Search

Introducing a novel approach for assessing connectivity in dynamic optical networks, we propose the quantum-driven particle swarm-optimized self-adaptive support vector machine (QPSO-SASVM) model. By integrating quantum computing and machine learning, this advanced framework offers enhanced convergence and robustness. Tested against a network simulation with 187 nodes and 96 DWDM channels, QPSO-SASVM outperforms traditional benchmarks such as LSTM, Naive method, E-DLSTM, and GRU. Evaluation using metrics such as signal-to-noise ratio, ROC curve, RMSE, and R2 consistently demonstrates superior predictive accuracy and adaptability. These results underscore QPSO-SASVM as a powerful tool for precise and reliable prediction in dynamic optical network environments. [ABSTRACT FROM AUTHOR]

The integration of communication and sensing (ICAS) in optical networks is an inevitable trend in building intelligent, multi-scenario, application-converged communication systems. However, due to the impact of nonlinear effects, co-fiber transmission of sensing signals and communication signals can cause interference to the communication signals, leading to an increased bit error rate (BER). This paper proposes a noncoherent solution based on the alternate polarization chirped return-to-zero frequency shift keying (Apol-CRZ-FSK) modulation format to realize a 4 × 100 Gbps dense wavelength division multiplexing (DWDM) optical network. Simulation results show that compared to traditional modulation formats, such as chirped return-to-zero frequency shift keying (CRZ-FSK) and differential quadrature phase shift keying (DQPSK), this solution demonstrates superior resistance to nonlinear effects, enabling longer transmission distances and better transmission performance. Moreover, to meet the transmission requirements and signal sensing and recognition needs in future optical networks, this study employs the Inception-ResNet-v2 convolutional neural network model to identify three modulation formats. Compared with six deep learning methods including AlexNet, ResNet50, GoogleNet, SqueezeNet, Inception-v4, and Xception, it achieves the highest performance. This research provides a low-cost, low-complexity, and high-performance solution for signal transmission and signal recognition in high-speed optical networks designed for integrated communication and sensing. [ABSTRACT FROM AUTHOR]

In optical networks, designing optical orthogonal codes (OOCs) with appropriate parameters is essential for enhancing the overall system performance. They are divided into two categories, constant-weight OOCs (CW-OOCs) and variable-weight OOCs (VW-OOCs), based on the number of distinct Hamming weights present in their codewords. This paper introduces a method for constructing VW-OOCs of length k p by using the structure of an integer ring and the Chinese Remainder Theorem. In particular, we present some specific VW-OOCs with weights of 3, 4, or 5. The results demonstrate that certain optimal VW-OOCs can be obtained with parameters that are not covered in the existing literature. [ABSTRACT FROM AUTHOR]

Optical packet switching has gained lot of momentum in last decade due to the advantages of optical fiber over copper cables. Optical switching is beneficial in optical networks which form connections of links and switching nodes. In these high speed networks minimum delay and high throughput are two important parameters which are considered. To minimize network delay shortest path algorithm is used for route selections. In previous studies while choosing shortest path distance among various nodes is considered. In this work we have shown that it is necessary to consider both distance and number of hops while choosing path from source to destination to minimize power per bit used for the transmission. [ABSTRACT FROM AUTHOR]

Current trends in network traffic management rely on the efficient control of individual flows. Software-defined networking popularized this notion. Per-flow management is perfectly viable in standard IP networks, in which packet processing is in the electric domain. However, optical networks provide more restrictions and constraints making per-flow traffic management difficult. One of the most important challenges is to reduce the concurrent number of flows present in the flow tables to make the switching process quicker. In this paper, we propose a mechanism to manage flow timeout values that uses idle timeout and hard timeout parameters. To calculate the appropriate values of the parameters, the mechanism analyzes the packet inter-arrival times. The algorithm also takes into account the current occupancy of the flow table. [ABSTRACT FROM AUTHOR]

We present the use of interconnected optical mesh networks for early earthquake detection and localization, exploiting the existing terrestrial fiber infrastructure. Employing a waveplate model, we integrate real ground displacement data from seven earthquakes with magnitudes ranging from four to six to simulate the strains within fiber cables and collect a large set of light polarization evolution data. These simulations help to enhance a machine learning model that is trained and validated to detect primary wave arrivals that precede earthquakes' destructive surface waves. The validation results show that the model achieves over 95% accuracy. The machine learning model is then tested against an M4.3 earthquake, exploiting three interconnected mesh networks as a smart sensing grid. Each network is equipped with a sensing fiber placed to correspond with three distinct seismic stations. The objective is to confirm earthquake detection across the interconnected networks, localize the epicenter coordinates via a triangulation method and calculate the fiber-to-epicenter distance. This setup allows early warning generation for municipalities close to the epicenter location, progressing to those further away. The model testing shows a 98% accuracy in detecting primary waves and a one second detection time, affording nearby areas 21 s to take countermeasures, which extends to 57 s in more distant areas. [ABSTRACT FROM AUTHOR]

【Objective】Natural disasters such as earthquakes have the characteristics of persistence and wide range. During the occurrence of disasters, the link resources of the optical network will be continuously damaged, resulting in the constant change of the link risk. In the face of constantly changing link risks, improper service recovery planning may cause service failures. From a service perspective, repeated faults will interrupt data transmission many times, and the subsequent link status damage may be aggravated after a disaster occurs. From the perspective of network management and control, repeated recovery wastes route calculation resources and occupies the recovery resources of other services. At the same time, different services have different requirements for transmission reliability because of the importance of the data to be transmitted. When a fault occurs, the high-importance services should be recovered first. Therefore, in the scenario of a large-scale persistent disaster, it is a problem worth studying to comprehensively consider the sustained impact of the disaster on link risk and the difference in path reliability requirements of different services for service recovery. To solve this problem, this paper proposes a link risk-aware service recovery algorithm-Dynamic Link Risk Reroute Algorithm (DLRRA) under persistent disasters.【Methods】Firstly, according to the service importance and link risk, we establish the service importance evaluation model and link risk evaluation model. Then we propose the optimization target route reliability. The DLRRA, combined with the optimization objective, fully considers the change of link risk degree caused by the impact of disasters on the continuity of links. By preferentially allocating low-risk recovery resources to the fault services of high importance, the risk of secondary failure of the same high-importance services is avoided during the continuous occurrence of disasters.【Results】The simulation results show that the second failure probability of DLRRA recovery is reduced by 11% compared with the traditional algorithm, and the average importance of DLRRA recovery under the high load is increased by 10%.【Conclusion】Therefore, the algorithm effectively avoids the loss caused by multiple service interruptions caused, and ensures the continuous and stable operation of important services in the disaster environment.

Optical backbone networks, characterized by using optical fibers as a transmission medium, constitute the fundamental infrastructure employed today by network operators to deliver services to users. As network capacity is one of the key factors influencing optical network performance, it is important to comprehend its limitations and have the capability to estimate its value. In this context, we revisit the concept of capacity from various perspectives, including channel capacity, link capacity, and network capacity, thus providing an integrated view of the problem within the framework of the backbone tier. Hence, we review the fundamental concepts behind optical networks, along with the basic physical phenomena present in optical fiber transmission, and provide methodologies for estimating the different types of capacities, mainly using simple formulations. In particular, we propose a method to evaluate the network capacity that relies on the optical reach to account for physical layer aspects, in conjunction with capacitated routing techniques for traffic routing. We apply this method to three reference networks and obtain capacities ranging from tens to hundreds of terabits/s. Whenever possible, we also compare our results with published experimental data to understand how they relate.

Optical backbone networks constitute the fundamental infrastructure employed today by network operators to deliver services to users. As network capacity is a key factor influencing optical network performance, it is important to understand how topological and physical properties impact its behavior and to have the capability to estimate its value. In this context, we propose here a method to evaluate the network capacity that relies on the optical reach to account for physical layer aspects in conjunction with constrained routing techniques for traffic routing. As this type of routing can lead to traffic blocking, particularly due to the limitation on the number of wavelengths per fiber, we also propose a fiber assignment algorithm designed to deal with this problem. We apply this method to a set of randomly generated networks using a modified Waxman model, and for a network with 60 nodes, in a scenario without blocking, we obtain capacities of about 2.5 Pbit/s for a symbol rate of 64 Gbaud and about 5 Pbit/s for a symbol rate of 128 Gbaud. Remarkably, this duplication in the total network capacity is achieved by an increase in the total fiber length of only about 51%. [ABSTRACT FROM AUTHOR]

Due to the advancement of high definition, 5G technologies, the Internet of Things, and Artificial Intelligence, the demand for optical networks has increased widely. Optical communication networks offer various metrics, including high transmission capacity, efficient anti-interference, minimum transmission loss and robustness, and so on, that offer opportunities for communication networks. To satisfy the optical network demands, effective network resource utilization is essential. Therefore, developing a tool with improved Quality of Transmission (QoT) accuracy in optical networks is necessary. Recently, Artificial intelligence (AI) approaches have provided various opportunities to resolve these issues and the deep learning (DL) algorithms offer improved performance over the conventional methods. This paper developed a novel DL-based cognitive QoT prediction model for Quantum optical communication networks. This proposed model predicts the QoT for the QoS (Quality of Service) setup using the DL model with the transmission computation. The proposed model utilized an optimized DL model called CNN-LSTM for the prediction process using the signal and link characteristics as input features. The DL model is trained using the transmission equations. The hyperparameters of the neural network are optimized using frog leap optimization to improve the predictive performance. The experimental results highlight the enhanced and improved version of the proposed model, and the results are compared with the conventional systems in terms of performance measures. [ABSTRACT FROM AUTHOR]

Telemedicine networks have seen significant changes in their capacity, monitoring, management, and control framework during the previous decades. The evolution of network capacity, control, and management for Unmanned Aerial Vehicle (UAV) & Software-Defined Networks (SDN) as support to telemedicine, artificial intelligence in telemedicine networks, and capabilities in designing a telemedicine network with respect to its performance and customization is presented in this study, with a historical history and a future view. The first section of the article goes over the history of traffic and capacity expansion, as well as future projections. By introducing a medical and image data communication protocol for telemedicine, the second section examines the technological constraints of expanding capacity in the era of UAV & softwaredefined networking. The third section discusses ways to maximize network capacity by considering quality of service (QoS) capacity issues. Finally, the article explores how to construct a telemedicine network that can provide performance, customization, and capabilities to keep up with increased traffic in the coming decades. Research gaps and future directions were presented in the last section [ABSTRACT FROM AUTHOR]

Optical backbone networks, characterized by using optical fibers as a transmission medium, constitute the fundamental infrastructure employed today by network operators to deliver services to users. As network capacity is one of the key factors influencing optical network performance, it is important to comprehend its limitations and have the capability to estimate its value. In this context, we revisit the concept of capacity from various perspectives, including channel capacity, link capacity, and network capacity, thus providing an integrated view of the problem within the framework of the backbone tier. Hence, we review the fundamental concepts behind optical networks, along with the basic physical phenomena present in optical fiber transmission, and provide methodologies for estimating the different types of capacities, mainly using simple formulations. In particular, we propose a method to evaluate the network capacity that relies on the optical reach to account for physical layer aspects, in conjunction with capacitated routing techniques for traffic routing. We apply this method to three reference networks and obtain capacities ranging from tens to hundreds of terabits/s. Whenever possible, we also compare our results with published experimental data to understand how they relate. [ABSTRACT FROM AUTHOR]

The all‐optical diffractive deep neural networks (D2NNs) framework as a hardware platform is demonstrated to implement various advanced functional meta‐devices with high parallelism and high processing speed. However, the design methodology merging trainable polarization modulation neurons into the D2NNs, which potentially possess higher integration and more task‐loading capacity, is not yet fully explored. Here, the matrix diffractive deep neural networks (M‐D2NNs) are proposed to deploy polarization‐sensitive Jones matrix metasurfaces into the all‐optical polarization multiplexing networks to perform sophisticated inference tasks as well as inverse designs for advanced functional meta‐devices. Three polarization multiplexing meta‐devices with advanced functionalities are implemented by the M‐D2NNs, that is, high task‐capacity integration classification, non‐interleaved high‐efficiency Jones matrix eight‐channel regulation, and custom‐polarization information cryptographic multiplexing. The M‐D2NNs are demonstrated to provide a new strategy to merge polarization into electromagnetic and optical field modulators by Jones matrix metasurfaces, which may drive the evolution of all‐optical networks toward multi‐task integration and more advanced functional devices. [ABSTRACT FROM AUTHOR]

The evolution of Internet and communication systems is exponentially increasing the complexity in communication networks. This paved the way for the incorporation of artificial intelligence (AI), machine learning (ML), and recently deep learning (DL), in various aspects so as to improve the intelligence in communication networks. As DL techniques are superior on finding solutions to complex problems, they are been utilized for optical network applications. This paper aims to review the progress of AI in optical communication and the advancements from ML to DL. The paper also presents a review of nine research papers that utilized conventional DL techniques along with their contribution in optical and wavelength division multiplexing (WDM) networks. Toward the end of this paper, the DL algorithm is studied and its performance parameters are compared to evaluate the simulation outputs of its variants. The comparative analysis shows that in future, improvements in the outputs of WDMs can be made by applying DL-based algorithms. [ABSTRACT FROM AUTHOR]

Conventional optical networks are limited by static operational methods that hinder their scalability and effectiveness. As networks operate with reduced margins to maximize resource utilization, the risk of hard failures increases, necessitating efficient failure prediction systems and accurate quality of transmission (QoT) estimation. Effective management requires the detection of soft failures, accurate bit error rate (BER) predictions, and dynamic network operations to maintain minimal margins. Machine learning (ML) offers promising solutions for automating these tasks, significantly enhancing failure management and network reliability. This article provides an extensive overview of ML techniques applied to optical networks, specifically focusing on failure management. The key ML techniques discussed include network kriging (NK) for performance estimation and failure localization, support vector machine (SVM) for classification tasks, convolutional neural networks (CNNs) for signal analysis and soft failure identification, and generative adversarial networks (GANs) for synthetic data generation and soft failure detection. It also explores the application of artificial neural networks (ANNs), autoencoders (AEs), Gaussian process (GP), long short-term memory (LSTM), and gated recurrent units (GRUs) in optical networks. This study surveys ML techniques for early-warning and failure prediction, failure detection, identification, localization, magnitude estimation, and soft failure detection and prediction. Emphasizing automation, it discusses how ML algorithms can streamline failure management processes, reducing manual intervention and service disruptions. The potential of large language models (LLMs) and digital twins (DTs) for further advancements in automating failure management, optimizing performance, and network optimization in optical networks is also examined. LLMs significantly advance network management by improving network design, diagnosis, security, and autonomous optimization through the integration of comprehensive domain resources and intelligent agents. These advancements are paving the way towards achieving artificial general intelligence and fully automated optical network management.

Humankind has entered a new era wherein a main characteristic is the convergence of various technologies providing services and exerting a major impact upon all aspects of human activity, be it social interactions with the natural environment. Fixed networks are about to play a major role in this convergence, since they form, along with mobile networks, the backbone that provides access to a broad gamut of services, accessible from any point of the globe. It is for this reason that we introduce a forward-looking approach for fixed networks, particularly focused on Fixed 6th Generation (F6G) networks. First, we adopt a novel classification scheme for the main F6G services, comprising six categories. This classification is based on the key service requirements, namely latency, capacity, and connectivity. F6G networks differ from those of previous generations (F1G–F5G) in that they concurrently support multiple key requirements. We then propose concrete steps towards transforming the main elements of fixed networks, such as optical transceivers, optical switches, etc., such that they satisfy the new F6G service requirements. Our study categorizes the main networking paradigm of optical switching into two categories, namely ultra-fast and ultra-high capacity switching, tailored to different service categories. With regard to the transceiver physical layer, we propose (a) the use of all-optical processing to mitigate performance barriers of analog-to-digital and digital-to-analog converters (ADC/DAC) and (b) the exploitation of optical multi-band transmission, space division-multiplexing, and the adoption of more efficient modulation formats.

In optical networks, increasing longevity is of critical importance. This article describes a cutting-edge routing protocol based on Q-learning techniques that have been meticulously constructed to extend the lifetime of optical networks by enhancing energy effectiveness and throughput. The protocol dynamically manages energy usage using Q-learning, a reinforcement learning approach. The primary objective is to choose routing algorithms that optimize long-term revenues for individual nodes while increasing energy efficiency. In a detailed study, the protocol's performance is compared to that of well-known rivals such as Low-Energy Adaptive Clustering Hierarchy (LEACH), Multi-Hop Low-Energy Adaptive Clustering Hierarchy (M-LEACH), and Balanced Low-Energy Adaptive Clustering Hierarchy (B-LEACH) (B-LEACH). The evaluation considers several factors, including network durability as measured by active/inactive node ratios, energy efficiency as measured by per-round energy consumption, quality of service as measured by throughput per round, and scalability as measured over networks with 40, 70, and 100 nodes. The complete examination for each network configuration spans over 5,000 cycles. M-LEACH outperforms LEACH and B-LEACH in all performance measures in the simulation results test, establishing a new benchmark. It is fascinating to compare the performance of the unique Q-learning-based protocol to that of LEACH, M-LEACH, and B-LEACH. Regarding network durability, energy efficiency, quality of service, and scalability, the proposed protocol outperforms. [ABSTRACT FROM AUTHOR]

This article addresses the 2‐edge‐connected minimum branch vertices problem, a variant of the minimum branch vertices problem in which the spanning subgraph is required to be 2‐edge‐connected for survivability reasons. The problem has been recently introduced and finds application in optical networks design scenarios, where branch vertices are associated to switch devices that allow to split the entering light signals and send them to several adjacent vertices. An exact approach to the problem has been proposed in the literature. In this paper, we formally prove its NP‐completeness and propose a genetic algorithm, which exploits some literature‐provided procedures for efficiently checking and restoring solutions feasibility, and makes use of novel ad‐hoc designed operators aiming to improve their values, reducing the number of branch vertices. The computational tests show that, on the benchmark instances, the genetic algorithm very often finds the optimal solution. Moreover, in order to further investigate the effectiveness and the performance of our algorithm, we generated a new set of random instances where the optimal solution is known a priori. [ABSTRACT FROM AUTHOR]

Humankind has entered a new era wherein a main characteristic is the convergence of various technologies providing services and exerting a major impact upon all aspects of human activity, be it social interactions with the natural environment. Fixed networks are about to play a major role in this convergence, since they form, along with mobile networks, the backbone that provides access to a broad gamut of services, accessible from any point of the globe. It is for this reason that we introduce a forward-looking approach for fixed networks, particularly focused on Fixed 6th Generation (F6G) networks. First, we adopt a novel classification scheme for the main F6G services, comprising six categories. This classification is based on the key service requirements, namely latency, capacity, and connectivity. F6G networks differ from those of previous generations (F1G–F5G) in that they concurrently support multiple key requirements. We then propose concrete steps towards transforming the main elements of fixed networks, such as optical transceivers, optical switches, etc., such that they satisfy the new F6G service requirements. Our study categorizes the main networking paradigm of optical switching into two categories, namely ultra-fast and ultra-high capacity switching, tailored to different service categories. With regard to the transceiver physical layer, we propose (a) the use of all-optical processing to mitigate performance barriers of analog-to-digital and digital-to-analog converters (ADC/DAC) and (b) the exploitation of optical multi-band transmission, space division-multiplexing, and the adoption of more efficient modulation formats. [ABSTRACT FROM AUTHOR]

Nowadays, the data centers have become a significant physical infrastructure for the purpose of supporting various Internet applications like cloud services, entertainment, web search and social networking. The traffic among the data centers is growing rapidly accompanied by the services that are obtained. The data centers are connected via fiber channels to support long-haul networks and high data rate transmissions by utilizing various modulation techniques. However, it has some drawbacks such as increased delay, computational complexities, high wavelength consumption, link failures, etc. Recently, researchers are focusing on improving the survivability and wavelength usage efficiency in optical data center networks. In this work, a novel framework depending on the concept of content connectivity is proposed for optical data center networks. Here, a mixed integer linear programming (MILP) is utilized for transmitting the data through optical data centers. The main intention of this research is to improve the performance and wavelength efficiency in optical data center networks. The performance of the MILP approach is evaluated and compared with the existing integer linear programming (ILP) technique and found that this new approach provides better performance with higher wavelength efficiency and reduced wavelength consumption. [ABSTRACT FROM AUTHOR]

This paper investigates the double-link protection in optical networks using pre-configured cycles (p-cycles) protection. The objectives of this work are to efficiently use redundant resources while providing double-link protection and reducing the computational complexity of the optimization model in an optical network. To accomplish these, we propose a SinGle p-Cycle (SG) method, which requires one p-cycle to protect a link from double-link failures. We formulated the Integer Linear Program for SG and DouBle cycle (DB) method. Simulation results obtained for SG are compared with DB, Improved DouBle cycle, and Link Pair Method (LPM) based on spare capacity and computation time. The computational complexity of SG is reduced by an order for the number of cycles compared to other p-cycles-based double-link protection methods. We demonstrate a significant reduction in computation time and spare capacity for the SG method for the same working capacity of an optical network. The SG method also computes spare capacity for big networks such as Net4, cost239, and USA Long haul. [ABSTRACT FROM AUTHOR]

Current trends in network traffic management rely on the efficient control of individual flows. Software-defined networking popularized this notion. Per-flow management is perfectly viable in standard IP networks, in which packet processing is in the electric domain. However, optical networks provide more restrictions and constraints making per-flow traffic management difficult. One of the most important challenges is to reduce the concurrent number of flows present in the flow tables to make the switching process quicker. In this paper, we propose a mechanism to manage flow timeout values that uses idle timeout and hard timeout parameters. To calculate the appropriate values of the parameters, the mechanism analyzes the packet inter-arrival times. The algorithm also takes into account the current occupancy of the flow table.

Networking research often requires realistic topologies to study performance and resilience. This project introduces TopoHub, an open repository of reference network topologies of variety of network sizes based on the Gabriel graph model. The accompanying Python package offers functionalities for topology generation, analysis, and integration with the Mininet network emulator. A web interface allows users to explore topologies, including visualization of link utilization under various traffic demands. The project aims to provide a comprehensive topology data source for networking researchers, enabling standardized benchmarking and reproducible research.

Fiber optic communications are inevitable to achieve higher data rates of modern telecom networks. After utilization of Wavelength division multiplexing, higher order modulations and polarization multiplexing, mode division multiplexing is a new dimension to achieve higher transmission capacity for optical fiber communication links. Different spatial distributions of optical energy along cross sectional area of optical fiber allows simultaneous transmission of data by considering each mode as an independent channel. During such simultaneous transmissions, possibility of mixing of signals amongst modes causes signal degradations and acts as limiting factor for bandwidth -- distance product of the link. This effect of mode coupling has been explored in this article by presenting its mathematical formulations. A simulation has been performed to study the impact of fiber constructional parameters on mode coupling using optical wavelengths used for telecommunication systems. The observations help to develop fiber for reduced mode coupling for particular group of modes and operating wavelengths. This article paves the way forward for study of mode coupling in micro and macro bending conditions for forthcoming research endeavours. [ABSTRACT FROM AUTHOR]

Filterless optical networks (FONs) have become a cost-effective solution for optical network deployment due to their low-cost characteristics. However, eliminating active switching elements causes signals to propagate over unintended links, wasting spectral resources. Therefore, semi-filterless optical networks (Semi-FONs) have become a more cost-effective solution. This paper mainly studies the routing, modulation, and spectrum assignment (RMSA) problem in semi-filterless optical networks. It proposes a single–multi-path combination (LR-SMPC) RMSA algorithm with the least resource consumption. The algorithm first obtains the K shortest paths that satisfy the conditions according to the K short path (KSP) algorithm and re-orders the paths according to the resource consumption path re-ordering strategy, selecting the three paths that consume the least resources as the set of candidate paths. Then, based on the single–multi-path combination scheme of the set of candidate paths, the resource consumption of each scheme and the maximum number of available spectrum blocks for each path is calculated, from which the single path or multi-path with the least resource consumption is selected to serve the request. We perform simulation experiments on two network topologies using Poisson traffic models and compare them with existing single-path algorithms (S-P), fixed spectrum assignment granularity algorithms (g = 1), and adaptation spectrum assignment algorithms (g adaptation) to evaluate the performance of the proposed algorithm. The simulation results show that the proposed algorithm exhibits better performance in terms of both blocking rate and spectrum utilization. [ABSTRACT FROM AUTHOR]

During the last decade, optical networks have become “smart networks”. Software-defined networks, software-defined optical networks, and elastic optical networks are some emerging technologies that provide a basis for promising innovations in the functioning and operation of optical networks. Machine learning algorithms are providing the possibility to develop this promising study area. Since machine learning can learn from a large amount of data available from the network elements. They can find a suitable solution for any environment and thus create more dynamic and flexible networks that improve the user experience. This paper performs a systematic mapping that provides an overview of machine learning in optical networks, identifies opportunities, and suggests future research lines. The study analyzed 96 papers from the 841 publications on this topic to find information about the use of machine learning techniques to solve problems related to the functioning and operation of optical networks. It is concluded that supervised machine learning techniques are mainly used for resource management, network monitoring, fault management, and traffic classification and prediction of an optical network. However, specific challenges need to be solved to successfully deploy this type of method in real communication systems since most of the research has been carried out in controlled experimental environments.

As next-generation networks begin to take shape, the necessity of Optical Transport Networks (OTNs) in helping achieve the performance requirements of future networks is evident. Future networks are characterized as being data-centric and are expected to have ubiquitous artificial intelligence integration and deployment. To this end, the efficient and timely transportation of fresh data from producer to consumer is critical. The work presented in this paper outlines the role of OTNs in future networking generations. Furthermore, key emerging OTN technologies are discussed. Additionally, the role intelligence will play in the Management and Orchestration (MANO) of next-generation OTNs is discussed. Moreover, a set of challenges and opportunities for innovation to guide the development of future OTNs is considered. Finally, a use case illustrating the impact of network dynamicity and demand uncertainty on OTN MANO decisions is presented. [ABSTRACT FROM AUTHOR]

One of the most important challenges of this century will be to minimise as much as possible the energy consumption of the worldwide digital infrastructure to have a significant contribution on our emissions of CO2 reduction since energy consumption and emission of CO2 are directly linked. Therefore, after an introduction (part 1), in part 2 of this paper, we will describe the status of the worldwide production of electricity, the contribution of information and communications technology (ICT) in terms of electricity consumption, and the identification of the critical network segments that can have a significant environmental impact. In part 3, we will focus on the data centres and core services that represent important network segments responsible for the largest emission of CO2. In part 4, we will address the access and aggregation part, which represents the second important network segment to optimise. Part 5 will focus on the home networking and enterprise. And before an estimation of the energy savings obtained when adopting the innovations proposed, the impact of the vertical market will be discussed in part 6. Finally, the conclusion (part 7) will summarise the results and perspectives will be proposed to complete the analysis. [ABSTRACT FROM AUTHOR]

Telecommunication networks frequently face technological advancements and need to upgrade their infrastructure. Adapting legacy networks to the latest technology requires synchronized technicians responsible for migrating the equipment. The goal of the network migration problem is to find an optimal plan for this process. This is a defining step in the customer acquisition of telecommunications service suppliers, and its outcome directly impacts the network owners' purchasing behavior. We propose the first exact method for the network migration problem, a logic-based Benders decomposition approach that benefits from a hybrid constraint programming–based column generation in its master problem and a constraint programming model in its subproblem. This integrated solution technique is applicable to any integer programming problem with similar structure, most notably the vehicle routing problem with node synchronization constraints. Comprehensive evaluation of our method over instances based on six real networks demonstrates the computational efficiency of the algorithm in obtaining quality solutions. We also show the merit of each incorporated optimization paradigm in achieving this performance. History: Accepted by David Alderson, Area Editor for Network Optimization: Algorithms & Applications. Funding: This work was supported by Mitacs. SciNet is funded by the Canada Foundation for Innovation, the Government of Ontario, Ontario Research Fund–Research Excellence, and the University of Toronto. Supplemental Material: The e-companion is available at https://doi.org/10.1287/ijoc.2023.1280. [ABSTRACT FROM AUTHOR]

The future age of optical networks demands autonomous functions to optimize available resources. With autonomy, the communication network should be able to learn and adapt to the dynamic environment. Among the different autonomous tasks, this work considers building self-adaptive and self-awareness-free space optic (FSO) networks by exploiting advances in artificial intelligence. In this regard, we study the use of machine learning (ML) techniques to build self-adaptive and self-awareness FSO systems capable of classifying the modulation format/baud rate and predicting the number of channel impairments. The study considers four modulation formats and four baud rates applicable in current commercial FSO systems. Moreover, two main channel impairments are considered. The results show that the proposed ML algorithm is capable of achieving 100% classification accuracy for the considered modulation formats/baud rates even under harsh channel conditions. Moreover, the prediction accuracy of the channel impairments ranges between 71% and 100% depending on the predicted parameter type and channel conditions. [ABSTRACT FROM AUTHOR]

Optical backbone networks constitute the fundamental infrastructure employed today by network operators to deliver services to users. As network capacity is a key factor influencing optical network performance, it is important to understand how topological and physical properties impact its behavior and to have the capability to estimate its value. In this context, we propose here a method to evaluate the network capacity that relies on the optical reach to account for physical layer aspects in conjunction with constrained routing techniques for traffic routing. As this type of routing can lead to traffic blocking, particularly due to the limitation on the number of wavelengths per fiber, we also propose a fiber assignment algorithm designed to deal with this problem. We apply this method to a set of randomly generated networks using a modified Waxman model, and for a network with 60 nodes, in a scenario without blocking, we obtain capacities of about 2.5 Pbit/s for a symbol rate of 64 Gbaud and about 5 Pbit/s for a symbol rate of 128 Gbaud. Remarkably, this duplication in the total network capacity is achieved by an increase in the total fiber length of only about 51%.

Permutation matrices form an important computational building block frequently used in various fields including, e.g., communications, information security, and data processing. Optical implementation of permutation operators with relatively large number of input–output interconnections based on power-efficient, fast, and compact platforms is highly desirable. Here, we present diffractive optical networks engineered through deep learning to all-optically perform permutation operations that can scale to hundreds of thousands of interconnections between an input and an output field-of-view using passive transmissive layers that are individually structured at the wavelength scale. Our findings indicate that the capacity of the diffractive optical network in approximating a given permutation operation increases proportional to the number of diffractive layers and trainable transmission elements in the system. Such deeper diffractive network designs can pose practical challenges in terms of physical alignment and output diffraction efficiency of the system. We addressed these challenges by designing misalignment tolerant diffractive designs that can all-optically perform arbitrarily selected permutation operations, and experimentally demonstrated, for the first time, a diffractive permutation network that operates at THz part of the spectrum. Diffractive permutation networks might find various applications in, e.g., security, image encryption, and data processing, along with telecommunications; especially with the carrier frequencies in wireless communications approaching THz-bands, the presented diffractive permutation networks can potentially serve as channel routing and interconnection panels in wireless networks.

Design of fault tolerant dense wavelength division multiplexing (DWDM) backbones is a major issue for service provision in the presence of failures. The problem is an NP-hard problem. This paper presents a genetic algorithm based approach for designing fault tolerant DWDM optical networks in the presence of a single link failure. The working and spare lightpaths are encoded into variable length chromosomes. Then the best lightpaths are found by use of a fitness function and these are assigned the minimum number of wavelengths according to the problem constraints using first-fit (FF) algorithm. The proposed approach has been evaluated for dedicated path protection architecture. The results, obtained from the ARPA2 test bench network, show that the method is well suited to tackling this complex and multi-constraint problem.

The quality of service (QoS) is an important and considerable issue in designing survivable dense wavelength division multiplexing (DWDM) backbones for IP networks. This paper investigates the effect of network topology on QoS delivering in survivable DWDM optical transport networks using bandwidth/load ratio and design flexibility metrics. The dedicated path protection architecture is employed to establish diverse working and spare lightpaths between each node pair in demand matrix for covering a single link failure model. The simulation results, obtained for the Pan-European and ARPA2 test bench networks, demonstrate that the network topology has a great influence on QoS delivering by network at optical layer for different applications. The Pan-European network, a more connected network, displays better performance than ARPA2 network for both bandwidth/load ratio and design flexibility metrics.

This paper examines applying machine learning to the assessment of the quality of the transmission in optical networks. The motivation for research into this problem derives from the fact that the accurate assessment of transmission quality is key to an effective management of an optical network by a network operator. In order to facilitate a potential implementation of the proposed solution by a network operator, the training data for the machine learning algorithms are directly extracted from an operating network via a control plane. Particularly, this work focuses on the application of single class and binary classification machine learning algorithms to optical network transmission quality assessment. The results obtained show that the best performance can be achieved using gradient boosting and random forest algorithms. [ABSTRACT FROM AUTHOR]

The Measurement-Device-Independent-Quantum Key Distribution (MDI-QKD) has the advantage of extending the secure transmission distances. The MDI-QKD combined with the Hybrid-Trusted and Untrusted Relay (HTUR) is used to deploy large-scale QKD networks, which effectively saves deployment cost. We propose an improved scheme for the QKD network architecture and cost analysis, which simplifies the number of QKD transmitters and incorporates the quantum key pool (QKP) in the QKD network. We developed a novel Hybrid-QKD-Network-Cost (HQNC) heuristic algorithm to solve the cost optimization problem. Simulations verified that the scheme in this paper could save the cost by over 50 percent and 90 percent, respectively. [ABSTRACT FROM AUTHOR]

Space division multiplexing (SDM) is promising to enhance capacity limits of optical networks. Among implementation options, few-mode fibres (FMFs) offer high efficiency gains in terms of integratability and throughput per volume. However, to achieve low insertion loss and low crosstalk, the beam launching should match the fiber modes precisely. We propose an all-optical data-driven technique based on multiplane light conversion (MPLC) and neural networks (NNs). By using a phase-only spatial light modulator (SLM), spatially separated input beams are transformed independently to coaxial output modes. Compared to conventional offline calculation of SLM phase masks, we employ an intelligent two-stage approach that considers knowledge of the experimental environment significantly reducing misalignment. First, a single-layer NN called Model-NN learns the beam propagation through the setup and provides a digital twin of the apparatus. Second, another single-layer NN called Actor-NN controls the model. As a result, SLM phase masks are predicted and employed in the experiment to shape an input beam to a target output. We show results on a single-passage configuration with intensity-only shaping. We achieve a correlation between experiment and network prediction of 0.65. Using programmable optical elements, our method allows the implementation of aberration correction and distortion compensation techniques, which enables secure high-capacity long-reach FMF-based communication systems by adaptive mode multiplexing devices. [ABSTRACT FROM AUTHOR]

Bismuth-doped fiber amplifiers offer an attractive solution for meeting continuously growing enormous demand on the bandwidth of modern communication systems. However, practical deployment of such amplifiers require massive development and optimization efforts with the numerical modeling being the core design tool. The numerical optimization of bismuth-doped fiber amplifiers is challenging due to a large number of unknown parameters in the conventional rate equations models. We propose here a new approach to develop a bismuth-doped fiber amplifier model based on a neural network purely trained with experimental data sets in E- and S-bands. This method allows a robust prediction of the amplifier operation that incorporates variations of fiber properties due to manufacturing process and any fluctuations of the amplifier characteristics. Using the proposed approach the spectral dependencies of gain and noise figure for given bi-directional pump currents and input signal powers have been obtained. The low mean (less than 0.19 dB) and standard deviation (less than 0.09 dB) of the maximum error are achieved for gain and noise figure predictions in the 1410–1490 nm spectral band. [ABSTRACT FROM AUTHOR]