Non-technological barriers: the last frontier towards AI-powered intelligent optical networks.

Machine learning (ML) has been remarkably successful in transforming numerous scientific and technological fields in recent years including computer vision, natural language processing, speech recognition, bioinformatics, etc. Naturally, it has long been considered as a promising mechanism to fundamentally revolutionize the existing archaic optical networks into next-generation smart and autonomous entities. However, despite its promise and extensive research conducted over the last decade, the ML paradigm has so far not been triumphant in achieving widespread adoption in commercial optical networks. In our perspective, this is primarily due to non-addressal of a number of critical non-technological issues surrounding ML-based solutions' development and use in real-world optical networks. The vision of intelligent and autonomous fiber-optic networks, powered by ML, will always remain a distant dream until these so far neglected factors are openly confronted by all relevant stakeholders and categorically resolved.

Convolutional-neural-network-based versus vision-transformer-based SNR estimation for visible light communication networks.

Visible light communication (VLC) has emerged as a promising technology for future sixth-generation (6 G) communications. Estimating and predicting the impairments, such as turbulence and free space signal scattering, can help to construct flexible and adaptive VLC networks. However, the monitoring of impairments of VLC is still in its infancy. In this Letter, we experimentally demonstrate a deep-neural-network-based signal-to-noise ratio (SNR) estimation scheme for VLC networks. A vision transformer (ViT) is first utilized and compared with the conventional scheme based on a convolutional neural network (CNN). Experimental results show that the ViT-based scheme exhibits robust performance in SNR estimation for VLC networks compared to the CNN-based scheme. Specifically, the ViT-based scheme can achieve accuracies of 76%, 63.33%, 45.33%, and 37.67% for 2-quadrature amplitude modulation (2QAM), 4QAM, 8QAM, and 16QAM, respectively, against 65%, 57.67%, 41.67%, and 34.33% for the CNN-based scheme. Additionally, data augmentation has been employed for achieving enhanced SNR estimation accuracies of 95%, 79.67%, 58.33%, and 50.33% for 2QAM, 4QAM, 8QAM, and 16QAM, respectively. The effect of the SNR step size of a contour stellar image dataset on the SNR estimation accuracy is also studied.

Application and comparison of active and transfer learning approaches for modulation format classification in visible light communication systems.

Automatic modulation classification (AMC) is a crucial part of adaptive modulation schemes for visible light communication (VLC) systems. However, most of the deep learning (DL) based AMC methods for VLC systems require a large amount of labeled training data which is quite difficult to obtain in practical systems. In this work, we introduce active learning (AL) and transfer learning (TL) approaches for AMC in VLC systems and experimentally analyze their performances. Experimental results show that the proposed novel AlexNet-AL and AlexNet-TL methods can significantly improve the classification accuracy with small sizes of training data. To be specific, using 60 labeled samples, AlexNet-AL and AlexNet-TL increase the classification accuracy by 6.82% and 14.6% compared to the result without AL and TL, respectively. Moreover, the use of data augmentation (DA) operation along with our proposed methods helps achieve further better performances.

Low-complexity carrier phase recovery based on principal component analysis for square-QAM modulation formats.

We propose, numerically analyze and experimentally demonstrate a low-complexity, modulation-order independent, non-data-aided (NDA), feed-forward carrier phase recovery (CPR) algorithm. The proposed algorithm enables synchronous decoding of arbitrary square-quadrature amplitude modulation (QAM) constellations and it is suitable for a realistic hardware implementation based on block-wise parallel processing. The proposed method is based on principal component analysis (PCA) and it outperforms the well-known and widely used blind phase search (BPS) algorithm at low signal-to-noise ratio (SNR) values, showing much lower cycle slip rate (CSR) both numerically and experimentally. For operation at higher SNR values, a hybrid two-stage implementation combining the proposed method and BPS is also proposed and their performance are investigated benchmarking them against the two-stage BPS (2S-BPS). The complexity of the proposed simple and hybrid methods are evaluated against 2S-BPS and computational complexity savings of 92% and 40% are expected for the simple and hybrid methods, respectively.

Temperature extraction in Brillouin optical time-domain analysis sensors using principal component analysis based pattern recognition.

We propose and experimentally demonstrate the use of principal component analysis (PCA) based pattern recognition to extract temperature distribution from the measured Brillouin gain spectra (BGSs) along the fiber under test (FUT) obtained by Brillouin optical time domain analysis (BOTDA) system. The proposed scheme employs a reference database consisting of relevant ideal BGSs with known temperature attributes. PCA is then applied to the BGSs in the reference database as well as to the measured BGSs so as to reduce their size by extracting their most significant features. Now, for each feature vector of the measured BGS, we determine its best match in the reference database comprised of numerous reduced-size feature vectors of the ideal BGSs. The known temperature attribute corresponding to the best-matched BGS in the reference database is then taken as the extracted temperature of the measured BGS. We analyzed the performance of PCA-based pattern recognition algorithm in detail and compared it with that of curve fitting method. The experimental results validate that the proposed technique can provide better accuracy, faster processing speed and larger noise tolerance for the measured BGSs. Therefore, the proposed PCA-based pattern recognition algorithm can be considered as an attractive method for extracting temperature distributions along the fiber in BOTDA sensors.

Joint OSNR monitoring and modulation format identification in digital coherent receivers using deep neural networks.

We experimentally demonstrate the use of deep neural networks (DNNs) in combination with signals' amplitude histograms (AHs) for simultaneous optical signal-to-noise ratio (OSNR) monitoring and modulation format identification (MFI) in digital coherent receivers. The proposed technique automatically extracts OSNR and modulation format dependent features of AHs, obtained after constant modulus algorithm (CMA) equalization, and exploits them for the joint estimation of these parameters. Experimental results for 112 Gbps polarization-multiplexed (PM) quadrature phase-shift keying (QPSK), 112 Gbps PM 16 quadrature amplitude modulation (16-QAM), and 240 Gbps PM 64-QAM signals demonstrate OSNR monitoring with mean estimation errors of 1.2 dB, 0.4 dB, and 1 dB, respectively. Similarly, the results for MFI show 100% identification accuracy for all three modulation formats. The proposed technique applies deep machine learning algorithms inside standard digital coherent receiver and does not require any additional hardware. Therefore, it is attractive for cost-effective multi-parameter estimation in next-generation elastic optical networks (EONs).

Experimental demonstration of joint OSNR monitoring and modulation format identification using asynchronous single channel sampling.

We experimentally demonstrate simultaneous optical signal-to-noise ratio (OSNR) monitoring and modulation format identification (MFI) in heterogeneous fiber-optic networks by using principal component analysis (PCA) and statistical distance measurement based pattern recognition on scatter plots obtained through asynchronous single channel sampling (ASCS). The proposed technique enables OSNR monitoring for several commonly-used modulation formats with mean OSNR estimation error of 1 dB and without requiring any information about the signal type during the online monitoring process. In addition, it successfully demonstrates the identification of unknown modulation formats of the received signals with an overall accuracy of 98.46%. The effects of chromatic dispersion (CD) on the performance of proposed technique are also analyzed. Due to the use of a single low-speed asynchronous sampling device in the proposed technique, the implementation complexity and cost of the monitoring devices can be significantly reduced.

Modulation format identification in heterogeneous fiber-optic networks using artificial neural networks.

We propose a simple and cost-effective technique for modulation format identification (MFI) in next-generation heterogeneous fiber-optic networks using an artificial neural network (ANN) trained with the features extracted from the asynchronous amplitude histograms (AAHs). Results of numerical simulations conducted for six different widely-used modulation formats at various data rates demonstrate that the proposed technique can effectively classify all these modulation formats with an overall estimation accuracy of 99.6% and also in the presence of various link impairments. The proposed technique employs extremely simple hardware and digital signal processing (DSP) to enable MFI and can also be applied for the identification of other modulation formats at different data rates without necessitating hardware changes.