Journal of Optical Communications and Networking最新文献

{"title":"Longitudinal power profile monitoring telemetry enabling self-healing optical networks","authors":"Alessandro Pacini;Fabien Boitier;Alix May;Vinod Bajaj;Andrea Sgambelluri;Alessio Giorgetti;Luca Valcarenghi;Patricia Layec","doi":"10.1364/JOCN.555840","DOIUrl":"https://doi.org/10.1364/JOCN.555840","url":null,"abstract":"Soft failures in optical networks pose a significant challenge, as their detection and localization are notoriously difficult. This often leads to suboptimal mitigation strategies being implemented before the root cause is identified. To address this, the longitudinal power monitoring (LPM) technique has gained significant attention in recent years. LPM leverages information from the coherent receiver to compute the power evolution along the optical path. This paper presents an architecture that integrates the power profile information retrieved from the receiver with the SDN controller. The result is a self-healing optical network capable of locating soft failures in its lightpaths and providing finely tuned reconfigurations to solve them. By developing an OpenConfig-compliant YANG model, we implemented a gNMI streaming mechanism to transmit power profile metrics every 1.5 s from the receiver to the SDN controller. This process utilizes two SDN applications that combine the received data at the controller to finalize the power profile computation and pinpoint the location of soft failures. The architecture’s effectiveness is demonstrated through two scenarios. In the first scenario, the SDN controller accurately identifies and resolves attenuation caused by VOAs strategically placed along a span. In the second scenario, the controller jointly examines the power profiles of two lightpaths to locate a faulty WSS that is causing attenuation in only one of them.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 7","pages":"580-589"},"PeriodicalIF":4.0,"publicationDate":"2025-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144281320","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}

{"title":"Toward low-complexity neural networks for failure management in optical networks","authors":"Lareb Zar Khan;Joao Pedro;Omran Ayoub;Nelson Costa;Andrea Sgambelluri;Lorenzo De Marinis;Antonio Napoli;Nicola Sambo","doi":"10.1364/JOCN.550933","DOIUrl":"https://doi.org/10.1364/JOCN.550933","url":null,"abstract":"Machine learning (ML) continues to show its potential and efficacy in automating network management tasks, such as failure management. However, as ML deployment considerations broaden, aspects that go beyond predictive performance, such as a model’s computational complexity (CC), start to gain significance, as higher CC incurs higher costs and energy consumption. Balancing high predictive performance with reduced CC is an important aspect, and therefore, it needs more investigation, especially in the context of optical networks. In this work, we focus on the problem of reducing the CC of ML models, specifically neural networks (NNs), for the use case of failure identification in optical networks. We propose an approach that exploits the relative activity of neurons in NNs to reduce their size (and hence, their CC). Our proposed approach, referred to as iterative neural removal (INR), iteratively computes neurons’ activity and removes neurons with no activity until reaching a predefined stopping condition. We also propose another approach, referred to as guided knowledge distillation (GKD), that combines INR with knowledge distillation (KD), a known technique for compression of NNs. GKD inherently determines the size of the compressed NN without requiring any manual suboptimal selection or other time-consuming optimization strategies, as in traditional KD. To quantify the effectiveness of INR and GKD, we evaluate their performance against pruning (i.e., a well-known NN compression technique) in terms of impact on predictive performance and reduction in CC and memory footprint. For the considered scenario, experimental results on testbed data show that INR and GKD are more effective than pruning in reducing CC and memory footprint.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 7","pages":"555-563"},"PeriodicalIF":4.0,"publicationDate":"2025-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144243820","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}

{"title":"Self-configuring metro-access network with OpenXR Pluggables and filter-less OADMs","authors":"A. Rafel;P. Wright;K. Farrow;R. Kapuscinski;A. Napoli;C. Castro;N. Sugden;A. Stavdas;I. Cooper;E. Kosmatos;P. Pavon-Marino;E. Fernandez;S. Xia;N. Calabretta;R. Casellas","doi":"10.1364/JOCN.553757","DOIUrl":"https://doi.org/10.1364/JOCN.553757","url":null,"abstract":"We present a proof-of-concept (PoC) of a metro-access optical network that uses automatically reconfigurable OpenXR Pluggables and filter-less optical add-drop multiplexers (OADMs) over a chain of access nodes connected to two metro nodes in a horseshoe topology. Each OADM consists of optical splitters and semiconductor optical amplifiers (SOAs), whose gains are individually managed by an open-source network controller. Two sets of XR Pluggables were stacked operating both in point-to-point (P2P) and point-to-multipoint (P2MP) configurations. We conducted physical-layer experiments and evaluated control plane aspects to assess the performance of the proposed network.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 6","pages":"543-554"},"PeriodicalIF":4.0,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144196804","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}

{"title":"Holographic viewpoint rotation prediction-based resource-efficient holographic-type communication service provision in an EON-enabled NG-RAN","authors":"Xin Wang;Chengyuan Zhang;Yafei Wang;Ruikun Wang;Qiaolun Zhang","doi":"10.1364/JOCN.553675","DOIUrl":"https://doi.org/10.1364/JOCN.553675","url":null,"abstract":"Holographic-type communication (HTC) services, driven by six degrees of freedom (6DoF)-enabled holographic viewpoints and multisensory media (e.g., visual, auditory, and olfactory) data, offer ultra-immersive realism but introduce significant challenges. Frequent and proactive user interactions in HTC exacerbate dynamic bandwidth demands and lead to redundant hologram transmissions, as users engage with only a small portion of the hologram at any time. Additionally, ultra-low latency and precise synchronization requirements across concurrent data flows carrying HTC services further complicate the resource-efficient multisensory data distribution. This paper investigates resource-efficient HTC service provision over an elastic optical network (EON)-enabled next-generation radio access network (NG-RAN), focusing on DU-CU deployment, holographic routing, and spectrum allocation for the transmission of holograms and multisensory media data. To address these issues, we propose a mixed-integer linear programming (MILP) model and a holographic viewpoint rotation prediction-based graph neural network with an edge-node switch convolution-enhanced deep reinforcement learning (VRP-GENSC-DRL) algorithm. The proposed algorithm integrates viewpoint rotation prediction (VRP) using long short-term memory (LSTM) to convert dynamic bandwidth demands into static requirements, a graph neural network (GNN) with edge-node switch convolution for precise feature extraction, and deep reinforcement learning (DRL) for optimized baseband function deployment and holographic RSA. Simulation results indicate that VRP-GENSC-DRL reduces the total number of active processing nodes and consumption of spectrum bandwidth by approximately 50% compared to benchmarks without VRP, effectively addressing the challenges of HTC service delivery.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 5","pages":"425-438"},"PeriodicalIF":4.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888400","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}

{"title":"Characterizing the ODN for a PON using longitudinal power monitoring and simplified coherent receivers","authors":"Chenxi Tan;Istvan Bence Kovacs;Seb J. Savory","doi":"10.1364/JOCN.550082","DOIUrl":"https://doi.org/10.1364/JOCN.550082","url":null,"abstract":"As passive optical networks (PONs) evolve to meet rising demands in bandwidth and quality of service, accurately monitoring power profiles and thus characterizing the optical distribution network (ODN) has become critically important. This paper first demonstrates the longitudinal power monitoring model for simplified coherent PONs using the regularized linear least squares method with piecewise linear fitting to monitor the power evolution and detect losses along the fiber link. The well-selected regularization was verified to be effective in solving the PON-specific ill-posed problem and mitigating the effects of noise to give a stable solution for longitudinal power monitoring. The proposed model was first verified for single-loss events in the simulation and experiment. Simulation results indicate a maximum quantification error of 0.04 dB and a localization error of 0.10 km under various single-loss insertion scenarios. In the experiment, the single-loss insertion was identified without prior knowledge of the number of losses, achieving maximum quantification and localization errors of 0.14 dB and 0.25 km, respectively, thus demonstrating high loss detection accuracy. The proposed model was also extended to multiple-loss detection, and the simulation results indicate its potential applicability in characterizing the ODN for simplified coherent PONs in practical deployments.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 8","pages":"C93-C104"},"PeriodicalIF":4.0,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143888297","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}

{"title":"Experimental demonstration of local AI-Agents for lifecycle management and control automation of optical networks","authors":"Chenyu Sun;Xin Yang;Nicola Di Cicco;Reda Ayassi;Venkata Virajit Garbhapu;Photios A. Stavrou;Massimo Tornatore;Gabriel Charlet;Yvan Pointurier","doi":"10.1364/JOCN.550286","DOIUrl":"https://doi.org/10.1364/JOCN.550286","url":null,"abstract":"This paper presents an innovative approach to automating the full lifecycle management of optical networks using locally fine-tuned large language models (LLMs) and digital twin technologies. We experimentally demonstrate the integration of generative AI and digital twins to create powerful AI-Agents capable of handling the design, deployment, maintenance, and upgrade phases in the lifecycle of optical networks. By deploying and fine-tuning LLMs locally, our framework eliminates the need for public cloud services, thereby ensuring data privacy and security. The experimental setup includes a commercial-product-based testbed with eight optical multiplex sections in the C-band, showcasing the effectiveness of the AI-Agents in various automation tasks, such as API-calling for service establishment and periodic power equalization, as well as log analysis for troubleshooting. The results highlight significant improvements in operational accuracy and efficiency, underscoring the feasibility of this approach in real-world scenarios. This work represents a significant advancement toward intent-based networking, showcasing the transformative potential of AI in automating and optimizing optical network operations.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 8","pages":"C82-C92"},"PeriodicalIF":4.0,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143875246","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}

{"title":"Data transfer method combining erasure coding and cumulative decoding-status feedback: demonstration on an optical packet-switching network testbed","authors":"Maho Ono;Yuusuke Hashimoto;Yuya Seki;Yosuke Tanigawa;Yusuke Hirota;Hideki Tode","doi":"10.1364/JOCN.550555","DOIUrl":"https://doi.org/10.1364/JOCN.550555","url":null,"abstract":"Optical packet-switching (OPS) networks remain an emerging technology, as exemplified by the feasibility challenges of optical RAM. Nevertheless, OPS networks possess significant potential advantages, including a high data transfer rate and low power consumption due to the elimination of optical–electrical–optical conversion, compared to conventional electronic packet-switching networks, flexibility in handling traffic fluctuations due to packet-switching principles, and low latency as they do not require overhead for communication path establishment. However, effective data recovery from non-negligible packet loss due to optical packet collisions remains a critical challenge in OPS networks. Packet-level forward error correction (FEC) is regarded as an effective data recovery method for lossy networks, such as OPS ones, because it does not rely on packet-by-packet feedback, which could be lost, and avoids the delays associated with feedback and retransmission. On the other hand, FEC requires the transmission of additional packets beyond the original data, increasing the computational load associated with encoding and decoding. In this paper, we propose a data transfer method based on erasure coding, which is useful not only in OPS networks but also in other network environments suffering from severe packet loss due to collisions or signal degradation, such as optical circuit switching networks and wireless networks. This method improves effective data transfer throughput by limiting the number of transmitted packets and reducing the computational overhead of the encoding and decoding processes. This improvement is achieved through the appropriate configuration of the distribution of XOR operation target packets that constitute XOR packets, thereby restricting the number of symbols encoded in each XOR operation and introducing cumulative feedback of which symbols were already recovered at the receiver. To validate the proposed method, we conducted not only simulation evaluations but also what we believe to be the world’s first packet transmission demonstration experiment using packet-level erasure coding over an actual OPS network testbed, taking actual computational overhead into account. The experimental results show that, in high transmission rate environments, the proposed method achieves up to a 188.7% increase in effective data transfer throughput compared to the benchmark LT-Codes-based packet-level FEC transmission method while reducing the processing time on the sender side by up to 15.6% and on the receiver side by up to 39.4%. In addition, the number of packets required for data decoding can be reduced by up to 63.3%.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 5","pages":"412-424"},"PeriodicalIF":4.0,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143871083","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}

{"title":"End-to-end transport network digital twins with cloud-native SDN controllers and generative AI [Invited]","authors":"Allen Abishek;Daniel Adanza;Pol Alemany;Lluis Gifre;Ramon Casellas;Ricardo Martinez;Raul Munoz;Ricard Vilalta","doi":"10.1364/JOCN.550864","DOIUrl":"https://doi.org/10.1364/JOCN.550864","url":null,"abstract":"This paper explores the potential of network digital twins (NDTs) in networking (both IP Ethernet networks and optical transport networks), highlighting their integration with cloud-native software-defined networking (SDN) controllers and intent-based networking enabled by generative artificial intelligence (GenAI). The proposed framework represents an approach that combines advanced virtualization, real-time analytics, and GenAI. The use of NDTs enables a comprehensive and dynamic digital representation of the physical network, capturing critical aspects, such as topology, traffic patterns, and performance metrics, which permits data-driven decision-making to lead to more efficient networking operations. The incorporation of cloud-native SDN controllers along with an NDT ensures that the system remains scalable, flexible, and responsive to dynamic network conditions. Intent-based networking, powered by GenAI, allows the network to interpret high-level objectives from operators and autonomously translate them into actionable configurations that are enforced by orchestrators and SDN controllers. This eliminates manual intervention, minimizes errors, accelerates the deployment of network services, and provides a means for easier network management. The presented framework significantly enhances automation, enabling predictive maintenance by identifying potential issues before they impact network performance. It optimizes network design by simulating various configurations and testing their feasibility in a risk-free environment. These capabilities collectively improve operational efficiency, reduce downtime, and ensure optimal resource utilization.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 7","pages":"C70-C81"},"PeriodicalIF":4.0,"publicationDate":"2025-04-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865242","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}

{"title":"Transmission performance of an MDM switching node with FM-EDFAs for high-speed DP-QPSK signals","authors":"Wei Yan;Baojian Wu;Yuhang Wang;Xiaoshi Lv;Feng Wen;Kun Qiu","doi":"10.1364/JOCN.553693","DOIUrl":"https://doi.org/10.1364/JOCN.553693","url":null,"abstract":"Mode division multiplexing (MDM) technology has been extensively investigated for improving the fiber transmission capacity. The researchers have started to devote their energies to multi-dimensional optical switching nodes compatible with spatial modes. We focus on a promising MDM switching node based on wavelength-selective switches and evaluate its crosstalk performance by the power transfer matrix method. The simulation shows that the number of cascaded nodes permitted for error-free transmission exponentially decreases with the crosstalk increase of the mode demultiplexers/multiplexers. An MDM switching node supporting four linearly polarized modes is constructed using homemade four-mode erbium-doped fiber amplifiers for the transmission of 100 Gb/s dual-polarization quadrate phase shift keying signals. The experimental results show that the receiver sensitivity degradation of all channels in DROP, ADD, EXPRESS, and EXCHANGE scenarios is no more than 2, 4.4, 6.4, and 6 dB compared with the back-to-back cases, respectively.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 5","pages":"392-400"},"PeriodicalIF":4.0,"publicationDate":"2025-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830517","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}

{"title":"SDN-enabled CV-QKD and classical channels coexistence: key insights for dense wavelength division multiplexing","authors":"Masab Iqbal;Michela Svaluto Moreolo;Raul Munoz;Laia Nadal;Arturo Villegas;Jose Manuel Rivas-Moscoso;Samael Sarmiento;Antonio Melgar;Pol Adillon;Jeison Tabares;Sebastian Etcheverry","doi":"10.1364/JOCN.553157","DOIUrl":"https://doi.org/10.1364/JOCN.553157","url":null,"abstract":"In this paper, we explored various physical-layer parameters affecting the coexistence of continuous-variable quantum key distribution (CV-QKD) and classical channels (CCs) within dense wavelength division multiplexing (DWDM) in the C-band. These parameters include the number of transmitted quantum symbols, power levels of CCs, quantum channel (QC) allocation within the C-band, power distribution among CCs, channel spacing between CCs and the QC, and CC power ranges suitable for both CCs and the QC. These insights provide valuable guidance for a software-defined networking (SDN) control system to manage CV-QKD and CC coexistence effectively. We observed that, for short distances and lower key rates, the number of quantum symbols exchanged does not need to reach the asymptotic convergence limit. However, achieving the asymptotic regime on a 10 km link requires transmitting approximately <tex>${1} times {{10}^{13}}$</tex> quantum symbols. CC power significantly impacts CV-QKD performance. For example, in a DWDM setup with 37 dummy CCs on a 100 GHz grid, CV-QKD can support up to 11 dBm total launch power over a 10 km link when the QC is positioned at 193.2 THz and a 200 GHz channel spacing between the QC and CCs is maintained. Strategic placement of the QC within the C-band also enhances performance. Placing the QC at higher frequency channels relative to CCs improves both the secret key fraction and the maximum supported power of CCs. For instance, placing the QC at 195.9 THz provides better performance than positioning it at 193.2 or 192.2 THz. However, when the QC is placed at 192.2 THz, the maximum supported CC power reduces to 9.8 dBm. Additionally, the relationship between power distribution and power concentration is complex and requires careful consideration. It depends on the number of active CCs, the power of CCs, and their spectral placement relative to the QC. We also analyzed the case of <tex>${8} times {200}{rm G}$</tex> modulated CCs and found that placing them 100 GHz from the QC introduces nonlinear noise but still allows a positive secret key fraction. Increasing the spacing to 200 GHz further improves CV-QKD performance. Joint performance analysis revealed that, at a 100 GHz spacing and a 30 dB optical signal-to-noise ratio for CCs, a launch power range of <tex>${-}{16.96}$</tex> to 9.03 dBm supports both error-free CC recovery and positive key rate generation over a 10 km link. This comprehensive analysis highlights the interplay between CV-QKD and CCs, offering practical strategies for optimizing their coexistence in DWDM systems through an SDN control system.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 6","pages":"B28-B37"},"PeriodicalIF":4.0,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817852","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}