Survey on Applications of Machine Learning in Low-Cost Non-Coherent Optical Systems: Potentials, Challenges, and Perspective
Abstract
:1. Introduction
1.1. The Challenge
1.2. Motivation
- Network security: OPM and MFI provide a means to secure optical networks; an attack on the network usually results in disruptions to the network parameters. Detecting the disruption may aid in the discovery of attacks and, maybe, in preventing them. This could be enabled by OPM and MFI using machine learning [17].
- Boosting network efficiency: Implementing OPM and MFI with machine learning helps the optical network improve its utilization of resources. Proactively anticipating certain events, such as failures and traffic bursts, provides valuable information for the network to adjust its resource utilization in the best way possible [15].
1.3. Related Survey Articles
1.4. Paper Contributions
- Reviews the current situation of OPM and MFI for direct detection systems in terms of channel impairments and monitoring parameters, and discusses the most widely used features that have been considered for ML algorithms in direct detection optical communication systems.
- Reviews the proposed ML solutions for OPM and MFI with a keen eye on what machine learning paradigms have been followed, what learning algorithms are used to develop monitoring solutions, and what type of monitoring tasks have been defined and addressed. This is preceded by a brief overview of the landscape of machine learning.
- Evaluates and analyzes the proposed machine learning solutions. It discusses, from a machine learning perspective, some pitfalls in the development of those solutions, such as the lack of clear arguments for some algorithm choices and the misinterpretation of some core machine learning assumptions. It also emphasizes important issues with the current literature such as the poor dataset construction and description as well as the lack of benchmarking datasets.
- Discuss recommendations for the potential implementation of machine-learning-based monitoring solutions in non-coherent optical systems. In particular, this paper provides observations on the developed ML methods, presents insights into how to solve the observed pitfalls, and highlights some lessons to help guide future research.
1.5. Paper Organization
2. Feature Selection for OPM
- Optical transmitter, where electrical-to-optical (E/O) signal conversion and laser modulation are achieved. Different types of modulation formats can be generated to improve the spectral efficiency (SE) of optical systems. These vary from low-order modulations (i.e., less number of bits per symbol-such as On-Off keying (OOK) and binary phase-shift keying (BPSK) formats) up to high-order formats (i.e., high number of bits per symbol-such as M-ary quadrature amplitude modulation (M-QAM), M = 4, 16, 64, and 128), as shown in the inset of Figure 2, and very recently the optimized modulation schemes, known as geometric and probabilistic modulation formats.
- Optical channel, where optical signals are transmitted and impaired with various channel impairments, as shown in the inset of Figure 2. Through optical channel, the optical modulated signals suffer from various optical impairments depending on the optical channel type (i.e., wired or wireless optical channels). For instance, wire channel, known as standard single-mode fiber (SMF) or few-mode fiber (FMF), introduces linear impairments-such as fiber chromatic dispersion (CD), polarization mode dispersion (PMD), mode-coupling (MC), etc., and non-linear impairments-such as self-phase modulation (SPM), cross-phase modulation (XPM), and four-wave mixing. Whereas, wireless optical channel (known as free-space optics (FSO) channel) is characterized by different impairments types such as weather turbulence and pointing error [31].
- Optical receiver, where optical-to-electrical (O/E) conversion is accomplished as well as signal demodulation and decoding. At the receiver side of the DD system, a simple photodetector is employed to recover the transmitted electrical signals. At this stage ML algorithms can take place to identify the different modulation formats (i.e., MFI) and/or monitor optical signal performance (i.e., OPM). It is noteworthy to mention that before applying different ML methods, a feature extraction step is implemented to extract the most useful information from the received signals to ease the task of the ML algorithm, as shown in the inset of Figure 2.
2.1. Eye Diagrams
2.2. Asynchronous Amplitude Histograms (AAHs)
2.3. Asynchronous Delay Tap Plots (ADTP’s)
2.4. Other Methods
3. Overview of Machine Learning Paradigms
3.1. Shallow Learning
3.2. Deep Learning
4. Survey of Proposed Solutions for DD-OPM
4.1. Bird-Eye View
4.2. Shallow Learning Algorithms
4.2.1. Solutions Based on Support Vector Machine (SVM)
4.2.2. Solutions Based on Principle Component Analysis (PCA)
4.2.3. Solutions Based on Kernel Regression
4.3. Deep Learning Algorithms
4.3.1. Solutions Based on MLP Networks
4.3.2. Solutions Based on CNNs
4.3.3. Solutions Based on Fusion Networks
5. Survey Observations
5.1. Under-Developed Arguments for Algorithm Design
5.1.1. Arguments Supporting Shallow Learning
- Although it was proposed prior to the deep learning era, ref. [35] proposed an SVM algorithm for OPM, yet it does not compare it with any competing shallow learning algorithms. This makes the choice of SVM seem a bit arbitrary, which could raise some questions on the worthiness of the reported results.
- Both refs. [12,73] utilize SVM to perform OPM tasks, and both have been proposed in the heydays of deep learning. Nonetheless, none has provided a convincing argument—whether theoretical or empirical—for why SVM is favored over deep learning algorithms. Ref. [73] claims superiority for SVM over artificial neural networks and K-nearest neighbors (K-NNs), and it also claims scalability for SVM. However, these two claims need to be reconsidered; kernel-based SVM is a shallow learning algorithm, and it suffers the same drawbacks other kernel machines suffer; see refs. [58,92] for more information. Deep learning algorithms have been proposed as a solution for those drawbacks [55,58], which invalidates those claims.
- The solutions in refs. [38,75] are developed around PCA, which is an unsupervised learning algorithm for dimensionality reduction. It does not, per se, help tackle a regression of classification tasks, and this is why both solutions apply a K-nearest neighbor (K-NN) on top of PCA to perform the classification and regression tasks of interest. Neither paper presents a clear argument for why PCA is needed in the first place and why it is followed by K-NN and not other shallow learning algorithms—especially given the fact that K-NN typically requires more memory and processing at inference time than the likes of SVM [61] require. Furthermore, no comparison with deep learning algorithms is presented, considering deep learning was state-of-the-art at the time of publishing both solutions.
- No clear reasoning for the choice of kernel-based regression is presented in [44]. The solution requires careful selection of the kernel, which is not discussed in the paper. In addition, the paper does not have proper reasoning for why kernel-based regression is chosen over competing algorithms such as kernel SVM. This casts some doubt on the reported results, i.e., whether they are, at their time, the best one could hope for or not.
5.1.2. Argument for DNN Development
- Early proposed solutions with neural networks lack proper arguments for the choice of architecture. Neither of the papers [32,34,37,39,77] discuss how the architecture is developed. They, in general, provide a brief description of artificial neural networks and provide simple reasoning of why MLP networks are chosen. That is all well and good, but it does not explain how an architecture (i.e., the number of hidden layers and the breadths of each hidden layer) is developed.
- MLP networks have long been established as universal function approximators [96]. That means they theoretically have enough representational power to express the relation between any observed variables and targets. This is not fully utilized in [78]. The paper develops multiple networks to predict modulation format and OSNR, which could be done with one network, as the work in refs. [11,82] has shown.
- Multi-task learning is proposed in [11,49,82] as a way to develop more effective and computationally efficient solutions for MFI and OPM. They all try to motivate MLT from the perspective of the empirical evidence reported in [97], yet all arguments fall short of being well-rounded; the development process of the DNNs in all papers is not clearly described, especially the reasoning behind the choices of breadth, depth, and activation functions. Such a description could define the boundary line for whether the reported results of MTL are convincing or not compared with single-task learning. Furthermore, refs. [49,82] go beyond the inadequate development of their proposed DNN; they only rely on [97] to motivate MTL and present no comparison to single-task learning at all.
- Developing CNNs for MFI and OPM problems needs to be well motivated, for convolution could be considered a form of regularization [55], which typically restricts the representational capability of an algorithm (It is well established that regularization is a way to constrain the hypothesis space of a learning algorithm, which means it can represent a smaller number of functions. See refs. [55,61] for more information.). Some papers, such as [40,41,86,88] resort to insufficient or incomplete arguments to motivate the choice of CNNs. All argue that the 2-dimensional observed variables call for convolution. This is not entirely wrong, but it is insufficient; the underlying principle of CNNs is capturing and utilizing local structure in 2-dimensional signals [55], which is not clearly mentioned in those papers. Furthermore, some of the papers provide incomplete or mis-presented arguments for using CNNs. Some examples of that are:
- Machine learning algorithms such as artificial neural networks are claimed to have limited feature-extraction ability in ref. [88]. This is in contrary to the fact that MLP networks, a form of artificial neural networks, are proven to be universal approximators [96], and recent deep learning literature has shown them to be powerful in learning complex functions [54,55].
- In [41], the blurriness of deep feature maps (commonly called high-level features) is claimed to be a clue to their ability to represent abstract concepts. This is not wrong, but it is also not quite correct. Blurriness in itself is a byproduct of systematic downsampling in CNNs (i.e., pooling operations). It may indicate an increased level of abstraction, but such an observation has been brought forward in the context of computer vision, where the observed variables are image pixels. There is nothing to suggest that blurriness carries the same meaning for other applications as it does for computer vision.
- Finally, CNNs in ref. [86] are claimed to be the only type of neural networks capable of “automatic feature extraction”. However, this claim needs to be reconsidered, as all DNNs are capable of automatic feature extraction because they are developed around the idea of data-driven feature learning [55]. This is a competing idea to feature engineering that is intrinsic to classical machine learning.
5.2. Unclear Dataset Description and Training Procedure
5.2.1. Poor Dataset Construction and Description
- Uniform and coarse sampling of a continuous space generates biased datasets. This is the problem with several papers, especially when considering continuous variables (whether observed variables or targets) such as OSNR or CD. Many DD-OPM solutions attempt to predict OSNR, yet they do not provide a proper dataset; the OSNR space is typically sampled uniformly with a relatively large step. The datasets in refs. [9,40,41,73,84,87] all are good examples of that problem. They consider a wide OSNR space, from ∼10 to ∼30 dB, and sample it uniformly with a relatively large step, 1 or 2 dB. Such sampling results in a discrete set of OSNR values. This is misleading, as OSNR is a real-valued parameter, not discrete.
- Proposing a machine-learning-based solution requires a careful and clear description of the development dataset. Many publications do not distinguish between four important elements, namely experimental setup, data collection, dataset construction, and data pre-processing. Typically, experimental setup and data collection are described together—see ref. [94,98]—for they describe how the optical system is set up and how the data samples are collected. Dataset construction focus on the details of the development dataset—constructing pairs of observed variables and their target responses—such as how the raw data are processed, how the dataset is structured, and what the total number of data points is. Papers such as refs. [9,31,40,49,73,87] fail to provide such a clear distinction, and, hence, basic details such as the number of data points are missing.
5.2.2. Improper Loss Function and Missing Training Hyper-Parameters
- Monitoring the training and validation losses is instrumental to developing a machine learning algorithm. Some papers do not provide information on those two losses. This casts some doubt on the validity of the results and elicits questions about how well the algorithm learns from the dataset and how suitable the training hyper-parameters are to the task in hand. Papers such as refs. [11,47,80,84] all lack information on training and validation losses.
- Picking the right loss function must reflect how the monitoring or identification tasks are posed, from a machine learning perspective, of course. For instance, picking an MSE loss function encodes two facts about the machine learning task. The first one is explicit; the domain of the targets has a continuous nature, see ref. [61]. This simply means the vector of targets could live in a sub-space of any dimensionality. The other fact is implicit and rooted in the modeling of the relation between the observed variables and the targets; the conditional probability of the targets given the observed variables follows a Gaussian distribution—see [61] for more details. Keeping those two facts in mind, a classification task should not be addressed with an MSE loss function; the targets are discrete in nature, and, as a consequence, the conditional probability governing the relation between the targets and the observed variables cannot be Gaussian. Such an observation, i.e., using MSE loss for classification, has appeared a few times in the DD-OPM literature, ref. [78,88,89] to name three examples.
5.3. Lack of Benchmark Dataset and Evaluation Metrics
5.3.1. Lack of Benchmark Datasets
5.3.2. Lack of Common Performance Monitoring Metrics
6. Lessons Learned and Recommendation for Future Research
6.1. Carefully Choosing a Paradigm
- Dataset size: this is a crucial and practical point to consider when choosing a paradigm. Deep learning algorithms tend to have an extremely large number of parameters [55], in the order of millions. Therefore, a considerably large dataset is needed to train deep algorithms. How big the dataset should be is still an open-ended question in the field of deep learning and the realm of machine learning in general. What is known for sure at this point in time is that the size is problem- and algorithm-dependent. Nevertheless, given the empirical evidence observed in the fields of computer vision and natural language processing, it could be said that dataset sizes should be in the order of hundreds of thousands to millions of data points, see refs. [105,106], for instance. Typically, the larger the dataset is, the more reliable the results of a deep algorithm are [54]. Therefore, One might consider this the first criteria to choose between the two paradigms; the availability of a large number of data points makes deep learning a favorable choice.
- Computing resources: this is another crucial and practical point; when the number of parameters as well as the dataset size are large, special computing resources are needed, ones with enough memory and processing units. This is the usual requirement for deep algorithms [107], for they have a large number of parameters and require large datasets. A solution that needs to be implemented with limited resources is better developed with a shallow learning algorithm than with a deep one, for shallow algorithms tend to have a smaller number of parameters compared with deep algorithms.
6.2. Improved Solution Development
- Algorithm choice: picking a learning algorithm should first be justified by the requirements of the DD-OPM problem itself, the type of observed variables, and type of targets. A common consequence of that step is that a few learning algorithms could be found suitable, so those algorithms should be pitted against each other using the same development dataset. This provides enough empirical evidence to favor one algorithm over the others, and it helps build a clear reasoning for how the proposed solution comes together.
- Clear development methodology: it is crucial to clearly describe how an algorithm is trained and tested on a dataset. Many algorithms are developed based on a heuristic design approach, such as in the case of neural networks [55], and some algorithms assume a certain relation between the observed variables and targets, such as the conditional Gaussian distribution used in regression problems [61]. In all cases, clearly specifying the hyper-parameters and how the algorithm is trained helps others verify the results and test the developed solution on different problems.
- Benchmark datasets: this suggestion is the most important lesson in this paper; solutions that depend on machine learning are data-driven and developed empirically. Hence, having large, diverse, and open-source datasets available to the community makes the published results trustworthy for three reasons: (i) they are obtained from well-designed datasets representing specific optical communication setups; (ii) comparison of DD-OPM and MFI solutions can be conducted across research groups; and (iii) verification of published results is possible. Benchmark datasets are common practice in all research fields adopting machine learning, e.g., ImageNet in computer vision [105], ViWi in wireless communications [108], and GLEU in natural Language Understanding (NLU) [109], and it should be adopted by the optical communications community.
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
Abbreviations
Acronym | Definition |
AADTP | Adaptive Asynchronous Delay Tap Plot |
AADTS | Adaptive Asynchronous delay-tap sampling |
AH | Amplitude histograms |
AAH | Asynchronous amplitude histograms |
ACC | Accuracy |
ADTS | Asynchronous delay-tap sampling |
ADTP | Asynchronous Delay tap plot |
ANN | Artificial neural network |
ANN-AE | Artificial neural network Auto-encoder |
ASCS | Asynchronous single channel sampling |
ASE | Amplified spontaneous emission |
ASSA | asynchronously sampled signal amplitude |
BRI | Bit rate identification |
CD | Chromatic dispersion |
CNN | Convolutional Neural Network |
CORR | Correlation |
DD | Direct detection |
DD-OPM | Direct-Detection Optical Performance Monitoring |
DGD | Differential group delay |
DNN | Deep neural network |
DP | Dual polarization |
DPSK | Differential phase shift keying |
DSP | Digital signal processing |
DQPSK | Differential quadrature phase shift keying |
EM | Expectation-maximization |
FMF | Few-mode fiber |
FSO | Free-space optics |
GVD | Group velocity dispersion |
HOG | Histograms of Oriented Gradients |
ICA | Independent component analysis |
IM-DD | Intensity modulation-direct detection |
IQH | In-phase and quadrature histogram |
k-NN | k-nearest neighbor |
MAE | Mean absolute error |
MC | Mode coupling |
MFI | Modulation format identification |
ME | Mean error |
ML | Machine learning |
ML-ANN | Multi-layers artificial neural network |
MLP | Multi-layer perceptron |
M-PAM | M-ary pulse amplitude modulation |
M-PSK | M-ary phase shift keying |
M-QAM | M-ary quadrature phase shift |
MSE | Mean square error |
MTL | Multi-task learning |
NLU | Natural Language Understanding |
NRZ | Non-return to zero |
OADMs | Optical add-drop multiplexers |
OOK | On-Off keying |
OSA | optical spectrum analyzer |
OPM | Optical performance monitoring |
OPS | Optical power spectrum |
OSNR | Optical signal to noise ratio |
PAED | Parametric asynchronous eye diagram |
PCA | Principle component analysis |
PDL | Polarization dependent loss |
PMD | Polarization mode dispersion |
PN | Phase noise |
ResNet | Residual Network |
RL | Reinforcement learning |
RMS | Root-mean-square |
RMSE | Root mean square error |
RNN | Recurrent neural network |
RZ | Return to zero |
SE | Spectral efficiency |
SIFT | Scale-Invariant Feature Transform |
SMF | Single-mode fiber |
SPM | Self-phase modulation |
SVM | Support vector machine |
SVR | Support vector regression |
XPM | Cross-phase modulation |
References
- Statistics. Available online: https://www.itu.int/en/ITU-D/Statistics/Pages/stat/default.aspx (accessed on 31 January 2023).
- Liu, X.; Lun, H.; Fu, M.; Fan, Y.; Yi, L.; Hu, W.; Zhuge, Q. Ai-based modeling and monitoring techniques for future intelligent elastic optical networks. Appl. Sci. 2020, 10, 363. [Google Scholar] [CrossRef] [Green Version]
- Gerstel, O.; Jinno, M.; Lord, A.; Yoo, S.J. Elastic optical networking: A new dawn for the optical layer? IEEE Commun. Mag. 2012, 50, s12–s20. [Google Scholar] [CrossRef]
- Jinno, M. Elastic optical networking: Roles and benefits in beyond 100-gb/s era. J. Lightwave Technol. 2017, 35, 1116–1124. [Google Scholar] [CrossRef]
- Morais, R.M.; Pedro, J. Machine learning models for estimating quality of transmission in dwdm networks. J. Opt. Commun. Netw. 2018, 10, D84–D99. [Google Scholar] [CrossRef]
- Guesmi, L.; Menif, M. Method of joint bit rate/modulation format identification and optical performance monitoring using asynchronous delay-tap sampling for radio-over-fiber systems. Opt. Eng. 2016, 55, 084108. [Google Scholar] [CrossRef]
- Dong, Z.; Khan, F.N.; Sui, Q.; Zhong, K.; Lu, C.; Lau, A.P.T. Optical performance monitoring: A review of current and future technologies. J. Lightwave Technol. 2016, 34, 525–543. [Google Scholar] [CrossRef]
- Kikuchi, K. Fundamentals of coherent optical fiber communications. J. Lightwave Technol. 2016, 34, 157–179. [Google Scholar] [CrossRef]
- Luo, H.; Huang, Z.; Wu, X.; Yu, C. Cost-effective multi-parameter optical performance monitoring using multi-task deep learning with adaptive adtp and aah. J. Lightwave Technol. 2021, 39, 1733–1741. [Google Scholar] [CrossRef]
- Cheng, Y.; Zhang, W.; Fu, S.; Tang, M.; Liu, D. Transfer learning simplified multi-task deep neural network for pdm-64qam optical performance monitoring. Opt. Express 2020, 28, 7607–7617. [Google Scholar] [CrossRef]
- Wan, Z.; Yu, Z.; Shu, L.; Zhao, Y.; Zhang, H.; Xu, K. Intelligent optical performance monitor using multi-task learning based artificial neural network. Opt. Express 2019, 27, 11281–11291. [Google Scholar] [CrossRef] [Green Version]
- Wei, J.; Huang, Z.; Su, S.; Zuo, Z. Using multidimensional adtpe and svm for optical modulation real-time recognition. Entropy 2016, 18, 30. [Google Scholar] [CrossRef] [Green Version]
- Lee, J.H.; Choi, H.Y.; Shin, S.K.; Chung, Y.C. A review of the polarization-nulling technique for monitoring optical-signal-to-noise ratio in dynamic wdm networks. J. Lightwave Technol. 2006, 24, 4162–4171. [Google Scholar] [CrossRef]
- Khan, F.N.; Fan, Q.; Lu, C.; Lau, A.P.T. Machine learning methods for optical communication systems and networks. In Optical Fiber Telecommunications VII; Academic Press: Cambridge, MA, USA, 2019. [Google Scholar]
- Khan, F.; Fan, Q.; Lu, C.; Lau, A. An optical communication’s perspective on machine learning and its applications. J. Lightwave Technol. 2019, 37, 493–516. [Google Scholar] [CrossRef]
- Rafique, D.; Szyrkowiec, T.; Grieber, H.; Autenrieth, A.; Elbers, J.-P. Cognitive assurance architecture for optical network fault management. J. Lightwave Technol. 2018, 36, 1443–1450. [Google Scholar] [CrossRef]
- Furdek, M.; Natalino, C. Machine learning for optical network security management. In Proceedings of the 2020 Optical Fiber Communications Conference and Exhibition (OFC), San Diego, CA, USA, 8–12 March 2020; IEEE: Piscataway, NJ, USA, 2020; pp. 1–3. [Google Scholar]
- Kashi, A.S.; Zhuge, Q.; Cartledge, J.; Borowiec, A.; Charlton, D.; Laperle, C.; O’Sullivan, M. Artificial neural networks for fiber nonlinear noise estimation. In Proceedings of the 2017 Asia Communications and Photonics Conference (ACP), Guangzhou, China, 10–13 November 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 1–3. [Google Scholar]
- Zhuge, Q.; Zeng, X.; Lun, H.; Cai, M.; Liu, X.; Yi, L.; Hu, W. Application of machine learning in fiber nonlinearity modeling and monitoring for elastic optical networks. J. Lightwave Technol. 2019, 37, 3055–3063. [Google Scholar] [CrossRef]
- Lau, A.P.T.; Khan, F.N. Machine Learning for Future Fiber-Optic Communication Systems; Academic Press: Cambridge, MA, USA, 2022. [Google Scholar]
- Caballero, F.V.; Ives, D.; Zhuge, Q.; O’Sullivan, M.; Savory, S.J. Joint estimation of linear and non-linear signal-to-noise ratio based on neural networks. In Proceedings of the 2018 Optical Fiber Communications Conference and Exposition (OFC), San Diego, CA, USA, 11–15 March 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–3. [Google Scholar]
- Arano-Martinez, J.A.; Martinez-Gonzalez, C.L.; Salazar, M.I.; Torres-Torres, C. A Framework for Biosensors Assisted by Multiphoton Effects and Machine Learning. Biosensors 2022, 12, 710. [Google Scholar] [CrossRef]
- Alagappan, G.; Ong, J.R.; Yang, Z.; Ang, T.Y.L.; Zhao, W.; Jiang, Y.; Zhang, W.; Png, C.E. Leveraging AI in Photonics and Beyond. Photonics 2022, 9, 75. [Google Scholar] [CrossRef]
- Saif, W.S.; Esmail, M.A.; Ragheb, A.M.; Alshawi, T.A.; Alshebeili, S.A. Machine learning techniques for optical performance monitoring and modulation format identification: A survey. IEEE Commun. Surv. Tutor. 2020, 22, 2839–2882. [Google Scholar] [CrossRef]
- Khan, F.N.; Zhong, K.; Zhou, X.; Al-Arashi, W.H.; Yu, C.; Lu, C.; Lau, A.P.T. Joint osnr monitoring and modulation format identification in digital coherent receivers using deep neural networks. Opt. Express 2017, 25, 17767–17776. [Google Scholar] [CrossRef]
- Musumeci, F.; Rottondi, C.; Nag, A.; Macaluso, I.; Zibar, D.; Ruffini, M.; Tornatore, M. An overview on application of machine learning techniques in optical networks. IEEE Commun. Surv. Tutor. 2018, 21, 1383–1408. [Google Scholar] [CrossRef] [Green Version]
- Mata, J.; de Miguel, I.; Duran, R.J.; Merayo, N.; Singh, S.K.; Jukan, A.; Chamania, M. Artificial intelligence (AI) methods in optical networks: A comprehensive survey. Opt. Switch. Netw. 2018, 28, 43–57. [Google Scholar] [CrossRef]
- Zhang, J.; Jiang, W.; Zhou, J.; Zhao, X.; Huang, X.; Yu, Z.; Yi, X.; Qiu, K. An iterative BP-CNN decoder for optical fiber communication systems. Opt. Lett. 2023, 48, 2289–2292. [Google Scholar] [CrossRef] [PubMed]
- Esmail, M.A. Autonomous Self-Adaptive and Self-Aware Optical Wireless Communication Systems. Sensors 2023, 23, 4331. [Google Scholar] [CrossRef] [PubMed]
- Amirabadi, M.A. A survey on machine learning for optical communication [machine learning view]. arXiv 2019, arXiv:1909.05148. [Google Scholar]
- Esmail, M.A.; Saif, W.S.; Ragheb, A.M.; Alshebeili, S.A. Free space optic channel monitoring using machine learning. Opt. Express 2021, 29, 10967–10981. [Google Scholar] [CrossRef]
- Jargon, J.A.; Wu, X.; Willner, A.E. Optical performance monitoring using artificial neural networks trained with eye-diagram parameters. IEEE Photonics Technol. Lett. 2009, 21, 54–56. [Google Scholar] [CrossRef]
- Thrane, J.; Wass, J.; Piels, M.; Diniz, J.C.; Jones, R.; Zibar, D. Machine learning techniques for optical performance monitoring from directly detected pdm-qam signals. J. Lightwave Technol. 2016, 35, 868–875. [Google Scholar] [CrossRef] [Green Version]
- Wu, X.; Jargon, A.; Skoog, R.A.; Paraschis, L.; Willner, A.E. Applications of artificial neural networks in optical performance monitoring. J. Lightwave Technol. 2009, 27, 3580–3589. [Google Scholar]
- Skoog, R.A.; Banwell, T.C.; Gannett, J.W.; Habiby, S.F.; Pang, M.; Rauch, M.E.; Toliver, P. Automatic identification of impairments using support vector machine pattern classification on eye diagrams. IEEE Photonics Technol. Lett. 2006, 18, 2398–2400. [Google Scholar] [CrossRef]
- Ribeiro, V.; Lima, M.; Teixeira, A. Artificial neural networks in the scope of optical performance monitoring. In Proceedings of the 10th Portuguese Conference on Automatic Control, Funchal, Portugal, 16–18 July 2012. [Google Scholar]
- Jargon, J.A.; Wu, X.; Willner, A.E. Optical performance monitoring by use of artificial neural networks trained with parameters derived from delay-tap asynchronous sampling. In Proceedings of the 2009 Conference on Optical Fiber Communication, San Diego, CA, USA, 22–26 March 2009; IEEE: Piscataway, NJ, USA, 2009; pp. 1–3. [Google Scholar]
- Tan, M.C.; Khan, F.N.; Al-Arashi, W.H.; Zhou, Y.; Lau, A.P.T. Simultaneous optical performance monitoring and modulation format/bit-rate identification using principal component analysis. J. Opt. Commun. Netw. 2014, 6, 441–448. [Google Scholar] [CrossRef]
- Wu, X.; Jargon, J.A.; Paraschis, L.; Willner, A.E. Ann-based optical performance monitoring of qpsk signals using parameters derived from balanced-detected asynchronous diagrams. IEEE Photonics Technol. Lett. 2011, 23, 248–250. [Google Scholar] [CrossRef]
- Fan, X.; Xie, Y.; Ren, F.; Zhang, Y.; Huang, X.; Chen, W.; Zhangsun, T.; Wang, J. Joint optical performance monitoring and modulation format/bit-rate identification by cnn-based multi-task learning. IEEE Photonics J. 2018, 10, 1–12. [Google Scholar] [CrossRef]
- Fan, X.; Wang, L.; Ren, F.; Xie, Y.; Lu, X.; Zhang, Y.; Zhangsun, T.; Chen, W.; Wang, J. Feature fusion-based multi-task convnet for simultaneous optical performance monitoring and bit-rate/modulation format identification. IEEE Access 2019, 7, 126709–126719. [Google Scholar] [CrossRef]
- Yu, Y.; Zhang, B.; Yu, C. Optical signal to noise ratio monitoring using single channel sampling technique. Opt. Express 2014, 22, 6874–6880. [Google Scholar] [CrossRef]
- Fan, X.; Ren, F.; Zhang, J.; Zhang, Y.; Niu, J.; Wang, J. Reliable optical performance monitor: The combination of parallel framework and skip connected generative adversarial network. IEEE Access 2020, 8, 158391–158401. [Google Scholar] [CrossRef]
- Anderson, T.B.; Kowalczyk, A.; Clarke, K.; Dods, S.D.; Hewitt, D.; Li, J.C. Multi impairment monitoring for optical networks. J. Lightwave Technol. 2009, 27, 3729–3736. [Google Scholar] [CrossRef]
- Dods, S.D.; Anderson, T.B. Optical performance monitoring technique using delay tap asynchronous waveform sampling. In Proceedings of the Optical Fiber Communication Conference, Anaheim, CA, USA, 5–10 March 2006; Optical Society of America: Washington, DC, USA, 2006; p. OThP5. [Google Scholar]
- Chan, C.C. Optical Performance Monitoring: Advanced Techniques for Next-Generation Photonic Networks; Academic Press: Cambridge, MA, USA, 2010. [Google Scholar]
- Ribeiro, V.; Costa, L.; Lima, M.; Teixeira, A.L. Optical performance monitoring using the novel parametric asynchronous eye diagram. Opt. Express 2012, 20, 9851–9861. [Google Scholar] [CrossRef]
- Khan, F.N.; Shen, T.S.R.; Zhou, Y.; Lau, A.P.T.; Lu, C. Optical performance monitoring using artificial neural networks trained with empirical moments of asynchronously sampled signal amplitudes. IEEE Photonics Technol. Lett. 2012, 24, 982–984. [Google Scholar] [CrossRef]
- Zheng, H.; Li, W.; Mei, M.; Wang, Y.; Feng, Z.; Chen, Y.; Shao, W. Modulation format-independent optical performance monitoring technique insensitive to chromatic dispersion and polarization mode dispersion using a multi-task artificial neural network. Opt. Express 2020, 28, 32331–32341. [Google Scholar] [CrossRef]
- Wang, D.; Zhang, M.; Zhang, Z.; Li, J.; Gao, H.; Zhang, F.; Chen, X. Machine learning-based multifunctional optical spectrum analysis technique. IEEE Access 2019, 7, 19726–19737. [Google Scholar] [CrossRef]
- Chen, H.; Poon, A.W.; Cao, X.-R. Transparent monitoring of rise time using asynchronous amplitude histograms in optical transmission systems. J. Lightwave Technol. 2004, 22, 1661. [Google Scholar] [CrossRef]
- Anderson, T.; Clarke, K.; Beaman, D.; Ferra, H.; Birk, M.; Zhang, G.; Magill, P. Experimental demonstration of multi-impairment monitoring on a commercial 10 gbit/s nrz wdm channel. In Proceedings of the 2009 Conference on Optical Fiber Communication, San Diego, CA, USA, 22–26 March 2009; IEEE: Piscataway, NJ, USA, 2009; pp. 1–3. [Google Scholar]
- Khan, F.; Lau, A.P.T.; Lu, C.; Wai, P.K.A. Chromatic dispersion monitoring for multiple modulation formats and data rates using sideband optical filtering and asynchronous amplitude sampling technique. Opt. Express 2011, 19, 1007–1015. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Deng, L.; Yu, D. Deep learning: Methods and applications. Found. Trends Signal Process. 2014, 7, 197–387. [Google Scholar] [CrossRef] [Green Version]
- Goodfellow, I.; Bengio, Y.; Courville, A. Deep Learning; MIT Press: Cambridge, MA, USA, 2016; Available online: http://www.deeplearningbook.org (accessed on 20 March 2023).
- Alrabeiah, M. Deep Learning for Large-Scale Mimo: An Intelligent Wireless Communications Approach; Technical Report; Arizona State University: Tempe, AZ, USA, 2021. [Google Scholar]
- Bengio, Y.; LeCun, Y. Scaling learning algorithms towards AI. Large-Scale Kernel Mach. 2007, 34, 1–41. [Google Scholar]
- Bengio, Y. Learning deep architectures for AI. Found. Trends® Mach. Learn. 2009, 2, 1–127. [Google Scholar] [CrossRef]
- Lowe, D.G. Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 2004, 60, 91–110. [Google Scholar] [CrossRef]
- Dalal, N.; Triggs, B. Histograms of oriented gradients for human detection. In Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR’05), San Diego, CA, USA, 20–25 June 2005; Volume 1, pp. 886–893. [Google Scholar]
- Bishop, C.M.; Nasrabadi, N.M. Pattern Recognition and Machine Learning; Springer: New York, NY, USA, 2006; Volume 4. [Google Scholar]
- LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef]
- Zeiler, M.D.; Fergus, R. Visualizing and understanding convolutional networks. In Proceedings of the European Conference on Computer Vision, Zurich, Switzerland, 6–12 September 2014; Springer: Cham, Switzerland, 2014; pp. 818–833. [Google Scholar]
- He, K.; Zhang, X.; Ren, S.; Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 770–778. [Google Scholar]
- Vaswani, A.; Shazeer, N.; Parmar, N.; Uszkoreit, J.; Jones, L.; Gomez, A.N.; Kaiser, L.; Polosukhin, I. Attention is all you need. Adv. Neural Inf. Process. Syst. 2017, 30. Available online: https://proceedings.neurips.cc/paper_files/paper/2017 (accessed on 25 May 2023).
- Tan, M.; Pang, R.; Le, Q.V. Efficientdet: Scalable and efficient object detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020. [Google Scholar]
- Redmon, J.; Divvala, S.; Girshick, R.; Farhadi, A. You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 779–788. [Google Scholar]
- He, K.; Gkioxari, G.; Dollár, P.; Girshick, R. Mask r-cnn. In Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy, 22–29 October 2017; pp. 2961–2969. [Google Scholar]
- Chan, W.; Jaitly, N.; Le, Q.; Vinyals, O. Listen, attend and spell: A neural network for large vocabulary conversational speech recognition. In Proceedings of the 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Shanghai, China, 20–25 March 2016; IEEE: Piscataway, NJ, USA, 2016; pp. 4960–4964. [Google Scholar]
- Graves, A.; Jaitly, N. Towards end-to-end speech recognition with recurrent neural networks. In Proceedings of the International Conference on Machine Learning, Beijing, China, 21–26 June 2014; PMLR: London, UK, 2014; pp. 1764–1772. [Google Scholar]
- Hinton, G.E.; Salakhutdinov, R.R. Reducing the dimensionality of data with neural networks. Science 2006, 313, 504–507. [Google Scholar] [CrossRef] [Green Version]
- Hinton, G.E.; Osindero, S.; Teh, Y.-W. A fast learning algorithm for deep belief nets. Neural Comput. 2006, 18, 1527–1554. [Google Scholar] [CrossRef]
- Esmail, M.A. Optical wireless performance monitoring using asynchronous amplitude histograms. IEEE Photonics J. 2021, 13, 1–9. [Google Scholar] [CrossRef]
- Ji, T.; Peng, Y.; Zhu, G. In-band osnr monitoring from stokes parameters using support vector regression. IEEE Photonics Technol. Lett. 2019, 31, 385–388. [Google Scholar] [CrossRef]
- Khan, F.N.; Yu, Y.; Tan, M.C.; Al-Arashi, W.H.; Yu, C.; Lau, A.P.T.; Lu, C. Experimental demonstration of joint osnr monitoring and modulation format identification using asynchronous single channel sampling. Opt. Express 2015, 23, 30337–30346. [Google Scholar]
- He, P.; Liu, X.; Gao, J.; Chen, W. Deberta: Decoding-Enhanced Bert with Disentangled Attention. In Proceedings of the International Conference on Learning Representations, Virtual Event, Austria, 3–7 May 2021; Available online: https://openreview.net/forum?id=XPZIaotutsD (accessed on 3 June 2023).
- Jargon, J.A.; Wu, X.; Choi, H.Y.; Chung, Y.C.; Willner, A.E. Optical performance monitoring of qpsk data channels by use of neural networks trained with parameters derived from asynchronous constellation diagrams. Opt. Express 2010, 18, 4931–4938. [Google Scholar] [CrossRef]
- Zhang, Q.; Chen, J.; Zhou, H.; Zhang, J.; Liu, M. A simple artificial neural network based joint modulation format identification and osnr monitoring algorithm for elastic optical networks. In Proceedings of the 2018 Asia Communications and Photonics Conference (ACP), Hangzhou, China, 26–29 October 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–3. [Google Scholar]
- Saif, W.S.; Ragheb, A.M.; Esmail, M.A.; Marey, M.; Alshebeili, S.A. Machine learning based low-cost optical performance monitoring in mode division multiplexed optical networks. Photonics 2022, 9, 73. [Google Scholar] [CrossRef]
- Rai, P.; Kaushik, R. Artificial intelligence based optical performance monitoring. J. Opt. Commun. 2021. [Google Scholar] [CrossRef]
- Luo, H.; Huang, Z.; Du, X.; Yu, C. Effect of bandwidth of direct detection receiver on multiparameter optical performance monitoring. In Proceedings of the Real-time Photonic Measurements, Data Management, and Processing V, Online, China, 11–16 October 2020; International Society for Optics and Photonics: Washington, DC, USA, 2020; Volume 11555, p. 115550H. [Google Scholar]
- Cheng, Y.; Fu, S.; Tang, M.; Liu, D. Multi-task deep neural network (mt-dnn) enabled optical performance monitoring from directly detected pdm-qam signals. Opt. Express 2019, 27, 19062–19074. [Google Scholar] [CrossRef]
- Yang, S.; Yang, L.; Luo, F.; Wang, X.; Li, B.; Du, Y.; Liu, D. Multi-channel multi-task optical performance monitoring based multi-input multi-output deep learning and transfer learning for sdm. Opt. Commun. 2021, 495, 127110. [Google Scholar] [CrossRef]
- Mrozek, T.; Perlicki, K. Simultaneous monitoring of the values of cd, crosstalk and osnr phenomena in the physical layer of the optical network using cnn. Opt. Quantum Electron. 2021, 53, 1–16. [Google Scholar] [CrossRef]
- Du, J.; Yang, T.; Chen, X.; Chai, J.; Zhao, Y.; Shi, S. A cnn-based cost-effective modulation format identification scheme by low-bandwidth direct detecting and low rate sampling for elastic optical networks. Opt. Commun. 2020, 471, 126007. [Google Scholar] [CrossRef]
- Wang, D.; Wang, M.; Zhang, M.; Zhang, Z.; Yang, H.; Li, J.; Li, J.; Chen, X. Cost-effective and data size–adaptive opm at intermediated node using convolutional neural network-based image processor. Opt. Express 2019, 27, 9403–9419. [Google Scholar] [PubMed]
- Mrozek, T. Simultaneous monitoring of chromatic dispersion and optical signal to noise ratio in optical network using asynchronous delay tap sampling and convolutional neural network (deep learning). In Proceedings of the 2018 20th International Conference on Transparent Optical Networks (ICTON), Bucharest, Romania, 1–5 July 2018; IEEE: Piscataway, NJ, USA, 2018; pp. 1–4. [Google Scholar]
- Wang, D.; Zhang, M.; Li, Z.; Li, J.; Fu, M.; Cui, Y.; Chen, X. Modulation format recognition and osnr estimation using cnn-based deep learning. IEEE Photonics Technol. Lett. 2017, 29, 1667–1670. [Google Scholar] [CrossRef]
- Khan, F.N.; Zhou, Y.; Lau, A.P.T.; Lu, C. Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks. Opt. Express 2012, 20, 12422–12431. [Google Scholar] [CrossRef] [PubMed] [Green Version]
- Saif, W.S.; Ragheb, A.M.; Seleem, H.E.; Alshawi, T.A.; Alshebeili, S.A. Modulation format identification in mode division multiplexed optical networks. IEEE Access 2019, 7, 156207–156216. [Google Scholar] [CrossRef]
- Saif, W.S.; Ragheb, A.M.; Nebendahl, B.; Alshawi, T.; Marey, M.; Alshebeili, S.A. Performance investigation of modulation format identification in super-channel optical networks. IEEE Photonics J. 2022, 14, 1–10. [Google Scholar] [CrossRef]
- Bengio, Y.; Delalleau, O.; Roux, N. The curse of highly variable functions for local kernel machines. Adv. Neural Inf. Process. Syst. 2005, 18. Available online: https://proceedings.neurips.cc/paper/2005/hash/663772ea088360f95bac3dc7ffb841be-Abstract.html (accessed on 3 June 2023).
- Devlin, J.; Chang, M.-W.; Lee, K.; Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv 2018, arXiv:1810.04805. [Google Scholar]
- Alrabeiah, M.; Alkhateeb, A. Deep learning for mmwave beam and blockage prediction using sub-6 ghz channels. IEEE Trans. Commun. 2020, 68, 5504–5518. [Google Scholar] [CrossRef]
- Alrabeiah, M.; Hredzak, A.; Alkhateeb, A. Millimeter wave base stations with cameras: Vision-aided beam and blockage prediction. In Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 25–28 May 2020; pp. 1–5. [Google Scholar]
- Hornik, K.; Stinchcombe, M.; White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 1989, 2, 359–366. [Google Scholar] [CrossRef]
- Caruana, R. Multitask learning. Mach. Learn. 1997, 28, 41–75. [Google Scholar] [CrossRef]
- Wu, S.; Alrabeiah, M.; Chakrabarti, C.; Alkhateeb, A. Blockage prediction using wireless signatures: Deep learning enables real-world demonstration. IEEE Open J. Commun. Soc. 2022, 3, 776–796. [Google Scholar] [CrossRef]
- Alrabeiah, M.; Alkhateeb, A. Deep learning for TDD and FDD massive MIMO: Mapping channels in space and frequency. In Proceedings of the 2019 53rd Asilomar Conference on Signals, Systems, and Computers, Pacific Grove, CA, USA, 3–6 November 2019; pp. 1465–1470. [Google Scholar]
- Charan, G.; Alrabeiah, M.; Alkhateeb, A. Vision-aided 6g wireless communications: Blockage prediction and proactive handoff. IEEE Trans. Veh. Technol. 2021, 70, 10193–10208. [Google Scholar] [CrossRef]
- Balestriero, R.; Baraniuk, R.G. Mad max: Affine spline insights into deep learning. Proc. IEEE 2020, 109, 704–727. [Google Scholar] [CrossRef]
- Saxe, A.M.; Bansal, Y.; Dapello, J.; Advani, M.; Kolchinsky, A.; Tracey, B.D.; Cox, D.D. On the information bottleneck theory of deep learning. J. Stat. Mech. Theory Exp. 2019, 2019, 124020. [Google Scholar] [CrossRef]
- Amjad, R.A.; Geiger, B.C. Learning representations for neural network-based classification using the information bottleneck principle. IEEE Trans. Pattern Anal. Mach. Intell. 2020, 42, 2225–2239. [Google Scholar] [CrossRef] [Green Version]
- Kawaguchi, K.; Kaelbling, L.P.; Bengio, Y. Generalization in deep learning. arXiv 2017, arXiv:1710.05468. [Google Scholar]
- Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; et al. ImageNet Large Scale Visual Recognition Challenge. Int. J. Comput. Vis. (IJCV) 2015, 115, 211–252. [Google Scholar] [CrossRef] [Green Version]
- Lin, T.-Y.; Maire, M.; Belongie, S.; Hays, J.; Perona, P.; Ramanan, D.; Dollár, P.; Zitnick, C.L. Microsoft coco: Common objects in context. In Proceedings of the European Conference on Computer Vision, Zurich, Switzerland, 6–12 September 2014; Springer: Cham, Switzerland, 2014; pp. 740–755. [Google Scholar]
- Thompson, N.C.; Greenewald, K.; Lee, K.; Manso, G.F. The computational limits of deep learning. arXiv 2020, arXiv:2007.05558. [Google Scholar]
- Alrabeiah, M.; Hredzak, A.; Liu, Z.; Alkhateeb, A. Viwi: A deep learning dataset framework for vision-aided wireless communications. In Proceedings of the 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, 25–28 May 2020; pp. 1–5. [Google Scholar]
- Wang, A.; Singh, A.; Michael, J.; Hill, F.; Levy, O.; Bowman, S.R. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA, 6–9 May 2019; Available online: https://openreview.net/forum?id=rJ4km2R5t7 (accessed on 3 June 2023).
Feature Source | OSNR | PMD | CD | Non-Linearity | Crosstalk |
---|---|---|---|---|---|
Eye diagram | [32,33,34] | [32,34,35] | [33,35] | [33] | [35] |
AAH | [10,11,25,36] | ||||
ADTP and ASCS (phase portrait) | [37,38,39,40,41,42,43] | [37,38,39,40,41,43,44] | [37,38,39,40,41,43,44] | – | [45,46] |
PAED | [47] | [47] | [47] | – | – |
ASSA | [48] | [48] | [48] | – | – |
OPS | [49,50] | – | – | – | – |
ML Algorithm | Feature | SIM/EXP | Train:Test | Signal Format | Rate (Gb/s) | Impairment (Range) | Performance (Acc/CORR) | Year | Ref |
---|---|---|---|---|---|---|---|---|---|
SVM | Eye diagram (23 zernike moments) | Both | 164:17 | - | - | CD (-) PMD (-) DGD (-) XT (-) | ACC = 95% (SIM) ACC = 60% (EXP) | 2006 | [35] |
SVM | 176,000 AAHs | SIM | 70%:30% | NRZ-OOK | 10 | OSNR (5:25) PE, (0.3:3.3) V (500:1000 m) | ACC @PE&V ACC @OSNR | 2021 | [73] |
SVR | Stokes Space 420,175 sim | EXP | – | NRZ PDM-QPSK | 112 | OSNR (11:35) CD (0:700) | ACC = 0.9821 | 2019 | [74] |
Multiclass SVM | multi-dim ADTPE | SIM | 70%:30% | RZ-OOK NRZ-DPSK DUO RZ-DQPSK PM RZ-QPSK PM-NRZ-16QAM | 10 40 40 40 100 200 | OSNR (10:30) CD (0:4000) ps/nm DGD (0:10 ps) | Overall ACC = 99.05% Recog. time ms | 2016 | [12] |
SVM & CNN | AAH & ADTP | SIM | 70%:30% | NRZ-OOK NRZ-DPSK RZ-DPSK | 10 40 | OSNR (10:25) CD (0:700) | ACC = 98.46% Error @OSNR | 2021 | [31] |
PCA | 26,208 ADTP’s | SIM | 70:30 60:40 50:50 | RZ-OOK PDM-RZ-QPSK PDM-NRZ-16QAM | 10/20 40/100 100/200 | OSNR (14:28) CD (−500:500) DGD (0:10) | ME = 1.0 @OSNR ME = 4.0 @CD ME = 1.6 @DGD | 2014 | [38] |
PCA | 26,208 ADTP’s | SIM | 70:30 60:40 50:50 | RZ-OOK PDM-RZ-QPSK PDM-NRZ-16QAM | 10/20 40/100 100/200 | OSNR (14:28) CD (−500:500) DGD (0:10) Non-linearity | ME = 1.2 @OSNR ME = 12 @CD ME = 2.1 @DGD | 2014 | [38] |
PCA | ASCS 432 scatter plot | EXP | 70%:30% | NRZ-OOK NRZ-DPSK RZ-DPSK | 10 | OSNR (10:25) CD (0:700) | ACC = 98.46% Error @OSNR | 2015 | [75] |
Kernel ridge regression | ADTP (Phase portrait-900 features each) | SIM | 1200:500 | NRZ-DPSK | 40 | OSNR (13–26) CD (0–700) DGD (0–20) | RMSE = ± 11 @CD RMSE = ± 0.75 @DGD | 2009 | [44] |
Kernel ridge regression | ADTP (Phase portrait-900 features each) | EXP | 1500:500 | NRZ-DPSK | 40 | OSNR (15–25) CD (−400:400) DGD (0–22.5) | RMSE = ± 11 @CD RMSE = ± 1.9 @DGD | 2009 | [44] |
ML Algorithm | Feature | SIM/EXP | Train:Test | Signal Format | Rate (Gb/s) | Impairment (Range) | Performance (Acc/CORR) | Year | Ref |
---|---|---|---|---|---|---|---|---|---|
ANN(1;12) | Eye diagram (4 inputs) | SIM | - | NRZ-OOK RZ-DPSK | 10 40 | OSNR (16–32) CD (0–800) DGD (0–40) | CORR = 0.91 (@10G) CORR = 0.96 (@40G) | 2009 | [32] |
ANN(1;28) | ADTP (7 statistics) | SIM | 125:64 | NRZ-OOK | 10 | OSNR (16–32) CD (0–60) DGD (0–10) | CORR = 0.97 | 2009 | [37] |
ANN(1;28) | Constellation (7 statistics) | SIM | 216:125 | RZ-QPSK | 40 | OSNR (12–32) CD (0–200) DGD (0–20) | CORR = 0.987 RMSE = 0.77 @OSNR RMSE = 18.71@CD RMSE = 1.17 @DGD | 2010 | [77] |
ANN(1;12) | Eye diagram (4 inputs) | SIM | 125:64 | RZ-OOK RZ-DPSK | 40 | OSNR (16–32) CD (0–60) PMD (1.25–8.78) | CORR = 0.97, 0.96 RMSE = 0.57, 0.77 @OSNR RMSE = 4.68, 4.47 @CD RMSE = 1.53, 0.92 @PMD | 2009 | [34] |
ANN(1;12) | Eye diagram (4 inputs) | EXP | 20:12 | RZ-OOK RZ-DPSK | 40 | OSNR (16–32) CD (0–60) | CORR = 0.99, 0.99 RMSE = 0.58, 1.85 @OSNR RMSE = 2.53, 3.18 @CD | 2009 | [34] |
ANN(1;12) | Eye diagram (4 inputs) | SIM | 135:32 | RZ-DPSK (3ch WDM) | 40 | Opt Power (−5:3) OSNR (20–36) CD (0–40) PMD (0–8) | CORR = 0.97 RMSE = 0.46 @Power RMSE = 1.45 @OSNR RMSE = 3.98 @CD RMSE = 0.65 @PMD | 2009 | [34] |
ANN(1;42) | 3627 groups of moments per BR & MF | SIM | – | RZ-DQPSK RZ-DQPSK RZ-DPSK | 40 56 40 | OSNR (10:26) CD (−500:500) DGD (0:14) | RMSE = 0.1, 0.1, 0.1 @OSNR RMSE = 27.3, 29, 17 @CD RMSE = 0.94, 1.3, 1 @DGD | 2012 | [48] |
ANN(1;3) | Eye diagram (1 feature) | EXP | 1664:832 | PDM-64QAM | 32 | OSNR (4:30) | RMSE = 0.2 @OSNR (4–17) | 2016 | [33] |
ANN(1;12) | ADPT (7 features) | SIM/ EXP | 180:144 | QPSK with: -Balanced detection -Single-ended detection | 100 | OSNR (14:32) CD (0:50) DGD (0:10) | CORR = 0.995, 0.996 RMSE = 0.45, 1.62 @OSNR RMSE = 3.67, 8.75 @CD RMSE = 0.8, 7.02 @DGD | 2010 | [39] |
ANN(1;40) | Eye diagram (PAED- 24 features) | SIM | – | QPSK | 40 | OSNR (10:30) CD (0:200) PMD (0:25) | ME = 1.5:2 @OSNR ME = @CD ME = @PMD | 2012 | [47] |
ANN(5;40) | 5 features AHs | SIM | – | 4QAM, 16QAM 32QAM, 64QAM, 128QAM | - | OSNR (15:20) | Error @OSNR | 2018 | [78] |
ANN-AE | AAH & ADTH | SIM | 70%:30% | DP-QPSK | 10 | OSNR (8:20) CD (160:1120) MC | RMSE = 0.0015 @OSNR RMSE = 0.28 @CD RMSE = @MC | 2022 | [79] |
ANN | Eye diagram | SIM | 70%:30% | NRZ-OOK | 10 | OSNR (15:30) CD (0:2.5) DGD (0.1-0.5) | MSE = 4.6071 @OSNR MSE = 0.0417 @CD MSE = 1.6 @DGD | 2021 | [80] |
MTL-ANN (1,100,2,50) | AHs | SIM/ EXP | 9072:1008 4320:480 | NRZ-OOK PAM4 PAM8 | 28 | OSNR (10:25) OSNR (15:30) OSNR (20:35) | ME = 0.12 @SIM ME = 0.11 @EXP @CD (−100:100) | 2019 | [11] |
MT-DNN-TL (4,100,50,30,2) | AHs | EXP | 440:243 | PDM-16QAM PDM-64QAM | 10 | OSNR (14:24) OSNR (23:34) | RMSE = 1.9 @OSNR | 2020 | [10] |
MTL-ANN (64 neurons/layer) | 5 Feature per OSNR | EXP | 70:30 | NRZ-QPSK PDM-16QAM | 10 32 | OSNR (1:30) in WDM systems | RMSE = 0.48 MAE = 0.28 | 2020 | [49] |
MTL-DNN | AADTPs & AAHs 36,000 samples | SIM/ EXP | 70%:30% | QPSK 16QAM | 14/28 | OSNR (15:29) CD (0, 858.5, 1507.9) | ACC = 99.92% @MFI ACC = 99.11% @BRI ACC = 99.94% @CDI MAE @OSNR | 2020 | [81] |
MTL-DNN | AAH | SIM/ EXP | – | PDM-QPSK PDM-8QAM PDM-16QAM | 2.9/9.8 | OSNR (10:22) OSNR (14:24) OSNR (17:26) CD (0:1600) | ACC = 97.25% @MFI ACC = 100% @BRI RMSE = 0.58% @OSNR RMSE = 0.97% @CD | 2019 | [82] |
ML Algorithm | Number of Layers | Feature | SIM/EXP | Train:Test | Signal Format | Rate (Gb/s) | Impairment (Range) | Performance (Acc/CORR) | Year | Ref |
---|---|---|---|---|---|---|---|---|---|---|
MTL-CNN | 5 | Eye diagram 2500 diagrams | SIM/ EXP | 75%:25% | NRZ-OOK RZ-OOK PAM4 | 10 | OSNR (5:12) OSNR (7:12) OSNR (15:23) | RMSE @OSNR MFI ACC = 100% | 2021 | [83] |
CNN | – | ADTS 62,000 images | SIM | 90%:10% | NRZ-OOK DPSK | 10 | OSNR (10:30) CD (400:1600) | ACC = 99.9% @CD ACC = 95.6% @OSNR ACC = 99.3% @Crosstalk | 2021 | [84] |
CNN | 6 | AAH | SIM/ EXP | 70%:30% | PM-QPSK PM-16QAM PM-64QAM | 16 | OSNR (2:13) CD (0:16,000) | ACC = 100% | 2020 | [85] |
CNN | 6 | ADTP 12,985 sample | EXP | – | 16QAM 32QAM 64QAM | 28 | OSNR (15:30) OSNR (25:40) | ACC = 97.81% ACC = 96.56% | 2019 | [86] |
CNN | – | ADTS 10,000 images | SIM | 90%:10% | NRZ-OOK | 10 | OSNR (10:40) CD (0:2000) | ACC = < @CD ACC = < @OSNR | 2018 | [87] |
CNN | 5 | Eye diagram | EXP | 70%:30% | RZ-OOK NRZ-OOK RZ-DPSK 4PAM | - | OSNR (10:25) | ACC = 100% @OSNR ACC = 100% @MFI | 2017 | [88] |
MTL-CNN | 8 | 6600 ADTP’s | EXP | 5940:660 | RZ-QPSK NRZ-OOK NRZ-DPSK | 10/20 | OSNR (10:28) CD (0:450) DGD (0:10) | RMSE = 0.73 @OSNR RMSE = 1.34 @CD RMSE = 0.47 @DGD | 2018 | [40] |
MTL-CNN | 10 | 6600 ASCS | SIM | — | QPSK 16QAM 64QAM | 60/100 | OSNR (10:28) CD (0:450) DGD (0:10) | RMSE = 0.81 @OSNR RMSE = 1.52 @CD RMSE = 0.32 @GDG | 2019 | [41] |
MTL-DNN | 9 | 36,000 AADTPs & AAH’s each | EXP | 90%:10% | QPSK 16QAM | 14/28 | OSNR (10:24) OSNR (15:29) CDI (0, 858.5, 1508) | MAE = 0.2867 @OSNR MAE = 0.2867 @OSNR ACC = 99.83% @CD | 2021 | [9] |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Alrabeiah, M.; Ragheb, A.M.; Alshebeili, S.A.; Seleem, H.E. Survey on Applications of Machine Learning in Low-Cost Non-Coherent Optical Systems: Potentials, Challenges, and Perspective. Photonics 2023, 10, 655. https://doi.org/10.3390/photonics10060655
Alrabeiah M, Ragheb AM, Alshebeili SA, Seleem HE. Survey on Applications of Machine Learning in Low-Cost Non-Coherent Optical Systems: Potentials, Challenges, and Perspective. Photonics. 2023; 10(6):655. https://doi.org/10.3390/photonics10060655
Chicago/Turabian StyleAlrabeiah, Muhammad, Amr M. Ragheb, Saleh A. Alshebeili, and Hussein E. Seleem. 2023. "Survey on Applications of Machine Learning in Low-Cost Non-Coherent Optical Systems: Potentials, Challenges, and Perspective" Photonics 10, no. 6: 655. https://doi.org/10.3390/photonics10060655
APA StyleAlrabeiah, M., Ragheb, A. M., Alshebeili, S. A., & Seleem, H. E. (2023). Survey on Applications of Machine Learning in Low-Cost Non-Coherent Optical Systems: Potentials, Challenges, and Perspective. Photonics, 10(6), 655. https://doi.org/10.3390/photonics10060655