Reliable quality of transmission (QoT) prediction is essential to ensure that services operate near their optimal working point, maximizing network capacity and efficiency while avoiding large design margins. A major source of QoT prediction error lies in the uncertain modeling of nonlinear fiber impairments, particularly the Kerr effect and stimulated Raman scattering, which are difficult to monitor with existing hardware. Accurate modeling of these effects requires knowledge of fiber insertion loss. Additionally, the gain spectrum of optical amplifiers, which governs amplified spontaneous emission noise, is not directly monitored. Further uncertainties stem from service end-to-end impairments, including wavelength selective switch (WSS) filtering-induced noise and from device-specific back-to-back (B2B) transponder performance, both of which are typically unknown at deployment time. To address these challenges, we propose incremental learning-based input refinement (IIR), a parameter estimation method that leverages multiple network snapshots to jointly refine fiber insertion losses, amplifier gain spectra, and end-to-end offset noise (comprising WSS filtering and transponder B2B contributions). IIR is applied incrementally during routine, live network (re-)optimization, requiring no intrusive measurements. The proposed method is validated through (1) simulations using experimental data on a C-band ring network and (2) experimental validation on a C-band mesh network. Results show that IIR significantly improves the estimation of key physical-layer parameters, enhancing QoT prediction accuracy and enabling effective closed-loop power optimization.
{"title":"Input refinement with incremental learning for accurate digital twin-enabled self-driven QoT optimization in optical networks","authors":"Xin Yang;Chenyu Sun;Reda Ayassi;Louis Aknin;Gabriel Charlet;Massimo Tornatore;Yvan Pointurier","doi":"10.1364/JOCN.575280","DOIUrl":"https://doi.org/10.1364/JOCN.575280","url":null,"abstract":"Reliable quality of transmission (QoT) prediction is essential to ensure that services operate near their optimal working point, maximizing network capacity and efficiency while avoiding large design margins. A major source of QoT prediction error lies in the uncertain modeling of nonlinear fiber impairments, particularly the Kerr effect and stimulated Raman scattering, which are difficult to monitor with existing hardware. Accurate modeling of these effects requires knowledge of fiber insertion loss. Additionally, the gain spectrum of optical amplifiers, which governs amplified spontaneous emission noise, is not directly monitored. Further uncertainties stem from service end-to-end impairments, including wavelength selective switch (WSS) filtering-induced noise and from device-specific back-to-back (B2B) transponder performance, both of which are typically unknown at deployment time. To address these challenges, we propose incremental learning-based input refinement (IIR), a parameter estimation method that leverages multiple network snapshots to jointly refine fiber insertion losses, amplifier gain spectra, and end-to-end offset noise (comprising WSS filtering and transponder B2B contributions). IIR is applied incrementally during routine, live network (re-)optimization, requiring no intrusive measurements. The proposed method is validated through (1) simulations using experimental data on a C-band ring network and (2) experimental validation on a C-band mesh network. Results show that IIR significantly improves the estimation of key physical-layer parameters, enhancing QoT prediction accuracy and enabling effective closed-loop power optimization.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 1","pages":"A75-A87"},"PeriodicalIF":4.3,"publicationDate":"2025-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145778203","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}
The satellite–ground integrated optical network (SGION) is a key architecture for achieving global access and end-to-end low-latency communication, and it is also deemed a foundation of the 6G mobile network. The lifespan of satellites is primarily determined by the charge–discharge cycles of onboard batteries. Due to orbital motion, satellites in Earth’s shadow cannot harvest energy from solar panels and therefore must continuously discharge their batteries until they re-enter sunlight. Excessive battery discharge for communication tasks during shadow periods accelerates battery aging. To prevent network-wide lifespan degradation caused by over-discharge in shadow regions, this paper establishes a lifespan-consumption model and proposes an energy-efficient scheduling algorithm for satellite laser terminals, as well as an energy-efficient routing algorithm based on space–ground cooperation for SGIONs. We evaluate the proposed routing algorithm via extensive simulations on Walker constellations with 72, 288, and 1152 satellites. Compared with the shortest-path algorithm, the proposed method decreases the overall satellite lifespan consumption by 43.83%, reduces the maximum per-satellite consumption by 40.87%, increases the latency by 0.3 ms, and increases the blockage rate by 0.1%.
{"title":"Energy-efficient routing based on satellite–ground cooperation in optical satellite networks","authors":"Zijian Cui;Wei Wang;Xin Li;Liyazhou Hu;Yongli Zhao;Jie Zhang","doi":"10.1364/JOCN.567925","DOIUrl":"https://doi.org/10.1364/JOCN.567925","url":null,"abstract":"The satellite–ground integrated optical network (SGION) is a key architecture for achieving global access and end-to-end low-latency communication, and it is also deemed a foundation of the 6G mobile network. The lifespan of satellites is primarily determined by the charge–discharge cycles of onboard batteries. Due to orbital motion, satellites in Earth’s shadow cannot harvest energy from solar panels and therefore must continuously discharge their batteries until they re-enter sunlight. Excessive battery discharge for communication tasks during shadow periods accelerates battery aging. To prevent network-wide lifespan degradation caused by over-discharge in shadow regions, this paper establishes a lifespan-consumption model and proposes an energy-efficient scheduling algorithm for satellite laser terminals, as well as an energy-efficient routing algorithm based on space–ground cooperation for SGIONs. We evaluate the proposed routing algorithm via extensive simulations on Walker constellations with 72, 288, and 1152 satellites. Compared with the shortest-path algorithm, the proposed method decreases the overall satellite lifespan consumption by 43.83%, reduces the maximum per-satellite consumption by 40.87%, increases the latency by 0.3 ms, and increases the blockage rate by 0.1%.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"1176-1188"},"PeriodicalIF":4.3,"publicationDate":"2025-12-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145674854","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 is crucial for optimizing optical network planning and operation. Machine learning has attracted attention as a promising scheme for QoT estimation. Usually, it is difficult to obtain a large amount of optical path data due to environmental and cost constraints. The data collection difficulties can be mitigated by transfer learning (TL) that leverages knowledge across domains. However, the QoT estimation model’s performance will degrade when the data distribution between the source and target domains is significantly different. Therefore, this paper proposes a domain discrepancy feedback optimization (DDFO) method to improve the QoT estimation accuracy under few-sample conditions. Within the proposed method, first, a dual-branch neural network with shared weights is constructed to learn from both the source and target domains jointly. Subsequently, an adaptive alignment layer is introduced to measure the feature distribution discrepancy between domains. Finally, the discrepancy loss is incorporated into the overall loss function to guide model training through the feedback mechanism. Simulation results show that the performance of the DDFO method demonstrates an improvement ranging from 26.38% to 42.65% compared with traditional artificial neural networks, TL, and sample-distribution-matching-based transfer learning in diverse network topology scenarios. DDFO demonstrates strong generalization and superior performance in few-sample QoT estimation, making it a promising solution for practical optical network optimization.
{"title":"Domain discrepancy feedback optimization method for few-sample QoT estimation in optical networks","authors":"Xiaobo Zuo;Zhiqun Gu;Shihao Fan;Danping Ren;Zhongcheng Wei;Nan Feng;Jijun Zhao","doi":"10.1364/JOCN.572972","DOIUrl":"https://doi.org/10.1364/JOCN.572972","url":null,"abstract":"Accurate quality of transmission (QoT) estimation is crucial for optimizing optical network planning and operation. Machine learning has attracted attention as a promising scheme for QoT estimation. Usually, it is difficult to obtain a large amount of optical path data due to environmental and cost constraints. The data collection difficulties can be mitigated by transfer learning (TL) that leverages knowledge across domains. However, the QoT estimation model’s performance will degrade when the data distribution between the source and target domains is significantly different. Therefore, this paper proposes a domain discrepancy feedback optimization (DDFO) method to improve the QoT estimation accuracy under few-sample conditions. Within the proposed method, first, a dual-branch neural network with shared weights is constructed to learn from both the source and target domains jointly. Subsequently, an adaptive alignment layer is introduced to measure the feature distribution discrepancy between domains. Finally, the discrepancy loss is incorporated into the overall loss function to guide model training through the feedback mechanism. Simulation results show that the performance of the DDFO method demonstrates an improvement ranging from 26.38% to 42.65% compared with traditional artificial neural networks, TL, and sample-distribution-matching-based transfer learning in diverse network topology scenarios. DDFO demonstrates strong generalization and superior performance in few-sample QoT estimation, making it a promising solution for practical optical network optimization.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"1161-1175"},"PeriodicalIF":4.3,"publicationDate":"2025-11-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612054","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 forecasting of optical network telemetry is critical for enabling predictive maintenance and proactive network management. However, conventional forecasting approaches often rely on task-specific architectures, extensive labeled datasets, and manual feature engineering—factors that limit their adaptability and scalability across heterogeneous deployment scenarios. In this work, we introduce a zero-shot forecasting framework that leverages pretrained large language models (LLMs) to perform prompt-based inference directly on telemetry data without requiring fine tuning, retraining, or supervision. Time series signals are tokenized at the digit level and reformulated as structured language sequences, enabling LLMs to perform forecasting, anomaly detection, and missing data imputation using natural language prompts. We evaluate our approach on real-world measurements from an aerial WDM system—comprising PM and SOP data under live traffic and varying environmental conditions—as well as on other out-of-distribution datasets. LLM demonstrates good forecasting accuracy and robustness to noise, missing inputs, and domain shifts, achieving performance that is competitive with classical and deep learning baselines across a range of metrics and conditions. Crucially, the model generalizes across multivariate and multimodal telemetry streams without architectural modification, enabling accurate forecasting from exogenous signals such as environmental variables. These results position instruction-tuned LLMs as lightweight, interpretable, and scalable building blocks for next-generation telemetry analytics—offering a unified, prompt-driven alternative to fragmented and model-centric forecasting pipelines.
{"title":"Zero-shot forecasting of optical network telemetry using large language models","authors":"Khouloud Abdelli","doi":"10.1364/JOCN.575791","DOIUrl":"https://doi.org/10.1364/JOCN.575791","url":null,"abstract":"Accurate forecasting of optical network telemetry is critical for enabling predictive maintenance and proactive network management. However, conventional forecasting approaches often rely on task-specific architectures, extensive labeled datasets, and manual feature engineering—factors that limit their adaptability and scalability across heterogeneous deployment scenarios. In this work, we introduce a zero-shot forecasting framework that leverages pretrained large language models (LLMs) to perform prompt-based inference directly on telemetry data without requiring fine tuning, retraining, or supervision. Time series signals are tokenized at the digit level and reformulated as structured language sequences, enabling LLMs to perform forecasting, anomaly detection, and missing data imputation using natural language prompts. We evaluate our approach on real-world measurements from an aerial WDM system—comprising PM and SOP data under live traffic and varying environmental conditions—as well as on other out-of-distribution datasets. LLM demonstrates good forecasting accuracy and robustness to noise, missing inputs, and domain shifts, achieving performance that is competitive with classical and deep learning baselines across a range of metrics and conditions. Crucially, the model generalizes across multivariate and multimodal telemetry streams without architectural modification, enabling accurate forecasting from exogenous signals such as environmental variables. These results position instruction-tuned LLMs as lightweight, interpretable, and scalable building blocks for next-generation telemetry analytics—offering a unified, prompt-driven alternative to fragmented and model-centric forecasting pipelines.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"1148-1160"},"PeriodicalIF":4.3,"publicationDate":"2025-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612050","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}
Miao Zhu;Rentao Gu;Jiangshan Dong;Lin Bai;Hui Li;Yuefeng Ji
The exponential growth of global network traffic has made the expansion of network capacity increasingly urgent. Multi-band and flexible grid technologies have emerged as promising solutions to enhance network transmission capacity. Fast routing is an important measure to ensure the survivability of a multi-band flexible optical network (MB-FON) that carries massive services. However, the extensive network resources and the inter-channel stimulated Raman scattering (ISRS) effect between different bands pose a challenge to the efficient solution of classical routing, modulation, and spectrum allocation (RMSA) methods. This paper leverages the parallel computing advantage of quantum computing and proposes a hybrid quantum-classical computing mechanism for quality of transmission (QoT)-aware dynamic RMSA in MB-FON. In this mechanism, a decouple-then-integrate strategy is proposed to formulate the QoT-aware RMSA problem as a quadratic unconstrained binary optimization model. The augmented Lagrangian method is introduced to deal with the inequality constraint in an ISRS-aware formulation, and a path fragmentation metric is proposed to design the optimization objective. In addition, a coherent Ising machine is used to solve the problem by adjusting the parameters and precision in combination with classical computing methods. Experiments were conducted on network topologies of different sizes. The experimental results show that the solution time can be reduced from nearly 6 s to 537 µs compared with the auxiliary graph-based heuristic algorithm in a 142-node network. It also demonstrates that the proposed mechanism outperforms classical heuristic algorithms in terms of blocking probability and spectrum utilization.
{"title":"Hybrid quantum-classical computing mechanism for QoT-aware dynamic routing, modulation, and spectrum allocation in a multi-band flexible optical network","authors":"Miao Zhu;Rentao Gu;Jiangshan Dong;Lin Bai;Hui Li;Yuefeng Ji","doi":"10.1364/JOCN.572283","DOIUrl":"https://doi.org/10.1364/JOCN.572283","url":null,"abstract":"The exponential growth of global network traffic has made the expansion of network capacity increasingly urgent. Multi-band and flexible grid technologies have emerged as promising solutions to enhance network transmission capacity. Fast routing is an important measure to ensure the survivability of a multi-band flexible optical network (MB-FON) that carries massive services. However, the extensive network resources and the inter-channel stimulated Raman scattering (ISRS) effect between different bands pose a challenge to the efficient solution of classical routing, modulation, and spectrum allocation (RMSA) methods. This paper leverages the parallel computing advantage of quantum computing and proposes a hybrid quantum-classical computing mechanism for quality of transmission (QoT)-aware dynamic RMSA in MB-FON. In this mechanism, a decouple-then-integrate strategy is proposed to formulate the QoT-aware RMSA problem as a quadratic unconstrained binary optimization model. The augmented Lagrangian method is introduced to deal with the inequality constraint in an ISRS-aware formulation, and a path fragmentation metric is proposed to design the optimization objective. In addition, a coherent Ising machine is used to solve the problem by adjusting the parameters and precision in combination with classical computing methods. Experiments were conducted on network topologies of different sizes. The experimental results show that the solution time can be reduced from nearly 6 s to 537 µs compared with the auxiliary graph-based heuristic algorithm in a 142-node network. It also demonstrates that the proposed mechanism outperforms classical heuristic algorithms in terms of blocking probability and spectrum utilization.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 1","pages":"A60-A74"},"PeriodicalIF":4.3,"publicationDate":"2025-11-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612156","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}
Luis Vallejo;Jose Mora;Wei Jin;Jaime Romero-Huedo;Lin Chen;Jianming Tang;Beatriz Ortega
To address the unprecedented technical challenges arising from ultra-dense cellular network deployment for applications in densely populated urban areas envisioned for 6G, this paper proposes and experimentally demonstrates a novel, to our knowledge, centralized bidirectional heterogeneous access network with advanced baseband unit (BBU) pooling and cost-effective remote radio head (RRH) designs free from both lasers and digital signal processing (DSP). The network supports flexible deployments of fiber, free space optical (FSO), and millimeter wave (mmWave) segments, thus ensuring ubiquitous network connectivity. More importantly, it also seamlessly converges various network segments (fiber, FSO, and mmWave) and enables their uplink (UL) and downlink (DL) signals to concurrently and continuously flow between the BBU and user equipment (UE) without requiring optical-electrical/electrical-optical conversions and/or DSPs at any intermediate nodes. In the proposed network, DL mmWave signals are generated and detected using a free-running laser and a passive envelope detection. For the UL case, conventional electrical local oscillators and mixers are used for mmWave up-conversion and down-conversion. The performances of the proposed networks, including UL/DL channel interferences and achievable throughputs, are experimentally evaluated over a fiber-FSO-mmWave setup with 10 km fiber, 1.8 m FSO, and 3 m mmWave links (39 GHz/0.4 Gbit/s for DL, 36.5 GHz/0.2 Gbit/s for UL). The experimental results show robust bidirectional transmissions with negligible UL/DL interferences and minimal impacts from Rayleigh and Brillouin backscattering.
为了解决在人口密集的城市地区部署超密集蜂窝网络所带来的前所未有的技术挑战，本文提出并实验证明了一种新颖的，据我们所知，具有先进基带单元（BBU）池和具有成本效益的远程无线电头（RRH）设计的双向异构接入网，不需要激光和数字信号处理（DSP）。该网络支持光纤、自由空间光（FSO）和毫米波（mmWave）的灵活部署，从而确保无处不在的网络连接。更重要的是，它还可以无缝地汇聚各种网段（光纤、FSO和毫米波），并使其上行（UL）和下行（DL）信号能够在BBU和用户设备（UE）之间并发地连续流动，而无需在任何中间节点进行光电/电光转换和/或dsp。在提出的网络中，使用自由运行激光器和被动包络检测产生和检测DL毫米波信号。对于UL案例，传统的电气本地振荡器和混频器用于毫米波上变频和下变频。所提出的网络的性能，包括UL/DL信道干扰和可实现的吞吐量，在光纤-FSO-毫米波设置下进行了实验评估，该设置具有10公里光纤，1.8 m FSO和3 m毫米波链路（DL为39 GHz/0.4 Gbit/s， UL为36.5 GHz/0.2 Gbit/s）。实验结果表明，该方法具有较强的双向传输能力，可忽略UL/DL干扰，且瑞利散射和布里渊散射的影响最小。
{"title":"Centralized bidirectional heterogeneous fiber-FSO-mmWave-converged networks for 6G dense cellular network deployments","authors":"Luis Vallejo;Jose Mora;Wei Jin;Jaime Romero-Huedo;Lin Chen;Jianming Tang;Beatriz Ortega","doi":"10.1364/JOCN.571969","DOIUrl":"https://doi.org/10.1364/JOCN.571969","url":null,"abstract":"To address the unprecedented technical challenges arising from ultra-dense cellular network deployment for applications in densely populated urban areas envisioned for 6G, this paper proposes and experimentally demonstrates a novel, to our knowledge, centralized bidirectional heterogeneous access network with advanced baseband unit (BBU) pooling and cost-effective remote radio head (RRH) designs free from both lasers and digital signal processing (DSP). The network supports flexible deployments of fiber, free space optical (FSO), and millimeter wave (mmWave) segments, thus ensuring ubiquitous network connectivity. More importantly, it also seamlessly converges various network segments (fiber, FSO, and mmWave) and enables their uplink (UL) and downlink (DL) signals to concurrently and continuously flow between the BBU and user equipment (UE) without requiring optical-electrical/electrical-optical conversions and/or DSPs at any intermediate nodes. In the proposed network, DL mmWave signals are generated and detected using a free-running laser and a passive envelope detection. For the UL case, conventional electrical local oscillators and mixers are used for mmWave up-conversion and down-conversion. The performances of the proposed networks, including UL/DL channel interferences and achievable throughputs, are experimentally evaluated over a fiber-FSO-mmWave setup with 10 km fiber, 1.8 m FSO, and 3 m mmWave links (39 GHz/0.4 Gbit/s for DL, 36.5 GHz/0.2 Gbit/s for UL). The experimental results show robust bidirectional transmissions with negligible UL/DL interferences and minimal impacts from Rayleigh and Brillouin backscattering.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"1136-1147"},"PeriodicalIF":4.3,"publicationDate":"2025-11-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145612043","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}
We develop four different quadratic unconstrained binary optimization formulations of routing problems relevant to the optical transport layers in telecommunications networks. Our formulations handle joint routing and wavelength assignment, unicast, multicast trees, and shared risk avoidance. We show that this approach is viable, even for multicast, and we test and compare the effectiveness of each formulation at solving these problems using the DWave hybrid solver. We describe expedients we applied to ensure valid solutions, along with challenges of the QUBO approach.
{"title":"Routing and wavelength assignment problems in optical networks—comparing formulations for solution by quantum annealing","authors":"Ethan Davies;Darren Banfield;Ben Weaver;Catherine White;Nigel Walker","doi":"10.1364/JOCN.553657","DOIUrl":"https://doi.org/10.1364/JOCN.553657","url":null,"abstract":"We develop four different quadratic unconstrained binary optimization formulations of routing problems relevant to the optical transport layers in telecommunications networks. Our formulations handle joint routing and wavelength assignment, unicast, multicast trees, and shared risk avoidance. We show that this approach is viable, even for multicast, and we test and compare the effectiveness of each formulation at solving these problems using the DWave hybrid solver. We describe expedients we applied to ensure valid solutions, along with challenges of the QUBO approach.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"B83-B91"},"PeriodicalIF":4.3,"publicationDate":"2025-11-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560818","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}
Optical power optimization is essential for improving the quality of transmission (QoT) in autonomous optical networks (AONs). However, online optical power optimization is challenging due to the potential performance degradation and even service disruption caused by exploratory adjustments. In this paper, we propose TrustOPT, a trusted online optimization strategy for reliable optical power optimization in AONs. By leveraging the Lipschitz constant (L-constant), TrustOPT defines an evolving trusted configuration space, ensuring that the QoT can remain above the required threshold even under worst-case degradation after each adjustment. Within the trusted space, advanced optimization algorithms are employed to efficiently optimize optical amplifier (OA) configurations for improved QoT. TrustOPT is validated on a field-deployed testbed with live services. Field-trial results demonstrate that TrustOPT achieves optimal optical power while maintaining a 4 dB Q-factor margin, even in a challenging scenario with only a 0.15 dB initial Q-factor margin. Compared with established optimization strategies, TrustOPT achieves superior performance in both optimization results and processes. Specifically, in terms of worst-case Q-factor during optimization, TrustOPT outperforms Bayesian optimization by over 4.73 dB, significantly enhancing the optimization reliability. Moreover, a strong agreement between the estimated and field-measured L-constants is observed, further verifying the reliability and practical effectiveness of the proposed approach. TrustOPT thus provides a robust and practical solution for achieving reliable online optical power optimization in future AONs.
光功率优化是提高自主光网络传输质量的关键。然而，由于探索性调整可能导致性能下降甚至业务中断，在线光功率优化具有挑战性。本文提出了一种可信任的在线优化策略TrustOPT，用于aon的可靠光功率优化。通过利用Lipschitz常数（L-constant）， TrustOPT定义了一个不断发展的可信配置空间，确保即使在每次调整后的最坏情况下，QoT也能保持在所需的阈值之上。在可信空间内，采用先进的优化算法对光放大器（OA）的配置进行有效优化，以提高QoT。TrustOPT在现场部署的测试平台上进行了验证。现场试验结果表明，即使在初始q因子裕度仅为0.15 dB的具有挑战性的情况下，TrustOPT也能在保持4 dB q因子裕度的情况下实现最佳光功率。与已有的优化策略相比，TrustOPT在优化结果和优化过程上都具有优越的性能。具体而言，在优化过程中的最坏情况q因子方面，TrustOPT优于贝叶斯优化超过4.73 dB，显著提高了优化可靠性。此外，估计的l -常数与现场测量的l -常数之间有很强的一致性，进一步验证了所提出方法的可靠性和实用性。因此，TrustOPT为未来aon实现可靠的在线光功率优化提供了一个强大而实用的解决方案。
{"title":"TrustOPT: a trusted online optimization strategy for reliable autonomous optical networks with field-trial demonstration","authors":"Qizhi Qiu;Xiaomin Liu;Yihao Zhang;Lilin Yi;Weisheng Hu;Qunbi Zhuge","doi":"10.1364/JOCN.572249","DOIUrl":"https://doi.org/10.1364/JOCN.572249","url":null,"abstract":"Optical power optimization is essential for improving the quality of transmission (QoT) in autonomous optical networks (AONs). However, online optical power optimization is challenging due to the potential performance degradation and even service disruption caused by exploratory adjustments. In this paper, we propose TrustOPT, a trusted online optimization strategy for reliable optical power optimization in AONs. By leveraging the Lipschitz constant (L-constant), TrustOPT defines an evolving trusted configuration space, ensuring that the QoT can remain above the required threshold even under worst-case degradation after each adjustment. Within the trusted space, advanced optimization algorithms are employed to efficiently optimize optical amplifier (OA) configurations for improved QoT. TrustOPT is validated on a field-deployed testbed with live services. Field-trial results demonstrate that TrustOPT achieves optimal optical power while maintaining a 4 dB Q-factor margin, even in a challenging scenario with only a 0.15 dB initial Q-factor margin. Compared with established optimization strategies, TrustOPT achieves superior performance in both optimization results and processes. Specifically, in terms of worst-case Q-factor during optimization, TrustOPT outperforms Bayesian optimization by over 4.73 dB, significantly enhancing the optimization reliability. Moreover, a strong agreement between the estimated and field-measured L-constants is observed, further verifying the reliability and practical effectiveness of the proposed approach. TrustOPT thus provides a robust and practical solution for achieving reliable online optical power optimization in future AONs.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 1","pages":"A44-A53"},"PeriodicalIF":4.3,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560753","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}
To reduce the effect of inter-channel stimulated Raman scattering in multi-band transmission, we propose a method to pre-equalize the input power to a transmission line solely on the basis of basic optical fiber parameters and the number of accommodated wavelengths in multi-band transmission using two wavelength bands. This proposed method was applied to an optical fiber transmission line installed in a field environment. After four spans of transmission using a cutoff shifted fiber (G.654.E), the signal quality (Q value) was 1.9 dB higher than when the method was not applied.
{"title":"Channel power pre-equalization method in heterogeneous multi-band transmission networks [Invited]","authors":"Takeshi Seki;Haruka Minami;Rie Hayashi;Takeshi Kuwahara","doi":"10.1364/JOCN.572028","DOIUrl":"https://doi.org/10.1364/JOCN.572028","url":null,"abstract":"To reduce the effect of inter-channel stimulated Raman scattering in multi-band transmission, we propose a method to pre-equalize the input power to a transmission line solely on the basis of basic optical fiber parameters and the number of accommodated wavelengths in multi-band transmission using two wavelength bands. This proposed method was applied to an optical fiber transmission line installed in a field environment. After four spans of transmission using a cutoff shifted fiber (G.654.E), the signal quality (Q value) was 1.9 dB higher than when the method was not applied.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"18 1","pages":"A54-A59"},"PeriodicalIF":4.3,"publicationDate":"2025-11-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11262756","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560754","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}
Dongxing He;Paulina S. Kuo;Ya-Shian Li-Baboud;Anouar Rahmouni;Matthew D. Shaw;Boris A. Korzh;Thomas Gerrits
We propose a single-photon time-of-flight (ToF) measurement method to benchmark fiber-path delay estimation in optical two-way time and frequency transfer (OTWTFT) protocols. The single-photon ToF measurement yields uncertainties better than 2 ps (0.5 mm fiber-path-length uncertainty) at 1 s integration times for a deployed 120 km (loopback) fiber. Differences between the ToF and the roundtrip time measurements from a White Rabbit precision time protocol appear to correlate with the clock phase error between two White Rabbit switches. The results suggest that augmenting single-photon ToF measurements with existing OTWTFT protocols could enhance the precision to sub-10-ps levels at metropolitan distances. Such a level of precision will be critical for synchronization in quantum networks.
{"title":"Single-photon time-of-flight measurements for benchmarking time transfer in quantum networks","authors":"Dongxing He;Paulina S. Kuo;Ya-Shian Li-Baboud;Anouar Rahmouni;Matthew D. Shaw;Boris A. Korzh;Thomas Gerrits","doi":"10.1364/JOCN.577755","DOIUrl":"https://doi.org/10.1364/JOCN.577755","url":null,"abstract":"We propose a single-photon time-of-flight (ToF) measurement method to benchmark fiber-path delay estimation in optical two-way time and frequency transfer (OTWTFT) protocols. The single-photon ToF measurement yields uncertainties better than 2 ps (0.5 mm fiber-path-length uncertainty) at 1 s integration times for a deployed 120 km (loopback) fiber. Differences between the ToF and the roundtrip time measurements from a White Rabbit precision time protocol appear to correlate with the clock phase error between two White Rabbit switches. The results suggest that augmenting single-photon ToF measurements with existing OTWTFT protocols could enhance the precision to sub-10-ps levels at metropolitan distances. Such a level of precision will be critical for synchronization in quantum networks.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 12","pages":"1128-1135"},"PeriodicalIF":4.3,"publicationDate":"2025-11-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145560817","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：