Growing capacity requirements are leading to the deployment of multiple fibers in each optical network link. Even though deploying state-of-the-art multi-fiber network architectures with stacked and independent fiber layers simplifies network design and control, spectrum can be used more efficiently if the optical-network nodes allow fiber layers to be interconnected, i.e., if the so-called lane change is enabled. Unfortunately, lane change in high-degree optical nodes requires wavelength selective switches (WSSs) with a high number of ports, which is prohibitively costly or even unfeasible with current WSS technology. Instead, lane change in low-degree optical nodes can be enabled at no extra cost, using WSS ports that are otherwise left empty. In this study, we describe our proposal for a multi-fiber network with partial lane-change capabilities and perform a simulative study to identify the advantages of this architecture, as well as discuss the emerging resource allocation challenges associated with it. We demonstrate that, by enabling lane change in degree-2 nodes, we can increase network throughput by 3% and restore 5%–8% more traffic in the case of single- and double-link failures at no additional equipment cost.
{"title":"Zero-cost upgrade to a multi-fiber network with partial lane-change capabilities","authors":"Oleg Karandin;Francesco Musumeci;Gabriel Charlet;Yvan Pointurier;Massimo Tornatore","doi":"10.1364/JOCN.533906","DOIUrl":"https://doi.org/10.1364/JOCN.533906","url":null,"abstract":"Growing capacity requirements are leading to the deployment of multiple fibers in each optical network link. Even though deploying state-of-the-art multi-fiber network architectures with stacked and independent fiber layers simplifies network design and control, spectrum can be used more efficiently if the optical-network nodes allow fiber layers to be interconnected, i.e., if the so-called lane change is enabled. Unfortunately, lane change in high-degree optical nodes requires wavelength selective switches (WSSs) with a high number of ports, which is prohibitively costly or even unfeasible with current WSS technology. Instead, lane change in low-degree optical nodes can be enabled at no extra cost, using WSS ports that are otherwise left empty. In this study, we describe our proposal for a multi-fiber network with partial lane-change capabilities and perform a simulative study to identify the advantages of this architecture, as well as discuss the emerging resource allocation challenges associated with it. We demonstrate that, by enabling lane change in degree-2 nodes, we can increase network throughput by 3% and restore 5%–8% more traffic in the case of single- and double-link failures at no additional equipment cost.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"H18-H26"},"PeriodicalIF":4.0,"publicationDate":"2024-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142438447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, we propose an original adaptive neural network equalizer (NNE) algorithm named SkipNet, which is suitable for rapid training on a packet-by-packet basis for burst-mode non-linear equalization in upstream PON transmission. SkipNet uses the simple LMS algorithm and avoids complex neural network training algorithms such as backpropagation and mini-batch training. We demonstrate SkipNet on captured continuous mode 100 Gbit/s PAM4 signals using an SOA preamplifier to achieve the challenging 29 dB PON optical loss budget. The adaptive SkipNet equalizer is shown to overcome combinations of severe SOA patterning effects and fiber dispersion impairments to achieve ${gt}{29};{rm dB}$ dynamic range back-to-back and ${gt}{22.9};{rm dB}$ dynamic range for up to 81.6 ps/nm accumulated dispersion. It can adapt in as little as 250 training symbols to each impairment scenario, which is equivalent to existing FFE/DFE solutions, while matching the non-linear performance of previously proposed static NNE solutions. To the best of our knowledge, SkipNet is the first ever adaptive NNE framework that can realistically be trained and adapted on a packet-by-packet basis and within strict PON packet preamble lengths.
本文提出了一种名为 "SkipNet "的独创自适应神经网络均衡器（NNE）算法，适用于在上游 PON 传输中逐个数据包快速训练突发模式非线性均衡。SkipNet 使用简单的 LMS 算法，避免了复杂的神经网络训练算法，如反向传播和迷你批量训练。我们使用 SOA 前置放大器在捕获的连续模式 100 Gbit/s PAM4 信号上演示了 SkipNet，以实现具有挑战性的 29 dB PON 光损耗预算。研究表明，自适应 SkipNet 均衡器能够克服严重的 SOA 图案效应和光纤色散损伤，从而在高达 81.6 ps/nm 的累积色散条件下实现${{29}/;{/rm dB}$的背靠背动态范围和${{22.9}/;{/rm dB}$的动态范围。它能在短短 250 个训练符号内适应每种损伤情况，这与现有的 FFE/DFE 解决方案相当，同时与之前提出的静态 NNE 解决方案的非线性性能相匹配。据我们所知，SkipNet 是有史以来第一个自适应 NNE 框架，可以在严格的 PON 数据包前导码长度范围内逐个数据包进行实际训练和调整。
{"title":"SkipNet: an adaptive neural network equalization algorithm for future passive optical networking","authors":"Stephen L. Murphy;Paul D. Townsend;Cleitus Antony","doi":"10.1364/JOCN.528490","DOIUrl":"10.1364/JOCN.528490","url":null,"abstract":"In this paper, we propose an original adaptive neural network equalizer (NNE) algorithm named SkipNet, which is suitable for rapid training on a packet-by-packet basis for burst-mode non-linear equalization in upstream PON transmission. SkipNet uses the simple LMS algorithm and avoids complex neural network training algorithms such as backpropagation and mini-batch training. We demonstrate SkipNet on captured continuous mode 100 Gbit/s PAM4 signals using an SOA preamplifier to achieve the challenging 29 dB PON optical loss budget. The adaptive SkipNet equalizer is shown to overcome combinations of severe SOA patterning effects and fiber dispersion impairments to achieve \u0000<tex>${gt}{29};{rm dB}$</tex>\u0000 dynamic range back-to-back and \u0000<tex>${gt}{22.9};{rm dB}$</tex>\u0000 dynamic range for up to 81.6 ps/nm accumulated dispersion. It can adapt in as little as 250 training symbols to each impairment scenario, which is equivalent to existing FFE/DFE solutions, while matching the non-linear performance of previously proposed static NNE solutions. To the best of our knowledge, SkipNet is the first ever adaptive NNE framework that can realistically be trained and adapted on a packet-by-packet basis and within strict PON packet preamble lengths.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"1082-1092"},"PeriodicalIF":4.0,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10712641","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141800990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper investigates the practical scalability of wavelength selective switching technology for the emerging multi-band and space-division-multiplexed (SDM) networks. Wavelength selective switching architectures are introduced for multi-band SDM networks. The switching capacity is analyzed for both weakly coupled and strongly coupled SDM networks. Key bottlenecks for scaling up toward multi-band and more spatial modes are identified. Contrary to the conventional view that liquid crystal on silicon (LCOS) was the only technological obstacle, the manufacturability of free-space optics with high numerical apertures and constraints on the optical dimensions also brought significant challenges for the development of highly integrated wavelength selective switches for multi-band SDM networks.
{"title":"Scaling wavelength selective switches for multi-band and space-division-multiplexed networks","authors":"Haoyu Wei;Weixin Chen;Haining Yang","doi":"10.1364/JOCN.531337","DOIUrl":"https://doi.org/10.1364/JOCN.531337","url":null,"abstract":"This paper investigates the practical scalability of wavelength selective switching technology for the emerging multi-band and space-division-multiplexed (SDM) networks. Wavelength selective switching architectures are introduced for multi-band SDM networks. The switching capacity is analyzed for both weakly coupled and strongly coupled SDM networks. Key bottlenecks for scaling up toward multi-band and more spatial modes are identified. Contrary to the conventional view that liquid crystal on silicon (LCOS) was the only technological obstacle, the manufacturability of free-space optics with high numerical apertures and constraints on the optical dimensions also brought significant challenges for the development of highly integrated wavelength selective switches for multi-band SDM networks.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"H9-H17"},"PeriodicalIF":4.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper reviews and analyzes multicore-fiber technologies in the context of submarine networks. As global/transcontinental capacity continues to grow at a large and steady pace, the subsea industry is challenged to deliver technologies that provide large-capacity networks in a faster, greener, and cost-effective fashion. Multicore fiber has been considered as a serious candidate for next-generation systems with the ability to maintain standard cable size at large core counts. This paper analyzes the technoeconomics of next-generation submarine systems including variables such as equipment size versus marine cost and other critical elements (not analyzed before, to our knowledge) for submarine system implementation. In this context, this paper also analyzes the state-of-the-art of multicore subsystems and components and discusses their roadmaps, requirements, and evolution toward the realization of a multicore ecosystem for next-generation SDM systems.
{"title":"Multicore-fiber submarine systems","authors":"Eduardo F. Mateo","doi":"10.1364/JOCN.532163","DOIUrl":"https://doi.org/10.1364/JOCN.532163","url":null,"abstract":"This paper reviews and analyzes multicore-fiber technologies in the context of submarine networks. As global/transcontinental capacity continues to grow at a large and steady pace, the subsea industry is challenged to deliver technologies that provide large-capacity networks in a faster, greener, and cost-effective fashion. Multicore fiber has been considered as a serious candidate for next-generation systems with the ability to maintain standard cable size at large core counts. This paper analyzes the technoeconomics of next-generation submarine systems including variables such as equipment size versus marine cost and other critical elements (not analyzed before, to our knowledge) for submarine system implementation. In this context, this paper also analyzes the state-of-the-art of multicore subsystems and components and discusses their roadmaps, requirements, and evolution toward the realization of a multicore ecosystem for next-generation SDM systems.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"H1-H8"},"PeriodicalIF":4.0,"publicationDate":"2024-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142397506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Caio Santos;Abdelrahmane Moawad;Behnam Shariati;Robert Emmerich;Pooyan Safari;Colja Schubert;Johannes K. Fischer
Due to the scarcity of diverse and well-organized public datasets, individual research organizations are often forced to develop and utilize their own datasets. However, the utilization of machine learning (ML) models in optical communications and networks heavily depends on the existence of high-quality datasets, especially covering the various parameters to be optimized in wavelength-division multiplexing (WDM) systems. In this work, we present a public dataset for developing and testing ML models. The dataset is developed in a laboratory setting and includes 12,672 samples including data points with different modulation formats, symbol rates, distances, WDM channel allocation profiles, etc. Each data point offers more than 60 features, revealing almost every aspect of the transmission setup. Moreover, we provide optical spectra of the entire C-band as well as a constellation diagram of the channel under test for all the data points. The diversity and extensiveness of the dataset alongside a well-structured document would allow plenty of use-cases and studies to be carried out covering quality of transmission (QoT) studies, optical spectrum analysis, constellation diagram modeling, digital twin evaluation, etc. Similar to our previous efforts, the current dataset aims to facilitate collaboration by offering a way for fair comparison of research outcomes in data analysis within the domain of optical communication systems.
由于缺乏种类繁多、组织有序的公共数据集，各个研究机构往往不得不开发和利用自己的数据集。然而，机器学习（ML）模型在光通信和网络中的应用在很大程度上依赖于高质量数据集的存在，尤其是涵盖波分复用（WDM）系统中需要优化的各种参数的数据集。在这项工作中，我们提出了一个用于开发和测试 ML 模型的公共数据集。该数据集是在实验室环境中开发的，包含 12672 个样本，包括不同调制格式、符号率、距离、波分复用信道分配情况等数据点。每个数据点提供 60 多个特征，揭示了传输设置的几乎所有方面。此外，我们还为所有数据点提供了整个 C 波段的光学光谱以及被测信道的星座图。数据集的多样性和广泛性以及结构良好的文档将允许开展大量的用例和研究，包括传输质量（QoT）研究、光学频谱分析、星座图建模、数字孪生评估等。与我们之前的工作类似，当前的数据集旨在通过提供一种公平比较光通信系统领域内数据分析研究成果的方法来促进合作。
{"title":"Experimental dataset for developing and testing ML models in optical communication systems","authors":"Caio Santos;Abdelrahmane Moawad;Behnam Shariati;Robert Emmerich;Pooyan Safari;Colja Schubert;Johannes K. Fischer","doi":"10.1364/JOCN.531788","DOIUrl":"https://doi.org/10.1364/JOCN.531788","url":null,"abstract":"Due to the scarcity of diverse and well-organized public datasets, individual research organizations are often forced to develop and utilize their own datasets. However, the utilization of machine learning (ML) models in optical communications and networks heavily depends on the existence of high-quality datasets, especially covering the various parameters to be optimized in wavelength-division multiplexing (WDM) systems. In this work, we present a public dataset for developing and testing ML models. The dataset is developed in a laboratory setting and includes 12,672 samples including data points with different modulation formats, symbol rates, distances, WDM channel allocation profiles, etc. Each data point offers more than 60 features, revealing almost every aspect of the transmission setup. Moreover, we provide optical spectra of the entire C-band as well as a constellation diagram of the channel under test for all the data points. The diversity and extensiveness of the dataset alongside a well-structured document would allow plenty of use-cases and studies to be carried out covering quality of transmission (QoT) studies, optical spectrum analysis, constellation diagram modeling, digital twin evaluation, etc. Similar to our previous efforts, the current dataset aims to facilitate collaboration by offering a way for fair comparison of research outcomes in data analysis within the domain of optical communication systems.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"G1-G10"},"PeriodicalIF":4.0,"publicationDate":"2024-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142377114","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Celso Henrique de Souza Lopes;Tomas Powell Villena Andrade;Luiz Augusto Melo Pereira;Evandro Conforti;Arismar Cerqueira Sodre Junior
This paper presents two distinct network architectures designed to address the demands of 5G/6G applications. The first architecture is an analog radio-over-fiber (RoF) optical fronthaul operating in the V-band at 60 GHz, integrated within a wavelength-division multiplexing passive optical network (WDM-PON). This setup employs photonic techniques for RF signal generation, specifically using carrier-suppressed double sideband (CS-DSB) modulation via Mach–Zehnder modulators (MZMs), enabling efficient frequency multiplication and signal transport. Experimental results demonstrate its ability to achieve a data rate of approximately 11.8 Gbit/s, meeting the requirements for 5G/6G cell densification. The second architecture is a heterogeneous network (HetNet) that combines fiber-wireless (FiWi), free space optics (FSO), and visible light communication (VLC) technologies in a unified network configuration designed for indoor 6G solutions. This HetNet architecture was tested at 39 GHz and features a 20 km optical fiber midhaul, an FSO fronthaul, and a dual VLC/RF access network. The setup was evaluated based on the root mean square error vector magnitude ( ${{rm EVM}_{{rm RMS}}}$ ) requirements, with results indicating satisfactory coexistence of the employed technologies, achieving a total data throughput of 1.5 Gbit/s.
{"title":"Implementation of HetNet architectures based on FSO, VLC, RoF, and photonics-based RF generation toward 6G applications","authors":"Celso Henrique de Souza Lopes;Tomas Powell Villena Andrade;Luiz Augusto Melo Pereira;Evandro Conforti;Arismar Cerqueira Sodre Junior","doi":"10.1364/JOCN.530373","DOIUrl":"https://doi.org/10.1364/JOCN.530373","url":null,"abstract":"This paper presents two distinct network architectures designed to address the demands of 5G/6G applications. The first architecture is an analog radio-over-fiber (RoF) optical fronthaul operating in the V-band at 60 GHz, integrated within a wavelength-division multiplexing passive optical network (WDM-PON). This setup employs photonic techniques for RF signal generation, specifically using carrier-suppressed double sideband (CS-DSB) modulation via Mach–Zehnder modulators (MZMs), enabling efficient frequency multiplication and signal transport. Experimental results demonstrate its ability to achieve a data rate of approximately 11.8 Gbit/s, meeting the requirements for 5G/6G cell densification. The second architecture is a heterogeneous network (HetNet) that combines fiber-wireless (FiWi), free space optics (FSO), and visible light communication (VLC) technologies in a unified network configuration designed for indoor 6G solutions. This HetNet architecture was tested at 39 GHz and features a 20 km optical fiber midhaul, an FSO fronthaul, and a dual VLC/RF access network. The setup was evaluated based on the root mean square error vector magnitude (\u0000<tex>${{rm EVM}_{{rm RMS}}}$</tex>\u0000) requirements, with results indicating satisfactory coexistence of the employed technologies, achieving a total data throughput of 1.5 Gbit/s.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 10","pages":"1070-1081"},"PeriodicalIF":4.0,"publicationDate":"2024-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142359740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Accurate quality-of-transmission (QoT) estimation tools are crucial to building digital twins (DTs) for optical networks. However, the input-parameter inaccuracy deteriorates the estimation accuracy of the physical models. To address this problem, an input-parameter refinement (IR) paradigm aiming at finding the mappings from uncertain parameters to their corresponding true values is proposed. The primary advantage of the IR paradigm, as demonstrated in this study for Raman amplifiers (RAs), lies in its applicability to dynamic optical networks, where system parameters such as loading conditions and optical device configurations are subject to frequent variations. The use of the proposed paradigm to refine the model of RAs is discussed in detail, while its applicability to other types of devices requires further investigation. The inaccuracy of fiber parameters, signal power, and pump power are taken into account. The particle swarm optimization (PSO) algorithm is utilized to address the problem of the coupling of these parameter inaccuracies. Experiments over a C + L band are conducted. In a single-span scenario, results show the proposed IR scheme can lower the physics-based RA model’s mean prediction error from ${sim}{0.92};{rm dB}$ to ${sim}{0.20};{rm dB}$ and lower the maximum absolute error (MAE) from ${sim}{3.09};{rm dB}$ to ${sim}{1.12};{rm dB}$ . The proposed IR scheme also exhibits high precision when applied in a two-span scenario, indicating its scalability to multi-span optical multiplexing section (OMS) scenarios. Furthermore, we demonstrate that the proposed IR scheme can also effectively enhance the accuracy of machine learning (ML) models. An IR-aided ML-based model training scheme is proposed. It offers significant advantages in scenarios where data collection from real systems is limited. With the proposed IR paradigm, the practical application of both physics-based models and ML-based models can be facilitated in future dynamic multiband optical networks.
精确的传输质量（QoT）估算工具对于构建光网络数字孪生（DT）至关重要。然而，输入参数不准确会降低物理模型的估计精度。为解决这一问题，我们提出了一种输入参数细化（IR）范例，旨在找到不确定参数与其相应真实值之间的映射关系。正如本研究针对拉曼放大器（RA）所展示的那样，IR 范式的主要优势在于它适用于动态光网络，在动态光网络中，加载条件和光学器件配置等系统参数会频繁变化。本文详细讨论了如何利用所提出的范例来完善拉曼放大器模型，同时还需要进一步研究该范例对其他类型设备的适用性。光纤参数、信号功率和泵浦功率的不准确性已被考虑在内。粒子群优化（PSO）算法用于解决这些参数不准确性的耦合问题。在 C + L 波段上进行了实验。在单跨场景中，结果表明所提出的 IR 方案可以将基于物理的 RA 模型的平均预测误差从 ${sim}{0.92};{rm dB}$ 降低到 ${sim}{0.20};{rm dB}$ 并将最大绝对误差（MAE）从 ${sim}{3.09};{rm dB}$ 降低到 ${sim}{1.12};{rm dB}$ 。当应用于双跨场景时，所提出的 IR 方案也表现出很高的精度，这表明它可以扩展到多跨光复用段 (OMS) 场景。此外，我们还证明了所提出的红外方案还能有效提高机器学习（ML）模型的精度。我们提出了一种基于红外辅助 ML 的模型训练方案。该方案在真实系统数据收集有限的情况下具有显著优势。有了所提出的红外范例，基于物理的模型和基于 ML 的模型都能在未来的动态多频带光网络中得到实际应用。
{"title":"Mapping-finding input-parameter refinement paradigm for a dynamic multiband optical network digital twin: the Raman amplifier modeling case","authors":"Yihao Zhang;Xiaomin Liu;Qizhi Qiu;Yichen Liu;Lilin Yi;Weisheng Hu;Qunbi Zhuge","doi":"10.1364/JOCN.539231","DOIUrl":"https://doi.org/10.1364/JOCN.539231","url":null,"abstract":"Accurate quality-of-transmission (QoT) estimation tools are crucial to building digital twins (DTs) for optical networks. However, the input-parameter inaccuracy deteriorates the estimation accuracy of the physical models. To address this problem, an input-parameter refinement (IR) paradigm aiming at finding the mappings from uncertain parameters to their corresponding true values is proposed. The primary advantage of the IR paradigm, as demonstrated in this study for Raman amplifiers (RAs), lies in its applicability to dynamic optical networks, where system parameters such as loading conditions and optical device configurations are subject to frequent variations. The use of the proposed paradigm to refine the model of RAs is discussed in detail, while its applicability to other types of devices requires further investigation. The inaccuracy of fiber parameters, signal power, and pump power are taken into account. The particle swarm optimization (PSO) algorithm is utilized to address the problem of the coupling of these parameter inaccuracies. Experiments over a C + L band are conducted. In a single-span scenario, results show the proposed IR scheme can lower the physics-based RA model’s mean prediction error from \u0000<tex>${sim}{0.92};{rm dB}$</tex>\u0000 to \u0000<tex>${sim}{0.20};{rm dB}$</tex>\u0000 and lower the maximum absolute error (MAE) from \u0000<tex>${sim}{3.09};{rm dB}$</tex>\u0000 to \u0000<tex>${sim}{1.12};{rm dB}$</tex>\u0000. The proposed IR scheme also exhibits high precision when applied in a two-span scenario, indicating its scalability to multi-span optical multiplexing section (OMS) scenarios. Furthermore, we demonstrate that the proposed IR scheme can also effectively enhance the accuracy of machine learning (ML) models. An IR-aided ML-based model training scheme is proposed. It offers significant advantages in scenarios where data collection from real systems is limited. With the proposed IR paradigm, the practical application of both physics-based models and ML-based models can be facilitated in future dynamic multiband optical networks.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 10","pages":"1059-1069"},"PeriodicalIF":4.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142328392","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Kenji Miyamoto;Hirotaka Ujikawa;Tatsuya Shimada;Tomoaki Yoshida
We propose a user-dedicated optical path switching technique for low-latency and seamless handover in the radio access network (RAN) with the all-photonic network (APN). The APN is a network that connects end points directly with optical paths of dedicated wavelengths assigned to each user and provides large-capacity and low-latency connections. As mobile systems beyond 5th generation (5G) and 6th generation (6G) will require extremely low latency, applying the APN to the RAN is promising to achieve this. However, the RAN with the APN has a challenge in optical path switching during the handover procedure of mobile systems because optical switches that compose the APN do not have an Internet protocol (IP) layer function that enables routing control for handover in the conventional router network. Our proposed optical path switching technique to solve this challenge utilizes optical-wireless cooperative control and switches an optical path dedicated to user equipment (UE) executing handover in conjunction with its handover procedure. The key point of the proposed technique is that a next generation node B (gNB) transmits an optimal-timing optical path switching trigger to the optical switch. We experimentally demonstrated the generation of a dedicated optical path for UE in the RAN with the APN as a premise to enable the proposed optical path switching technique. To evaluate the feasibility and effectiveness of the proposed optical path switching technique, we experimentally compared the optical switch and router in terms of latency performance, packet loss, and packet misdirection in the path switching during handover. The results indicated successful optical path switching during handover without packet loss and packet misdirection while reducing the latency per single network equipment by 99%, from 4 µs for the router to 45 ns for the optical switch.
我们提出了一种用户专用光路切换技术，可在全光子网络（APN）的无线接入网（RAN）中实现低延迟和无缝切换。APN 是一种通过为每个用户分配专用波长的光路直接连接端点的网络，可提供大容量和低延迟连接。由于第五代（5G）和第六代（6G）之后的移动系统将要求极低的延迟，因此将 APN 应用于 RAN 有望实现这一目标。然而，由于组成 APN 的光交换机不具备互联网协议 (IP) 层功能，无法在传统路由器网络中实现路由控制以进行切换，因此，采用 APN 的 RAN 在移动系统切换过程中面临光路径切换的挑战。为解决这一难题，我们提出了光路径切换技术，利用光-无线协同控制，结合用户设备（UE）的切换程序，切换专用于执行切换的光路径。该技术的关键在于下一代节点 B（gNB）向光交换机发送最佳时间光路径切换触发器。我们在实验中演示了以 APN 为前提，在 RAN 中为 UE 生成专用光路，从而实现所提出的光路切换技术。为了评估所提出的光路径切换技术的可行性和有效性，我们在实验中比较了光交换机和路由器在切换过程中路径切换的延迟性能、数据包丢失和数据包误导。结果表明，路由器在切换过程中成功地进行了光路径切换，没有出现数据包丢失和数据包误导，同时单个网络设备的延迟时间减少了 99%，从路由器的 4 µs 减少到光交换机的 45 ns。
{"title":"User-dedicated optical path switching with optical-wireless cooperative control for low-latency and seamless handover","authors":"Kenji Miyamoto;Hirotaka Ujikawa;Tatsuya Shimada;Tomoaki Yoshida","doi":"10.1364/JOCN.522722","DOIUrl":"https://doi.org/10.1364/JOCN.522722","url":null,"abstract":"We propose a user-dedicated optical path switching technique for low-latency and seamless handover in the radio access network (RAN) with the all-photonic network (APN). The APN is a network that connects end points directly with optical paths of dedicated wavelengths assigned to each user and provides large-capacity and low-latency connections. As mobile systems beyond 5th generation (5G) and 6th generation (6G) will require extremely low latency, applying the APN to the RAN is promising to achieve this. However, the RAN with the APN has a challenge in optical path switching during the handover procedure of mobile systems because optical switches that compose the APN do not have an Internet protocol (IP) layer function that enables routing control for handover in the conventional router network. Our proposed optical path switching technique to solve this challenge utilizes optical-wireless cooperative control and switches an optical path dedicated to user equipment (UE) executing handover in conjunction with its handover procedure. The key point of the proposed technique is that a next generation node B (gNB) transmits an optimal-timing optical path switching trigger to the optical switch. We experimentally demonstrated the generation of a dedicated optical path for UE in the RAN with the APN as a premise to enable the proposed optical path switching technique. To evaluate the feasibility and effectiveness of the proposed optical path switching technique, we experimentally compared the optical switch and router in terms of latency performance, packet loss, and packet misdirection in the path switching during handover. The results indicated successful optical path switching during handover without packet loss and packet misdirection while reducing the latency per single network equipment by 99%, from 4 µs for the router to 45 ns for the optical switch.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 10","pages":"1050-1058"},"PeriodicalIF":4.0,"publicationDate":"2024-09-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142324250","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Submarine cable is a crucial infrastructure for international communications, and its cost and survivability are two key factors that must be considered at its design phase. In this paper, we propose a machine-learning-assisted submarine cable route planning algorithm for minimizing its accumulated cost and risk. The cost and risk distribution and the direction of the submarine cable route’s starting point and endpoint are used as prior data to initialize the state-action of reinforcement learning (RL). We also propose a multi-agent cross reinforcement learning (MA-XRL) framework composed of Q-learning and SARSA to improve the global optimization capability of RL in the case of multi-objective optimization. The results show that, compared to ant colony optimization (ACO), MA-XRL can reduce the accumulated cost by 26.87% under the same accumulated risk. The maximum accumulated cost of the Pareto solutions obtained by MA-XRL is lower than the minimum accumulated cost of that obtained by ACO. Meanwhile, the running time of MA-XRL is only 1.3‰ of that of ACO. Without prior data of cost and risk initialization, the accumulated cost and risk of the best submarine cable route obtained by MA-XRL is 1.84 times and 7.08 times those with cost and risk distribution initialization, respectively. The direction initialization can accelerate the agent to find the endpoint of the submarine cable route and double the search stability of MA-XRL. Compared to using Q-learning or SARSA alone, MA-XRL can respectively reduce the accumulated risk by 71.81% and 39.51% under the same accumulated cost and can reduce the accumulated cost by 16.65% and 11.99% under the same accumulated risk, respectively.
{"title":"Multi-objective optimization for submarine optical cable route planning based on cross reinforcement learning","authors":"Zanshan Zhao;Guanjun Gao;Weiming Gan;Jialiang Zhang;Zengfu Wang;Haoyu Wang;Yonggang Guo","doi":"10.1364/JOCN.529175","DOIUrl":"https://doi.org/10.1364/JOCN.529175","url":null,"abstract":"Submarine cable is a crucial infrastructure for international communications, and its cost and survivability are two key factors that must be considered at its design phase. In this paper, we propose a machine-learning-assisted submarine cable route planning algorithm for minimizing its accumulated cost and risk. The cost and risk distribution and the direction of the submarine cable route’s starting point and endpoint are used as prior data to initialize the state-action of reinforcement learning (RL). We also propose a multi-agent cross reinforcement learning (MA-XRL) framework composed of Q-learning and SARSA to improve the global optimization capability of RL in the case of multi-objective optimization. The results show that, compared to ant colony optimization (ACO), MA-XRL can reduce the accumulated cost by 26.87% under the same accumulated risk. The maximum accumulated cost of the Pareto solutions obtained by MA-XRL is lower than the minimum accumulated cost of that obtained by ACO. Meanwhile, the running time of MA-XRL is only 1.3‰ of that of ACO. Without prior data of cost and risk initialization, the accumulated cost and risk of the best submarine cable route obtained by MA-XRL is 1.84 times and 7.08 times those with cost and risk distribution initialization, respectively. The direction initialization can accelerate the agent to find the endpoint of the submarine cable route and double the search stability of MA-XRL. Compared to using Q-learning or SARSA alone, MA-XRL can respectively reduce the accumulated risk by 71.81% and 39.51% under the same accumulated cost and can reduce the accumulated cost by 16.65% and 11.99% under the same accumulated risk, respectively.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 10","pages":"1018-1033"},"PeriodicalIF":4.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320452","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Noemi Merayo;David de Pintos;Juan Carlos Aguado;Ignacio de Miguel;Ramon J. Duran Barroso;Ruben M. Lorenzo
Software-defined networking (SDN) provides an efficient framework for managing passive optical networks (PONs) with equipment from different manufacturers, technologies, and standards. Thus, we recently proposed a robust and flexible SDN-OpenFlow agent to configure and manage 10 gigabit symmetric passive optical networks (XGS-PONs) to support Internet (data) services. That SDN agent communicates with the SDN controller via the OpenFlow protocol and with the optical line terminal (OLT) of the PON via the manufacturer’s chipset-specific API (application programming interface). In this paper, we significantly extend that SDN agent by incorporating the capability to support two essential services for network operators and Internet service providers, specifically voice over IP (VoIP) and video services. The required extensions and configuration procedures on the different layers that compose the SDN agent are described, and an experimental validation of the extended SDN agent in an XGS-PON is conducted, demonstrating its effectiveness in the integration of those two services. The source code of the SDN agent has been made open and available on GitHub.
软件定义网络（SDN）为管理采用不同制造商、技术和标准的设备的无源光网络（PON）提供了一个高效的框架。因此，我们最近提出了一种强大而灵活的 SDN-OpenFlow 代理，用于配置和管理万兆位对称无源光网络（XGS-PON），以支持互联网（数据）服务。该 SDN 代理通过 OpenFlow 协议与 SDN 控制器通信，并通过制造商芯片组特定的 API（应用编程接口）与 PON 的光线路终端 (OLT) 通信。在本文中，我们大幅扩展了 SDN 代理，为网络运营商和互联网服务提供商提供了支持两种基本服务的功能，特别是 IP 语音（VoIP）和视频服务。本文描述了组成 SDN 代理的不同层所需的扩展和配置程序，并在 XGS-PON 中对扩展 SDN 代理进行了实验验证，证明了它在集成这两种服务方面的有效性。SDN 代理的源代码已在 GitHub 上开放和提供。
{"title":"Software-defined networking agent for integrating voice, data, and video services into XGS-PON architectures","authors":"Noemi Merayo;David de Pintos;Juan Carlos Aguado;Ignacio de Miguel;Ramon J. Duran Barroso;Ruben M. Lorenzo","doi":"10.1364/JOCN.531051","DOIUrl":"https://doi.org/10.1364/JOCN.531051","url":null,"abstract":"Software-defined networking (SDN) provides an efficient framework for managing passive optical networks (PONs) with equipment from different manufacturers, technologies, and standards. Thus, we recently proposed a robust and flexible SDN-OpenFlow agent to configure and manage 10 gigabit symmetric passive optical networks (XGS-PONs) to support Internet (data) services. That SDN agent communicates with the SDN controller via the OpenFlow protocol and with the optical line terminal (OLT) of the PON via the manufacturer’s chipset-specific API (application programming interface). In this paper, we significantly extend that SDN agent by incorporating the capability to support two essential services for network operators and Internet service providers, specifically voice over IP (VoIP) and video services. The required extensions and configuration procedures on the different layers that compose the SDN agent are described, and an experimental validation of the extended SDN agent in an XGS-PON is conducted, demonstrating its effectiveness in the integration of those two services. The source code of the SDN agent has been made open and available on GitHub.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 10","pages":"1034-1049"},"PeriodicalIF":4.0,"publicationDate":"2024-09-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142320444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：