiplications and 77K log 2 (K) + 103K + 147 real additions. The RNN structure with a single recurrent layer has used in [21], whose cost can be calculated as…”

Section: A Complexity Of Literature Estimatorsmentioning

confidence: 99%

“…Here, N i , N h1 , and N o are the number of neurons in the input, hidden recurrent, and output layers, respectively. According to (26), the cost of the RNN structure in [21] is 1053 real multiplications and 1092 real additions.…”

Section: A Complexity Of Literature Estimatorsmentioning

confidence: 99%

“…Recently, the linear and nonlinear SNR components have been jointly estimated using an FFNN with two-hidden layers and recurrent NNs (RNNs) along with a single-recurrent layer in [20] and [21], respectively. The authors in [20], [21] have used the entropy-based and lower quartile-based input features generated from the received signal without needing the transmitted signal knowledge. Generating the entropy-based and lower quartile-based input features is an efficient approach in terms of computational complexity when compared with [14]- [19].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Parallel Neural Network Structures for Signal-to-Noise Ratio Estimation in Optical Fiber Communication Systems

Al-Nahhal,

Dobre

et al. 2024

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

This paper proposes two novel neural network (NN) structures to estimate long-term steady linear and nonlinear signal-to-noise ratio (SNR) components in optical fiber communication systems. The first proposed structure is a parallel NNbased (ParNN) estimator, which estimates each SNR component using a different NN structure and input feature set. A combination of gated recurrent unit and dense layers is used to estimate the linear SNR component. On the other hand, the nonlinear SNR component is estimated using a combination of convolutional layer with dense layer. The proposed input features of the ParNN estimator are generated solely from the received signal without knowledge of the transmitted signal. These features are formed of the lower quartile, upper quartile, and entropy, which can accurately characterize the behavior of the SNR components by measuring the received signal spread and uncertainty. For further improvement of the ParNN estimator, an additional stage is added to form the proposed enhanced ParNN (EParNN) estimator. This additional stage consists of two feedforward NNs (FFNNs), each with a single dense layer, where the first FFNN is used to estimate the linear SNR component and the second one estimates the nonlinear SNR component. The input of this additional stage is a combination of the input features and output of the ParNN estimator. The computational complexity is derived for the proposed estimators. The training and testing dataset is built from 16-ary quadrature amplitude modulation of a dualpolarization on a wide range of standard single-mode fiber system configurations, e.g., number of wavelength division multiplexing channels, optical launch power, and number of spans. Numerical results demonstrate that the proposed ParNN estimator achieves better SNR estimation accuracy with comparable computational complexity compared to the most efficient work in the literature. The proposed ParNN estimator can independently estimate each SNR component, in which the complexity per SNR component is reduced. Moreover, the proposed EParNN estimator improves SNR estimation accuracy compared to the ParNN estimator at the expense of a slight increase in the computational complexity.

show abstract

Section: Numerical Results and Discussionmentioning

confidence: 99%

Section: Complexity Analysismentioning

confidence: 99%

Section: A Complexity Of Literature Estimatorsmentioning

confidence: 99%

Section: A Complexity Of Literature Estimatorsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Parallel Neural Network Structures for Signal-to-Noise Ratio Estimation in Optical Fiber Communication Systems

Al-Nahhal,

Dobre

et al. 2024

J. Lightwave Technol.

Self Cite

View full text Add to dashboard Cite

show abstract

Joint OSNR and Nonlinear Noise Power Estimation Based on Deep Learning for Coherent Optical Communication Systems

Li,

Zhang,

Zhang

et al. 2023

IEEE Photonics J.

View full text Add to dashboard Cite

In this paper, a joint OSNR and nonlinear noise power estimation scheme based on multi-task deep neural network (MT-DNN) is proposed with the advantages of dispersion-insensitive, modulation-format-transparent for high-speed, long-haul, multi-channel fiber-optic communication systems. Amplitude histograms (AHs) are generated by processing the spectrums collected with different OSNR, launch power and transmission distance by an offline spectrum preprocessing flow. The MT-DNN can automatically learn the features of the AHs to achieve OSNR and nonlinear noise power estimation, simultaneously. For 4-quadrature amplitude modulation (4QAM), 16QAM and 64QAM signals under different transmission conditions, the average MAE and RMSE are calculated for the OSNR estimate and the nonlinear noise power estimate, which are both less than 1 dB. Moreover, the resistance of OSNR estimation to amplified spontaneous emission (ASE) noise and nonlinearity, and the tolerance of nonlinear noise estimation to launch power and transmission distance are investigated, respectively. The results demonstrate that the joint OSNR and nonlinear noise power estimation scheme is insensitive to dispersion, transparent to modulation format, and has high accuracy and high tolerance. This research provides a research reference value for future optical performance monitoring of coherent optical communication systems.

show abstract

Machine Learning-Based Self-Interference Cancellation for Full-Duplex Radio: Approaches, Open Challenges, and Future Research Directions

Elsayed,

El-Banna,

Dobre

et al. 2024

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

In contrast to the long-held belief that wireless systems can only work in half-duplex mode, full-duplex (FD) systems are able to concurrently transmit and receive information over the same frequency bands to theoretically enable a twofold increase in spectral efficiency. Despite their significant potential, FD systems suffer from an inherent self-interference (SI) due to a coupling of the transmit signal to its own FD receive chain. Selfinterference cancellation (SIC) techniques are the key enablers for realizing the FD operation, and they could be implemented in the propagation, analog, and/or digital domains. Particularly, digital domain cancellation is typically performed using modeldriven approaches, which have proven to be insufficient to seize the growing complexity of forthcoming communication systems. For the time being, machine learning (ML) datadriven approaches have been introduced for digital SIC to overcome the complexity hurdles of traditional methods. This paper reviews and summarizes the recent advances in applying ML to SIC in FD systems. Further, it analyzes the performance of various ML approaches using different performance metrics, such as the achieved SIC, training overhead, memory storage, and computational complexity. Finally, this paper discusses the challenges of applying ML-based techniques to SIC, highlights their potential solutions, and provides a guide for future research directions.

show abstract

Learned Signal-to-Noise Ratio Estimation in Optical Fiber Communication Links

Cited by 5 publications

References 21 publications

Parallel Neural Network Structures for Signal-to-Noise Ratio Estimation in Optical Fiber Communication Systems

Parallel Neural Network Structures for Signal-to-Noise Ratio Estimation in Optical Fiber Communication Systems

Joint OSNR and Nonlinear Noise Power Estimation Based on Deep Learning for Coherent Optical Communication Systems

Machine Learning-Based Self-Interference Cancellation for Full-Duplex Radio: Approaches, Open Challenges, and Future Research Directions

Contact Info

Product

Resources

About