Fiber-optic multi-band transmission (MBT) aims at exploiting the low-loss spectral windows of single-mode fibers (SMFs) for data transport, expanding by ~11 times the available bandwidth of C-band line systems and by ~5 times C+L-band line systems'. MBT offers a high potential for cost-efficient throughput upgrades of optical networks, even in absence of available dark-fibers, as it utilizes more efficiently the existing infrastructures. This represents the main advantage compared to approaches such as multi-mode/-core fibers or spatial division multiplexing. Furthermore, the industrial trend is clear: the first commercial C+L-band systems are entering the market and research has moved toward the neighboring S-band. This article discusses the potential and challenges of MBT covering the ITU-T optical bands O -> L. MBT performance is assessed by addressing the generalized SNR (GSNR) including both the linear and nonlinear fiber propagation effects. Nonlinear fiber propagation is taken into account by computing the generated nonlinear interference by using the generalized Gaussian-noise (GGN) model, which includes the interaction of nonlinear fiber propagation with stimulated Raman scattering (SRS), and in general considers wavelength-dependent fiber parameters. For linear effects, we hypothesize typical components' figures and discussion on components' limitations, such as transceivers', amplifiers' and filters' are not part of this work. We focus on assessing the transmission throughput that is realistic to achieve by using feasible multi-band components without specific optimizations and implementation discussion. So, results are meant to address the potential throughput scaling by turning-on excess fiber transmission bands. As transmission fiber, we focus exclusively on the ITU-T G.652.D, since it is the most widely deployed fiber type worldwide and the mostly suitable to multi-band transmission, thanks to its ultra-wide low-loss single-mode high-dispersion spectral region. Similar analyses could be carried out for other single-mode fiber types. We estimate a total single-fiber throughput of 450 Tb/s over a distance of 50 km and 220 Tb/s over regional distances of 600 km: ~10 times and 8 times more than C-band transmission respectively and ~2.5 times more than full C+L.

We present the results of the comparative performance-versus-complexity analysis for the several types of artificial neural networks (NNs) used for nonlinear channel equalization in coherent optical communication systems. The comparison is carried out using an experimental set-up with the transmission dominated by the Kerr nonlinearity and component imperfections. For the first time, we investigate the application to the channel equalization of the convolution layer (CNN) in combination with a bidirectional long short-term memory (biLSTM) layer and the design combining CNN with a multi-layer perceptron. Their performance is compared with the one delivered by the previously proposed NN-based equalizers: one biLSTM layer, three-dense-layer perceptron, and the echo state network. Importantly, all architectures have been initially optimized by a Bayesian optimizer. First, we present the general expressions for the computational complexity associated with each NN type; these are given in terms of real multiplications per symbol. We demonstrate that in the experimental system considered, the convolutional layer coupled with the biLSTM (CNN+biLSTM) provides the largest Q-factor improvement compared to the reference linear chromatic dispersion compensation (2.9 dB improvement). Then, we examine the trade-off between the computational complexity and performance of all equalizers and demonstrate that the CNN+biLSTM is the best option when the computational complexity is not constrained, while when we restrict the complexity to some lower levels, the three-layer perceptron provides the best performance.

Multi-band (MB) optical transmission promises to extend the lifetime of existing optical fibre infrastructures, which usually transmit within the C-band only, with C+L-band being also used in a few high-capacity links. In this work, we propose a physical-layer-aware provisioning scheme tailored for MB systems. This solution utilizes the physical layer information to estimate, by means of the generalized Gaussian noise (GGN) model, the generalized signal-to-noise ratio (GSNR). The GSNR is evaluated assuming transmission up to the entire low-loss spectrum of optical fiber, i.e., from 1260 nm to 1625 nm. We show that MB transmission may lead to a considerable reduction of the blocking probability, despite the increased trans- mission penalties resulting from using additional optical fiber transmission bands. Transponders supporting several modulation formats (polarization multiplexing quadrature phase shift keying _ PM-QPSK _, polarization multiplexing 8 quadrature amplitude modulation _ PM-8QAM _, and PM-16QAM) from O- to L- band are considered. An increase of the accommodated traffic with respect to the C-band transmission only case, ranging from about four times with S+C+L-band and up to more than six times when transmitting from E to L-band is reported.

Experimental results based on offline processing reported at optical conferences increasingly rely on neural network-based equalizers for accurate data recovery. However, achieving low-complexity implementations that are efficient for real-time digital signal processing remains a challenge. This paper addresses this critical need by proposing a systematic approach to designing and evaluating low-complexity neural network equalizers. Our approach focuses on three key phases: training, inference, and hardware synthesis. We provide a comprehensive review of existing methods for reducing complexity in each phase, enabling informed choices during design. For the training and inference phases, we introduce a novel methodology for quantifying complexity. This includes new metrics that bridge software-to-hardware considerations, revealing the relationship between complexity and specific neural network architectures and hyperparameters. We guide the calculation of these metrics for both feed-forward and recurrent layers, highlighting the appropriate choice depending on the application's focus (software or hardware). Finally, to demonstrate the practical benefits of our approach, we showcase how the computational complexity of neural network equalizers can be significantly reduced and measured for both teacher (biLSTM+CNN) and student (1D-CNN) architectures in different scenarios. This work aims to standardize the estimation and optimization of computational complexity for neural networks applied to real-time digital signal processing, paving the way for more efficient and deployable optical communication systems.

This paper performs a detailed, multi-faceted analysis of key challenges and common design caveats related to the development of efficient neural networks (NN) based nonlinear channel equalizers in coherent optical communication systems. The goal of this study is to guide researchers and engineers working in this field. We start by clarifying the metrics used to evaluate the equalizers’ performance, relating them to the loss functions employed in the training of the NN equalizers. The relationships between the channel propagation model’s accuracy and the performance of the equalizers are addressed and quantified. Next, we assess the impact of the order of the pseudo-random bit sequence used to generate the – numerical and experimental – data as well as of the DAC memory limitations on the operation of the NN equalizers both during the training and validation phases. Finally, we examine the critical issues of overfitting limitations, the difference between using classification instead of regression, and batch-size-related peculiarities. We conclude by providing analytical expressions for the equalizers’ complexity evaluation in the digital signal processing (DSP) terms and relate the metrics to the processing latency.

Nonlinearity compensation is considered as a key enabler to increase channel transmission rates in the installed optical communication systems. Recently, data-driven approaches — motivated by modern machine learning techniques — have been proposed for optical communications in place of traditional model-based counterparts. In particular, the application of neural networks (NN) allows improving the performance of complex modern fiber-optic systems without relying on any a priori knowledge of their specific parameters. In this work, we introduce a novel design of complex-valued NN for optical systems and examine its performance in standard single mode fiber (SSMF) and large effective-area fiber (LEAF) links operating in relatively high nonlinear regime. First, we present a methodology to design a new type of NN based on the assumption that the channel model is more accurate in the nonlinear regime. Second, we implement a Bayesian optimizer to jointly adapt the size of the NN and its number of input taps depending on the different fiber properties and total length. Finally, the proposed NN is numerically and experimentally validated showing an improvement of 1.7 dB in the linear regime, 2.04 dB at the optimal optical power and 2.61 at the max available power on Q-factor when transmitting a WDM 30×200G DP-16QAM signal over a 620 km SSMF legacy link. The results highlight that the NN is able to mitigate not only part of the nonlinear impairments caused by optical fiber propagation but also imperfections resulting from using low-cost legacy transceiver components, such as digital-to-analog converter (DAC) and Mach-Zehnder modulator.