Journal of Optical Communications and Networking最新文献

{"title":"CTabDDPM-based data augmentation for fault diagnosis of optical networks","authors":"Chunyu Zhang;Haijun Zhang;Weijie Yang;Bing Ye;Min Zhang;Danshi Wang","doi":"10.1364/JOCN.591406","DOIUrl":"https://doi.org/10.1364/JOCN.591406","url":null,"abstract":"Data imbalance constitutes a primary bottleneck that constrains the performance of intelligent fault-diagnosis models for optical networks. To address this challenge, a data augmentation method based on a conditional tabular denoising diffusion probabilistic model (CTabDDPM) is proposed. Accurate conditional generation is enabled by the CTabDDPM, such that samples can be generated in a fault-class-directed manner. In addition, the diffusion mechanism allows the joint data distribution to be learned progressively, thereby effectively ensuring the physical consistency of the generated data. To further enable a systematic evaluation of generative performance, a multidimensional assessment framework is established that encompasses distributional similarity, structural fidelity, and task utility. Experiments conducted on a real optical module dataset demonstrate that, under an extremely imbalanced setting (0.84%), the proposed method achieves a diagnostic accuracy of 0.9987 and an F1 score of 0.9788, while the false negative rate and false positive rate are reduced to 0.0107 and 0.0304, respectively. These results substantially outperform the baseline generative models, thereby validating both the effectiveness and practical value of the proposed method for improving fault diagnosis under severe class imbalance.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"820-831"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626432","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":"Dynamic routing and spectrum assignment in elastic optical networks using graph signal correlation","authors":"Mohammad Hossein Zarei;Mohammad Hadi;Mohammad Reza Pakravan","doi":"10.1364/JOCN.592663","DOIUrl":"https://doi.org/10.1364/JOCN.592663","url":null,"abstract":"Elastic optical networks (EONs) have emerged as a flexible and spectrally efficient solution for future backbone infrastructures, where dynamic routing and spectrum assignment (RSA) is a key but complex resource allocation task. Existing RSA schemes are mainly based on heuristics, mathematical optimization, or machine learning and deep reinforcement learning, often trading off blocking performance, computational complexity, and interpretability. In this paper, we propose a graph signal correlation-based RSA (GSC-RSA) scheme that exploits graph signal processing (GSP) tools to perform dynamic and proactive optical resource allocation. The physical topology is first mapped to its line graph, and both the spectrum availability and the candidate paths are modeled as graph signals defined on the line graph nodes. A correlation-based metric is then defined between path signals and spectrum availability signals constructed from contiguous slot blocks. This metric jointly captures the feasibility of each path–block pair, the path length, and the load distribution over the network. For each incoming request, GSC-RSA evaluates this metric over all candidate path–block combinations and selects the one with the highest score in a single analytic decision step. We evaluate the proposed scheme under dynamic traffic on representative EON topologies and compare it against two classical <tex>$K$</tex>-shortest-path first-fit and exact-fit heuristics and two recent fragmentation-aware RSA algorithms. Simulation results indicate that GSC-RSA can significantly reduce request and bandwidth blocking probabilities while maintaining competitive spectrum utilization and per-request computational cost compatible with online operation. These results demonstrate that GSP provides an effective and scalable framework for dynamic RSA in EONs.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"848-861"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148627100","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":"Variational autoencoder domain adaptation for cross-system generalization in ML-based SOP monitoring","authors":"Leyla Sadighi;Stefan Karlsson;Carlos Natalino;Mojtaba Eshghie;Fehmida Usmani;Eoin Kenny;Lena Wosinska;Paolo Monti;Marija Furdek;Marco Ruffini","doi":"10.1364/JOCN.598996","DOIUrl":"https://doi.org/10.1364/JOCN.598996","url":null,"abstract":"Machine learning (ML) models trained to detect physical-layer threats on one optical fiber system often fail catastrophically when applied to a different system, due to variations in operating wavelength, fiber properties, and network architecture. To overcome this, we propose a domain adaptation (DA) framework based on a variational autoencoder (VAE) that learns a shared representation capturing event signatures common to both systems while suppressing system-specific differences. The shared encoder is first trained on the combined data from two distinct optical systems: a 21 km O-band dark-fiber testbed (System 1) and a 63.4 km C-band live metro ring (System 2). The encoder is then frozen, and a classifier is trained using labels from an individual system. The proposed approach achieves 95.3% and 73.5% cross-system accuracy when moving from System 1 to System 2 and vice versa, respectively. This corresponds to gains of 83.4% and 51% over a fully supervised deep neural network (DNN) baseline trained on a single system, while preserving intra-system performance.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"C149-C159"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11631647","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148627429","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}

{"title":"Experimental demonstration of Vandermonde-structured generalized Frank sequence division multiplexing on a 1.8 Tb/s comb-based DSCM-coherent PON system","authors":"Geyang Wang;Chen Ding;Qiarong Xiao;Zijian Li;Yuan Liu;Chun-Kit Chan;Chaoran Huang;Chester Shu;Lian-Kuan Chen","doi":"10.1364/JOCN.596539","DOIUrl":"https://doi.org/10.1364/JOCN.596539","url":null,"abstract":"We propose a novel, to our knowledge, Vandermonde-structured generalized Frank sequence division multiplexing (VGFDM) scheme. The widely used discrete Fourier transform structure can be seen as the special case of our scheme. The VGFDM framework reduces the peak-to-average power ratio (PAPR), without spectral efficiency loss, and creates a uniform signal-to-noise ratio across the user and subcarrier levels. The proposed VGFDM-based digital subcarrier multiplexing passive optical network (DSCM-PON) not only achieves fast Fourier transform (FFT)-like computational complexity due to its unique structure but also dispenses with the additional inverse FFT/FFT modules required in precoding-based orthogonal frequency division multiplexing (OFDM)-PON systems. Proposed schemes redistribute impairment/noise such that grouped subcarriers exhibit similar effective SNR, thereby eliminating the need for per-subcarrier adaptive loading and enabling the use of a single encoder-decoder pair for the entire system. Experimental results from a 1.8 Tb/s optical frequency comb-based coherent DSCM-PON show a 10.8% improvement in generalized mutual information (GMI) compared to the conventional DSCM baseline with neither VGFDM nor entropy loading (EL) under the same baud rate and digital signal processing configuration, demonstrating its potential for practical high-capacity access networks. The scheme substantially reduces the complexity of the optimization algorithm, which is experimentally validated in a multi-user frequency division multiplexing PON system where maximizing the total GMI is achieved while lowering the algorithmic complexity from <tex>$text{O}(text{N}^{2})$</tex> to <tex>$text{O}(1)$</tex>.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"862-872"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148627773","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":"CD-CBA: a cross-domain communication-bound-aware resource allocation framework for pipeline-parallel distributed LLM training over dynamic multi-datacenter optical networks","authors":"Dianxuan Fu;Yihao Zhang;Xiaomin Liu;Qizhi Qiu;Yicheng Xu;Xingyu Liu;Xin Miao;Ping Du;Shikui Shen;Weisheng Hu;Qunbi Zhuge","doi":"10.1364/JOCN.600581","DOIUrl":"https://doi.org/10.1364/JOCN.600581","url":null,"abstract":"The explosive development in artificial intelligence (AI) like large language models (LLMs) requires massive graphics processing units (GPUs) during training, making distributed machine learning (DML) across multiple data centers (DCs) a practical approach to obtaining sufficient training resources. Among cross-DC DML techniques, pipeline parallelism (PP) is a natural solution, which partitions LLM layers across GPUs and orchestrates point-to-point communication between adjacent nodes. However, the high communication latency induces severe GPU idle time (“bubble”) due to poor communication and computation time overlapping in inter-DC PP. While prior works have explored partitioning and reordering computation tasks, the resource allocation for inter-DC communication between pipelined computing tasks over optical networks has been overlooked, resulting in higher GPU idle time and request congestion. Therefore, it is extremely important and challenging to propose an advanced inter-DC network resource allocation solution under the complex PP workload. In this work, we propose a cross-domain communication-bound-aware (CD-CBA) PP scheduling framework for multi-DC optical networks. Simulation results show that the proposed framework lowers the LLM training iteration time by up to 31.25%, decreases the bubble ratio by up to 11.81%, and reduces the transmission request blocking by up to 19.33%.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"873-884"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148747069","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":"QoT-aware spectral and spatial scaling trade-offs in multi-band space division multiplexing over EONs [Invited]","authors":"Arash Rezaee;Farhad Arpanaei;Ryan McCann;Laia Nadal;Jose Alberto Hernandez;Vinod M. Vokkarane","doi":"10.1364/JOCN.596854","DOIUrl":"https://doi.org/10.1364/JOCN.596854","url":null,"abstract":"Multi-band space division multiplexed (MB-SDM) elastic optical networks provide a practical path to ultra-high-capacity backbone transport by combining spectral expansion beyond the C-band with spatial multiplexing over weakly coupled multi-core fibers (MCFs). Yet, the benefits of these two scaling dimensions are strongly shaped by physical layer impairments and cannot be assessed independently. This paper presents a quality of transmission (QoT)-aware planning framework for MB-SDM backbone networks that jointly evaluates C, <tex>$text{C} +text{L}$</tex>, <tex>$text{C} +text{S}$</tex>, and <tex>$text{C} +text{L} +text{S}$</tex> transmission over 4-, 7-, 13-, and 19-core MCFs. The framework relies on a unified generalized signal-to-noise ratio model including amplified spontaneous emission, nonlinear interference, inter-channel stimulated Raman scattering, inter-core crosstalk (ICXT), transceiver limitations, and filtering and aging penalties. A QoT-aware spectral–spatial resource allocation algorithm is evaluated under dynamic traffic, where modulation formats are precomputed based on precise impairment modeling with launch power optimization, and bandwidth slicing is applied; the ICXT model is further validated through experiments on a commercial 19-core MCF. Results on the U.S. backbone topology show that the preferred band configuration depends strongly on the core count scenario. For 4- and 7-core MCFs, <tex>$text{C} +text{L}$</tex> provides better throughput and lower blocking than <tex>$text{C} +text{S}$</tex>. For 13-core MCFs, <tex>$text{C} +text{S}$</tex> becomes more effective because the L-band is more strongly affected by ICXT. For 19-core MCFs, the system becomes ICXT-dominated, causing severe degradation in C and <tex>$text{C} +text{L}$</tex>, while <tex>$text{C} +text{S}$</tex> achieves the best overall performance. Notably, despite the larger spatial resource pool, the maximum throughput in the <tex>$text{C} +text{L} +text{S}$</tex> scenario decreases from 107.94 Pbps in the 13-core case to 44.76 Pbps in the 19-core case, confirming that aggressive spatial densification can reduce usable network capacity.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"C160-C172"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148747653","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":"Uncertainty-guided Bayesian continual learning for robust nonlinear impairment estimation in evolving optical networks","authors":"Huazhi Lun;Lei Shi;Haoran Hu;Xingyu Wang;Huicun Yu;Jie Tang;Ying Liu","doi":"10.1364/JOCN.595882","DOIUrl":"https://doi.org/10.1364/JOCN.595882","url":null,"abstract":"Machine learning models for nonlinear impairment (NLI) estimation in optical networks suffer from model aging: as network conditions evolve, catastrophic forgetting causes accumulated performance degradation that neither static retraining nor one-shot fine-tuning can reliably prevent. We propose an uncertainty-guided Bayesian continual learning (CL) framework that enables an NLI estimator to sequentially adapt to new network states while preserving knowledge of prior operating regimes. By modeling network parameters as mean-field Gaussian variational posteriors, the framework enables two synergistic mechanisms from a single uncertainty signal: uncertainty-weighted regularization that softly penalizes changes to high-certainty parameters and uncertainty-based gradient masking that hard-protects the most reliable weights. We validate the framework on a multi-stage lifecycle simulation of the NSFNET topology, spanning mixed modulation formats, multiple symbol rates, and flex-grid channel spacings. The proposed method maintains stable long-term estimation accuracy throughout the sequence, substantially outperforming fine-tuning in both knowledge retention and forgetting suppression. An ablation study confirms that the two mechanisms are synergistic, jointly achieving significantly higher knowledge retention than either component alone. These results demonstrate a practical path toward trustworthy, lifelong ML estimators for autonomous optical network management.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"832-847"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626941","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":"Optical switching enabling integrated sensing and communication services in 6G networks [Invited]","authors":"Anna Tzanakaki;Markos Anastasopoulos","doi":"10.1364/JOCN.593297","DOIUrl":"https://doi.org/10.1364/JOCN.593297","url":null,"abstract":"Integrated sensing and communication (ISAC) is a key feature envisioned in 6G networks, enabling radio access infrastructures to jointly support connectivity and sensing services. To date, ISAC-related research mainly focuses on waveform design, signal processing, and radio resource optimization, while the role of the underlying transport infrastructure for networked ISAC services remains largely unexplored. In this paper, we propose a 6G-ready network architecture that enables networked ISAC through the adoption of optical transport networks in open-radio access networks (O-RANs). We introduce an optimization framework that dynamically allocates sensing and communication flows for monostatic and multi-static sensing applications, enabling sensing-aware transport reconfiguration while preserving communication service performance. The proposed concept is validated through both experimental evaluation on a 6G ISAC testbed and large-scale simulations over a metro–access WDM network. Results demonstrate that optical circuit switching enables dynamic aggregation and scheduling of sensing I/Q streams, significantly reducing optical transport resource utilization (e.g., wavelength usage and transport capacity) while maintaining high target detection probability. These findings clearly indicate that optical transport networks can be a critical enabler for scalable, efficient, and sensing-aware 6G ISAC deployments.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"C137-C148"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626894","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":"Seismic monitoring and cable supervision on optical data networks: requirements, challenges, and results","authors":"Cecilia Clivati;Renato Ambrosone;Davide Calonico;Francesco Carpentieri;Rossella Centonze;Simone Donadello;Aladino Govoni;Andre Herrero;Marianna Hovsepyan;Filippo Levi;Lucia Margheriti;Antonino Nespola;Federico Notarstefano;Stefano Straullu;Maurizio Vassallo;Emanuele Virgillito;Vittorio Curri","doi":"10.1364/JOCN.590258","DOIUrl":"https://doi.org/10.1364/JOCN.590258","url":null,"abstract":"Optical fiber sensing on deployed cables is gaining significant interest as a means to enhance network integrity and expand environmental monitoring capabilities. To fully achieve these goals, sensing signals must coexist with data transmission. While phase and state-of-polarization analysis are promising candidates for this integration, their practical exploitation presents several challenges. Because these methods measure the integrated deformation along the entire cable, sensitivity is often limited by high environmental noise floors. Furthermore, event interpretation and localization require more sophisticated analytics than conventional distributed fiber sensing. Incorporating fiber sensing into standard network architectures also necessitates a novel telemetry management system capable of handling heterogeneous datasets, high data rates, and stringent synchronization requirements. We present progress on these aspects, based on multi-year analysis of fiber-sensing data collected in field environments. Our results confirm that integrated sensing achieves the sensitivity required to detect mid- and low-magnitude seismic events within a range of tens of kilometers from the fiber, holding the potential to support seismic monitoring services in terrestrial areas. Additionally, we demonstrate the detection and localization of anomalous vibrations and anthropogenic events and the development of an autonomous anomaly-detection tool suitable for real-time alerting. Finally, we outline the requirements for an advanced network management system designed to accommodate sensing alongside conventional telemetry, supporting the transition from proof-of-concept experiments to robust, large-scale applications.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 8","pages":"C127-C136"},"PeriodicalIF":5.1,"publicationDate":"2026-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11626643","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148626926","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}

{"title":"Scalable and energy-efficient deployment of fully virtualized 10 Gb/s OLTs on multi-node GPU servers","authors":"Takahiro Suzuki;Yasuhiro Matsumoto;Jun-ichi Kani;Tatsuya Shimada","doi":"10.1364/JOCN.589733","DOIUrl":"https://doi.org/10.1364/JOCN.589733","url":null,"abstract":"To address the rapid diversification of service requirements in optical access networks while supporting legacy systems, network function virtualization (NFV) of access equipment is essential. While the utilization of virtualized systems comprising control and management layer software and whitebox optical line terminals (OLTs) is beginning to spread, studies are underway to fully virtualize OLTs, including the physical (PHY) layer, in order to further increase flexibility and efficiency. Although previous studies have demonstrated 10G-EPON functionality through parallel implementation on graphic processing units (GPUs), the evaluation was limited to the operation on a single server that did not take into account scaling, and the power consumption was excessive, at approximately 51 W per OLT. This paper proposes an architecture and lightweight resource allocation algorithms to enable scalable and energy-efficient deployment of a large number of fully virtualized 10G-EPON OLTs on multi-node GPU servers. While detailing the control architecture of the OLT processes on multi-node servers, we formulate the problem of efficiently allocating active OLTs to GPUs as a bin packing problem and solve it using heuristic approaches based on first fit and next fit algorithms. Evaluations show that 40,960 users can be accommodated on a 16-node GPU server cluster and when the traffic volume of each OLT is low, the proposed algorithm, which operates in a processing time of less than a few milliseconds, can reduce the GPU power consumption to 0.594 W per OLT by consolidating 320 OLTs into one GPU.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 7","pages":"C83-C91"},"PeriodicalIF":5.1,"publicationDate":"2026-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11581413","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148443082","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}