Networks are complex interacting systems involving cloud operations, core and metro transport, and mobile connectivity all the way to video streaming and similar user applications. With localized and highly engineered operational tools, it is typical of these networks to take days to weeks for any changes, upgrades, or service deployments to take effect. Machine learning, a sub-domain of artificial intelligence, is highly suitable for complex system representation. In this tutorial paper, we review several machine learning concepts tailored to the optical networking industry and discuss algorithm choices, data and model management strategies, and integration into existing network control and management tools. We then describe four networking case studies in detail, covering predictive maintenance, virtual network topology management, capacity optimization, and optical spectral analysis.

Metaheuristic algorithms have applicability in various fields where it is necessary to solve optimization problems. It has been a common practice in this field for several years to propose new algorithms that take inspiration from various natural and physical processes. The exponential increase of new algorithms is a controversial issue that several researchers have criticized. However, their efforts to point out multiple issues involved in these practices have been insufficient since the number of existing metaheuristics continues to increase yearly. To know the current state of this problem, this paper analyzes a sample of 111 recent studies where so-called new, hybrid, or improved optimization algorithms are proposed. Throughout the document, the topics reviewed will be addressed from a general perspective to their specific aspects. Among the study’s findings, it is observed that only 43% of the analyzed papers make some mention of the No Free Lunch (NFL) theorem, being this significant result ignored by most of the studies where new algorithms are presented. Of the analyzed studies, 65% present an improved version of some established algorithm, which reveals that the trend is no longer to propose metaheuristics based on new analogies. Additionally, a compilation of solutions found in engineering problems commonly used to verify the performance of state-of-the-art algorithms is presented. To demonstrate that algorithms with a low level of innovation can be erroneously considered as new frameworks for years, the metaheuristics known as Black Widow Optimization and Coral Reef Optimization are analyzed. The study of its components reveals that they do not have any innovation. Instead, they are just deficient mixtures of different evolutionary operators. This result applies by extension to their recently proposed improved versions.

The availability of coarse-resolution cost-effective Optical Spectrum Analyzers (OSA) allows its widespread deployment in operators’ networks. In this paper, we explore several machine learning approaches for soft-failure detection, identification and localization that take advantage of OSAs. In particular, we present three different solutions for the two most common filter-related soft-failures; filter shift and tight filtering which noticeably deform the expected shape of the optical spectrum. However, filter cascading is a key challenge as it affects the shape of the optical spectrum similarly to tight filtering; the approaches are specifically designed to avoid the misclassification of properly operating signals when normal filter cascading effects are present. The proposed solutions are: $i) multi-classifier$ approach, which uses features extracted directly from the optical spectrum, $ii) single-classifier$ approach, which uses pre-processed features to compensate for filter cascading, and $iii) residual-based$ approach, which uses a residual signal computed from subtracting the acquired single by OSAs from an expected signal synthetically generated. Extensive numerical results are ultimately presented to compare the performance of the proposed approaches in terms of accuracy and robustness.

In elastic optical networks (EONs), effective soft failure localization is of paramount importance to early detection of service level agreement violations while anticipating possible hard failure events. So far, failure localization techniques have been proposed and deployed mainly for hard failures, while significant work is still required to provide effective and automated solutions for soft failures, both during commissioning testing and in-operation phases. In this paper, we focus on soft failure localization in EONs by proposing two techniques for active monitoring during commissioning testing and for passive in-operation monitoring. The techniques rely on specifically designed low-cost optical testing channel (OTC) modules and on the widespread deployment of cost-effective optical spectrum analyzers (OSAs). The retrieved optical parameters are elaborated by machine learning-based algorithms running in the agent’s node and in the network controller. In particular, the Testing optIcal Switching at connection SetUp timE (TISSUE) algorithm is proposed to localize soft failures by elaborating the estimated bit-error rate (BER) values provided by the OTC module. In addition, the FailurE causE Localization for optIcal NetworkinG (FEELING) algorithm is proposed to localize failures affecting a lightpath using OSAs. Extensive simulation results are presented, showing the effectiveness of the TISSUE algorithm in properly exploiting OTC information to assess BER performance of quadrature-phase-shift-keying-modulated signals, and the high accuracy of the FEELING algorithm to correctly detect soft failures as laser drift, filter shift, and tight filtering.

In multi-domain elastic optical networks with alien wavelengths, each domain needs to consider intradomain and interdomain alien traffic to estimate and guarantee the required quality of transmission (QoT) for each lightpath and perform provisioning operations. This paper experimentally demonstrates an alien wavelength performance monitoring technique and machine-learning-aided QoT estimation for lightpath provisioning of intradomain/interdomain traffic. Testbed experiments demonstrate modulation format recognition, QoT monitoring, and cognitive routing for a 160 Gbaud alien multi-wavelength lightpath. By using experimental training datasets from the testbed and an artificial neural network, we demonstrated an accurate optical-signal-to-noise ratio prediction with an accuracy of $\sim 95\%$ when using 1200 data points.