Scalable methods for optical transmission performance prediction using machine learning (ML) are studied in metro reconfigurable optical add-drop multiplexer (ROADM) networks. A cascaded learning framework is introduced to encompass the use of cascaded component models for end-to-end (E2E) optical path prediction augmented with different combinations of E2E performance data and models. Additional E2E optical path data and models are used to reduce the prediction error accumulation in the cascade. Off-line training (pre-trained prior to deployment) and transfer learning are used for component-level erbium-doped fiber amplifier (EDFA) gain models to ensure scalability. Considering channel power prediction, we show that the data collection process of the pre-trained EDFA model can be reduced to only 5% of the original training set using transfer learning. We evaluate the proposed method under three different topologies with field deployed fibers and achieve a mean absolute error of 0.16 dB with a single (one-shot) E2E measurement on the deployed 6-span system with 12 EDFAs.
{"title":"Multi-span optical power spectrum prediction using cascaded learning with one-shot end-to-end measurement","authors":"Zehao Wang;Yue-Kai Huang;Shaobo Han;Daniel Kilper;Tingjun Chen","doi":"10.1364/JOCN.533634","DOIUrl":"https://doi.org/10.1364/JOCN.533634","url":null,"abstract":"Scalable methods for optical transmission performance prediction using machine learning (ML) are studied in metro reconfigurable optical add-drop multiplexer (ROADM) networks. A cascaded learning framework is introduced to encompass the use of cascaded component models for end-to-end (E2E) optical path prediction augmented with different combinations of E2E performance data and models. Additional E2E optical path data and models are used to reduce the prediction error accumulation in the cascade. Off-line training (pre-trained prior to deployment) and transfer learning are used for component-level erbium-doped fiber amplifier (EDFA) gain models to ensure scalability. Considering channel power prediction, we show that the data collection process of the pre-trained EDFA model can be reduced to only 5% of the original training set using transfer learning. We evaluate the proposed method under three different topologies with field deployed fibers and achieve a mean absolute error of 0.16 dB with a single (one-shot) E2E measurement on the deployed 6-span system with 12 EDFAs.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 1","pages":"A23-A33"},"PeriodicalIF":4.0,"publicationDate":"2024-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595082","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}
Farhad Arpanaei;Mahdi Ranjbar Zefreh;Carlos Natalino;Piotr Lechowicz;Shuangyi Yan;Jose M. Rivas-Moscoso;Oscar Gonzalez de Dios;Juan Pedro Fernandez-Palacios;Hami Rabbani;Maite Brandt-Pearce;Alfonso Sanchez-Macian;Jose Alberto Hernandez;David Larrabeiti;Paolo Monti
Both multi-band and space division multiplexing (SDM) independently represent cost-effective approaches for next-generation optical backbone networks, particularly as data exchange between core data centers reaches the petabit-per-second scale. This paper focuses on different strategies for implementing band and SDM elastic optical network (BSDM EON) technology and analyzes the total network capacity of three sizes of backbone metro-core networks: ultra-long-, long-, and medium-distance networks related to the United States, Japan, and Spain, respectively. Two BSDM strategies are considered, namely, multi-core fibers (MCFs) and BSDM based on standard single-mode fiber (SSMF) bundles of multi-fiber pairs (BuMFPs). For MCF-based BSDM, we evaluated the performance of four manufactured trench-assisted weakly coupled (TAWC) MCFs with 4, 7, 13, and 19 cores. Simulation results reveal that, in the regime of ultra-low (UL) loss and inter-core crosstalk (ICXT), MCF-based throughput can be up to 14% higher than SSMF BuMFP-based BSDM when the core pitch exceeds 43 µm and the loss coefficient is lower than that of standard single-mode fibers. However, increasing the number of cores with (non-)standard cladding diameters, UL loss, and ICXT coefficient is not beneficial. As core counts increase up to 13 for non-standard cladding diameters ( ${lt}230;{unicode{x00B5}{rm m}}$ ), the core pitch and loss coefficient also increase, leading to degraded performance of MCF-based BSDM compared to SSMF BuMFP-based BSDM. The results indicate that, in scenarios with 19 MFPs, SSFM BuMFP-based BSDM outperforms 19-core MCF-based scenarios, increasing the throughput by 55% to 73%, from medium-backbone networks to ultra-long ones.
{"title":"Ultra-high-capacity band and space division multiplexing backbone EONs: multi-core versus multi-fiber","authors":"Farhad Arpanaei;Mahdi Ranjbar Zefreh;Carlos Natalino;Piotr Lechowicz;Shuangyi Yan;Jose M. Rivas-Moscoso;Oscar Gonzalez de Dios;Juan Pedro Fernandez-Palacios;Hami Rabbani;Maite Brandt-Pearce;Alfonso Sanchez-Macian;Jose Alberto Hernandez;David Larrabeiti;Paolo Monti","doi":"10.1364/JOCN.533086","DOIUrl":"https://doi.org/10.1364/JOCN.533086","url":null,"abstract":"Both multi-band and space division multiplexing (SDM) independently represent cost-effective approaches for next-generation optical backbone networks, particularly as data exchange between core data centers reaches the petabit-per-second scale. This paper focuses on different strategies for implementing band and SDM elastic optical network (BSDM EON) technology and analyzes the total network capacity of three sizes of backbone metro-core networks: ultra-long-, long-, and medium-distance networks related to the United States, Japan, and Spain, respectively. Two BSDM strategies are considered, namely, multi-core fibers (MCFs) and BSDM based on standard single-mode fiber (SSMF) bundles of multi-fiber pairs (BuMFPs). For MCF-based BSDM, we evaluated the performance of four manufactured trench-assisted weakly coupled (TAWC) MCFs with 4, 7, 13, and 19 cores. Simulation results reveal that, in the regime of ultra-low (UL) loss and inter-core crosstalk (ICXT), MCF-based throughput can be up to 14% higher than SSMF BuMFP-based BSDM when the core pitch exceeds 43 µm and the loss coefficient is lower than that of standard single-mode fibers. However, increasing the number of cores with (non-)standard cladding diameters, UL loss, and ICXT coefficient is not beneficial. As core counts increase up to 13 for non-standard cladding diameters (\u0000<tex>${lt}230;{unicode{x00B5}{rm m}}$</tex>\u0000), the core pitch and loss coefficient also increase, leading to degraded performance of MCF-based BSDM compared to SSMF BuMFP-based BSDM. The results indicate that, in scenarios with 19 MFPs, SSFM BuMFP-based BSDM outperforms 19-core MCF-based scenarios, increasing the throughput by 55% to 73%, from medium-backbone networks to ultra-long ones.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 12","pages":"H66-H78"},"PeriodicalIF":4.0,"publicationDate":"2024-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142595084","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}
Uncoupled multicore fibers (MCFs) are expected to be the first to be commercially deployed due to their high compatibility with existing single-mode fiber technologies. Since MCFs have a 3D shape, they generally exhibit connection polarity. Thus, optical devices based on MCFs also generally have polarity, which will complicate the core resource assignment and end-to-end core connections in future MCF-based spatial channel networks (SCNs). In this paper, we first discuss the polarity of MCF-based optical devices (MODs) such as MCF patch cords, spatial multiplexers (SMUXs), core selective switches (CSSs), and core selectors (CSs). We then propose a definition for global core numbers in a two-MCF unidirectional (2MCF-UD) SCN and a single-MCF bidirectional (1MCF-BD) SCN. We also propose a method for managing the polarity of MODs and correctly connecting cores end-to-end. To verify the effectiveness of the proposed global core numbering and polarity management method for MODs, testbeds emulating a 2MCF-UD SCN and a 1MCF-BD SCN are constructed using prototype CSS, CS, and SMUX devices. By using light with different optical frequencies as input and observing the output spectrum, we confirm that the spatial channel specified by the global core number is established correctly end-to-end in the SCN if the polarity of the MODs is set correctly.
{"title":"Polarity management of multicore fiber-based optical devices in unidirectional and bidirectional spatial channel networks","authors":"Masahiko Jinno;Rika Tahara;Kyosuke Nakada;Takuma Izumi;Kako Matsumoto","doi":"10.1364/JOCN.532960","DOIUrl":"https://doi.org/10.1364/JOCN.532960","url":null,"abstract":"Uncoupled multicore fibers (MCFs) are expected to be the first to be commercially deployed due to their high compatibility with existing single-mode fiber technologies. Since MCFs have a 3D shape, they generally exhibit connection polarity. Thus, optical devices based on MCFs also generally have polarity, which will complicate the core resource assignment and end-to-end core connections in future MCF-based spatial channel networks (SCNs). In this paper, we first discuss the polarity of MCF-based optical devices (MODs) such as MCF patch cords, spatial multiplexers (SMUXs), core selective switches (CSSs), and core selectors (CSs). We then propose a definition for global core numbers in a two-MCF unidirectional (2MCF-UD) SCN and a single-MCF bidirectional (1MCF-BD) SCN. We also propose a method for managing the polarity of MODs and correctly connecting cores end-to-end. To verify the effectiveness of the proposed global core numbering and polarity management method for MODs, testbeds emulating a 2MCF-UD SCN and a 1MCF-BD SCN are constructed using prototype CSS, CS, and SMUX devices. By using light with different optical frequencies as input and observing the output spectrum, we confirm that the spatial channel specified by the global core number is established correctly end-to-end in the SCN if the polarity of the MODs is set correctly.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 12","pages":"H53-H65"},"PeriodicalIF":4.0,"publicationDate":"2024-11-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142587587","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}
Management of spectrum fragmentation in optical transport networks typically requires after the fact defragmentation. This paper proposes a probabilistic approach that mitigates the creation of fragmentation by reducing spectral waste and increasing the expected number of allowable additional lightpaths. The proposed approach is simulated and compared against both first fit as well as fragmentation aware spectrum assignment methods, and the comparison results are provided.
{"title":"Probabilistic path computation and frequency assignment to mitigate spectral fragmentation in elastic optical networks","authors":"Francois Moore;Andrea Fumagalli","doi":"10.1364/JOCN.538610","DOIUrl":"https://doi.org/10.1364/JOCN.538610","url":null,"abstract":"Management of spectrum fragmentation in optical transport networks typically requires after the fact defragmentation. This paper proposes a probabilistic approach that mitigates the creation of fragmentation by reducing spectral waste and increasing the expected number of allowable additional lightpaths. The proposed approach is simulated and compared against both first fit as well as fragmentation aware spectrum assignment methods, and the comparison results are provided.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"1179-1188"},"PeriodicalIF":4.0,"publicationDate":"2024-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142579184","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 suppression of inter-core crosstalk (IC-XT) that affects each lightpath is crucial for resource allocation in space-division multiplexing elastic optical networks (SDM-EONs) with multi-core fibers (MCFs). Resource allocation approaches that limit the simultaneous use of adjacent cores in the same frequency band to the MCFs composing each lightpath have been widely adopted to suppress IC-XT. However, in principle, such methods are inefficient because they cannot fully utilize all cores. This study examines the core density from the perspective of the core layout in weakly coupled MCFs and the IC-XT suppression requirement. The densest MCF layout maximizes the network capacity while restricting the amount of IC-XT within the tolerance threshold for each lightpath. Specifically, we propose an XT-free condition, maintaining the IC-XT to each lightpath within the acceptable tolerance level. In addition, we evaluated numerous MCFs that satisfy or do not satisfy the XT-free condition with various network topologies and cladding diameters. This evaluation also validates the IC-XT reduction performance of the proposed framework compared with that of the conventional resource-allocation approach. Here, we incorporate our indirect IC-XT calculation method that affects lightpaths from other cores via its nearest cores, which was overlooked in the resource allocation problem. Based on these comprehensive examinations, we propose a method to determine the densest core layout for a given network topology and route and modulation format selection algorithm.
{"title":"Layout design of densest weakly coupled multi-core fibers to minimize the network blocking rate","authors":"Yuya Seki;Yosuke Tanigawa;Yusuke Hirota;Hideki Tode","doi":"10.1364/JOCN.531706","DOIUrl":"https://doi.org/10.1364/JOCN.531706","url":null,"abstract":"The suppression of inter-core crosstalk (IC-XT) that affects each lightpath is crucial for resource allocation in space-division multiplexing elastic optical networks (SDM-EONs) with multi-core fibers (MCFs). Resource allocation approaches that limit the simultaneous use of adjacent cores in the same frequency band to the MCFs composing each lightpath have been widely adopted to suppress IC-XT. However, in principle, such methods are inefficient because they cannot fully utilize all cores. This study examines the core density from the perspective of the core layout in weakly coupled MCFs and the IC-XT suppression requirement. The densest MCF layout maximizes the network capacity while restricting the amount of IC-XT within the tolerance threshold for each lightpath. Specifically, we propose an XT-free condition, maintaining the IC-XT to each lightpath within the acceptable tolerance level. In addition, we evaluated numerous MCFs that satisfy or do not satisfy the XT-free condition with various network topologies and cladding diameters. This evaluation also validates the IC-XT reduction performance of the proposed framework compared with that of the conventional resource-allocation approach. Here, we incorporate our indirect IC-XT calculation method that affects lightpaths from other cores via its nearest cores, which was overlooked in the resource allocation problem. Based on these comprehensive examinations, we propose a method to determine the densest core layout for a given network topology and route and modulation format selection algorithm.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 12","pages":"H40-H52"},"PeriodicalIF":4.0,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565606","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}
Carlos Natalino;Talles Magalhaes;Farhad Arpanaei;Fabricio R. L. Lobato;Joao C. W. A. Costa;Jose Alberto Hernandez;Paolo Monti
The dynamic provisioning of optical network services requires algorithms to find a suitable solution given the specific service requirements and the current network state. These algorithms are usually evaluated using a software simulator developed ad hoc, which may require different levels of detail depending on the problem addressed and how realistic the evaluation needs to be. Moreover, to demonstrate they are a significant contribution to the field, these new algorithms must be benchmarked against the best-performing previously proposed solutions. Due to the large set of parameters and their wide range of possible values, benchmarking algorithms from the literature is not straightforward and can quickly become challenging and time-consuming. This work introduces the Optical Networking Gym, an open-source toolkit that simplifies implementing optical resource assignment simulations and benchmarking new solutions against previously published algorithms. The toolkit provides environments modeling relevant optical networking scenarios, common algorithms for solving problems related to these scenarios, and a set of scripts to prepare and execute simulations for various use cases. Currently, four environments are available, with the possibility of increasing this number through contributions from the co-authors and the community. This paper describes the architecture, interface, environments, and scripts included with the toolkit. We adopt the quality of transmission (QoT)-aware dynamic resource allocation of optical services as the network scenario under examination. Three use cases highlight the toolkit’s modularity, flexibility, and performance. The toolkit allows researchers to streamline the process of developing simulation scenarios and algorithms, enhancing their ability to benchmark their algorithms.
{"title":"Optical Networking Gym: an open-source toolkit for resource assignment problems in optical networks","authors":"Carlos Natalino;Talles Magalhaes;Farhad Arpanaei;Fabricio R. L. Lobato;Joao C. W. A. Costa;Jose Alberto Hernandez;Paolo Monti","doi":"10.1364/JOCN.532850","DOIUrl":"https://doi.org/10.1364/JOCN.532850","url":null,"abstract":"The dynamic provisioning of optical network services requires algorithms to find a suitable solution given the specific service requirements and the current network state. These algorithms are usually evaluated using a software simulator developed ad hoc, which may require different levels of detail depending on the problem addressed and how realistic the evaluation needs to be. Moreover, to demonstrate they are a significant contribution to the field, these new algorithms must be benchmarked against the best-performing previously proposed solutions. Due to the large set of parameters and their wide range of possible values, benchmarking algorithms from the literature is not straightforward and can quickly become challenging and time-consuming. This work introduces the Optical Networking Gym, an open-source toolkit that simplifies implementing optical resource assignment simulations and benchmarking new solutions against previously published algorithms. The toolkit provides environments modeling relevant optical networking scenarios, common algorithms for solving problems related to these scenarios, and a set of scripts to prepare and execute simulations for various use cases. Currently, four environments are available, with the possibility of increasing this number through contributions from the co-authors and the community. This paper describes the architecture, interface, environments, and scripts included with the toolkit. We adopt the quality of transmission (QoT)-aware dynamic resource allocation of optical services as the network scenario under examination. Three use cases highlight the toolkit’s modularity, flexibility, and performance. The toolkit allows researchers to streamline the process of developing simulation scenarios and algorithms, enhancing their ability to benchmark their algorithms.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 12","pages":"G40-G51"},"PeriodicalIF":4.0,"publicationDate":"2024-10-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142565630","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}
Yijun Cheng;Zejun Chen;Zihe Hu;Meng Xiang;Zhijun Yan;Yuwen Qin;Songnian Fu
Nonlinear equalization (NLE) is essential for guaranteeing the performance of an optical network (ON). Effective NLE implementation relies on key parameters of the transmission link, including the modulation format (MF) and the launch power. As ONs become more agile, the parameters of fiber optical transmission need to be adaptive and relevant to the routing condition. Therefore, successful NLE implementation relies on the realization of transmission awareness (TA). Although machine learning-enabled optical performance monitoring (OPM) has been extensively investigated in the past few years, current NLE algorithms cannot autonomously perceive transmission parameters. Furthermore, current TA implementation still needs human intervention to guide the NLE. In addition, existing ML-based OPM and NLE cannot be trained autonomously, leading to the incapability of environmental change and mislabeling. Here, we propose cognitive learning (CL) for TA-guided NLE in agile ONs. We perform an experiment involving 32 Gbaud polarization-division-multiplexed (PDM)-quadrature phase shift keying (QPSK)/16-quadrature amplitude modulation (QAM) transmission over 1500 km of standard single-mode fiber (SSMF) with a variable launch power from 0 to 3 dBm. When a deep neural network (DNN) with amplitude histograms (AHs) as inputs and one step per span-learned digital back-propagation (1stps-LDBP) are developed, the CL simultaneously enables both TA and NLE, with the capability of self-learning, mislabeling resistance, and dynamic adaptation. The proof-of-concept experimental results indicate that both the accuracy of TA and the Q-factor of PDM-16QAM can be improved by 34.8% and 0.84 dB, respectively, when the launch power is 3 dBm. Moreover, the accuracy of TA is enhanced by 35.3%, even when the used data has 30% mislabeling. Therefore, the CL framework can be customized to satisfy various NLE implementations, thereby supporting the adaptive transmission of agile ONs.
{"title":"Cognitive learning enabled agile optical network","authors":"Yijun Cheng;Zejun Chen;Zihe Hu;Meng Xiang;Zhijun Yan;Yuwen Qin;Songnian Fu","doi":"10.1364/JOCN.538632","DOIUrl":"https://doi.org/10.1364/JOCN.538632","url":null,"abstract":"Nonlinear equalization (NLE) is essential for guaranteeing the performance of an optical network (ON). Effective NLE implementation relies on key parameters of the transmission link, including the modulation format (MF) and the launch power. As ONs become more agile, the parameters of fiber optical transmission need to be adaptive and relevant to the routing condition. Therefore, successful NLE implementation relies on the realization of transmission awareness (TA). Although machine learning-enabled optical performance monitoring (OPM) has been extensively investigated in the past few years, current NLE algorithms cannot autonomously perceive transmission parameters. Furthermore, current TA implementation still needs human intervention to guide the NLE. In addition, existing ML-based OPM and NLE cannot be trained autonomously, leading to the incapability of environmental change and mislabeling. Here, we propose cognitive learning (CL) for TA-guided NLE in agile ONs. We perform an experiment involving 32 Gbaud polarization-division-multiplexed (PDM)-quadrature phase shift keying (QPSK)/16-quadrature amplitude modulation (QAM) transmission over 1500 km of standard single-mode fiber (SSMF) with a variable launch power from 0 to 3 dBm. When a deep neural network (DNN) with amplitude histograms (AHs) as inputs and one step per span-learned digital back-propagation (1stps-LDBP) are developed, the CL simultaneously enables both TA and NLE, with the capability of self-learning, mislabeling resistance, and dynamic adaptation. The proof-of-concept experimental results indicate that both the accuracy of TA and the Q-factor of PDM-16QAM can be improved by 34.8% and 0.84 dB, respectively, when the launch power is 3 dBm. Moreover, the accuracy of TA is enhanced by 35.3%, even when the used data has 30% mislabeling. Therefore, the CL framework can be customized to satisfy various NLE implementations, thereby supporting the adaptive transmission of agile ONs.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"1170-1178"},"PeriodicalIF":4.0,"publicationDate":"2024-10-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552005","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}
Predicting the quality of transmission (QoT) is a critical task in the management and optimization of modern fiber-optic networks. Traditional machine learning (ML) QoT prediction models, typically trained on pre-collected datasets, are designed to make long-term predictions once deployed. However, this static training strategy often falls short in the face of time-dependent network evolution and variations. We identify the root cause of these shortcomings as shifts in data distribution, which are not accounted for in conventional static models. In response to these challenges, we propose an online continual learning pipeline that is specifically designed for stable QoT prediction in optical networks. This pipeline directly addresses the problem of distribution shifts by continuously updating the prediction model in response to real-time network data. We explore and compare various strategies within this framework and demonstrate that the integration of the adaptive retraining strategy and the regularized online continual learning algorithm (OCL-REG) significantly enhances the QoT prediction stability while optimizing the resource efficiency. OCL-REG demonstrates superior adaptability and stability, achieving an average cumulative mean squared error (C-MSE) of 0.19 on a testbench with a data distribution shift sequence containing 1000 batches. Moreover, the OCL-REG model requires fewer samples for adaptation, averaging around 107 samples, compared to the conventional retraining strategy, which requires an average of 253 samples. Our approach presents a paradigm shift in QoT prediction, moving from a static to a dynamic, lifelong learning model that is more attuned to the evolving realities of real fiber-optic networks.
{"title":"Lifelong QoT prediction: an adaptation to real-world optical networks","authors":"Qihang Wang;Zhuojun Cai;Faisal Nadeem Khan","doi":"10.1364/JOCN.531851","DOIUrl":"https://doi.org/10.1364/JOCN.531851","url":null,"abstract":"Predicting the quality of transmission (QoT) is a critical task in the management and optimization of modern fiber-optic networks. Traditional machine learning (ML) QoT prediction models, typically trained on pre-collected datasets, are designed to make long-term predictions once deployed. However, this static training strategy often falls short in the face of time-dependent network evolution and variations. We identify the root cause of these shortcomings as shifts in data distribution, which are not accounted for in conventional static models. In response to these challenges, we propose an online continual learning pipeline that is specifically designed for stable QoT prediction in optical networks. This pipeline directly addresses the problem of distribution shifts by continuously updating the prediction model in response to real-time network data. We explore and compare various strategies within this framework and demonstrate that the integration of the adaptive retraining strategy and the regularized online continual learning algorithm (OCL-REG) significantly enhances the QoT prediction stability while optimizing the resource efficiency. OCL-REG demonstrates superior adaptability and stability, achieving an average cumulative mean squared error (C-MSE) of 0.19 on a testbench with a data distribution shift sequence containing 1000 batches. Moreover, the OCL-REG model requires fewer samples for adaptation, averaging around 107 samples, compared to the conventional retraining strategy, which requires an average of 253 samples. Our approach presents a paradigm shift in QoT prediction, moving from a static to a dynamic, lifelong learning model that is more attuned to the evolving realities of real fiber-optic networks.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"1159-1169"},"PeriodicalIF":4.0,"publicationDate":"2024-10-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538035","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}
As guaranteed reliable experience (GRE) is one of the features of fifth-generation fixed networks (F5G), high-reliability optical transport networks (OTNs) have become one of the key technologies supporting this feature. Unfortunately, current OTN protection methods often provide fixed bandwidth for protection of 1 Gbps or more, which leads to resource wastage. Fine grain OTN (fgOTN) is an extension of existing OTN, which supports hitless bandwidth adjustment and uses 10 Mbps time slot isolation. The application of fgOTN’s advantages to network protection can save resources. However, how much initial protection bandwidth is reserved for links to improve the service recovery success probability after faults is a key issue to be studied. If the initially reserved protection bandwidth is too much, that may waste precious bandwidth resources and fail to recover other services. If the initially reserved protection bandwidth is too small, the controller needs to adjust the bandwidth frequently to meet service requirements, which puts tremendous pressure on network management and control. This study proposes a maximum bandwidth segmented shared protection (MBSSP) scheme, which is based on optimized centralized and distributed collaboration network management architecture. The protection scheme includes two algorithms: (i) the resource reservation algorithm used before the fault occurs based on maximum bandwidth segmented shared protection and (ii) the protection switch algorithm used after the fault occurs based on bandwidth adjustment. Simulative results show that, in a 38-node topology, compared with minimum bandwidth dedicated protection (MBDP), MBSSP only sacrifices 0.8% of resource utilization but can reduce the bandwidth adjustment probability by 15.8% and improves the recovery success probability by 33.4%. Compared with end-to-end shared protection (E2ESP), MBSSP improves recovery success probability by 42.9% and saves resources by 16.7%, although it increases the bandwidth adjustment probability by 20%.
{"title":"Segmented protection scheme based on maximum bandwidth sharing in F5G","authors":"Wenhong Liu;Yongli Zhao;Yajie Li;Xin Li;Sabidur Rahman;Jie Zhang","doi":"10.1364/JOCN.529958","DOIUrl":"https://doi.org/10.1364/JOCN.529958","url":null,"abstract":"As guaranteed reliable experience (GRE) is one of the features of fifth-generation fixed networks (F5G), high-reliability optical transport networks (OTNs) have become one of the key technologies supporting this feature. Unfortunately, current OTN protection methods often provide fixed bandwidth for protection of 1 Gbps or more, which leads to resource wastage. Fine grain OTN (fgOTN) is an extension of existing OTN, which supports hitless bandwidth adjustment and uses 10 Mbps time slot isolation. The application of fgOTN’s advantages to network protection can save resources. However, how much initial protection bandwidth is reserved for links to improve the service recovery success probability after faults is a key issue to be studied. If the initially reserved protection bandwidth is too much, that may waste precious bandwidth resources and fail to recover other services. If the initially reserved protection bandwidth is too small, the controller needs to adjust the bandwidth frequently to meet service requirements, which puts tremendous pressure on network management and control. This study proposes a maximum bandwidth segmented shared protection (MBSSP) scheme, which is based on optimized centralized and distributed collaboration network management architecture. The protection scheme includes two algorithms: (i) the resource reservation algorithm used before the fault occurs based on maximum bandwidth segmented shared protection and (ii) the protection switch algorithm used after the fault occurs based on bandwidth adjustment. Simulative results show that, in a 38-node topology, compared with minimum bandwidth dedicated protection (MBDP), MBSSP only sacrifices 0.8% of resource utilization but can reduce the bandwidth adjustment probability by 15.8% and improves the recovery success probability by 33.4%. Compared with end-to-end shared protection (E2ESP), MBSSP improves recovery success probability by 42.9% and saves resources by 16.7%, although it increases the bandwidth adjustment probability by 20%.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"16 11","pages":"1145-1158"},"PeriodicalIF":4.0,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142524177","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 propose an innovative optimization framework using a multi-objective genetic algorithm to simultaneously optimize the launch power profile and design Raman amplifiers. Its flexibility allows us to find better solutions and reduce the number of Raman pumps. Moreover, we utilize the framework to compare the potential of four multi-band transmission systems leveraging hybrid fiber amplification. Simulation results highlight that complementing a C + L-band system with the S-band leads to higher total system capacity than using the E-band or interleaving data channels and Raman pumps.
我们提出了一种创新的优化框架，利用多目标遗传算法同时优化发射功率曲线和设计拉曼放大器。它的灵活性使我们能够找到更好的解决方案，并减少拉曼泵的数量。此外，我们还利用该框架比较了四种利用混合光纤放大的多波段传输系统的潜力。仿真结果表明，与使用 E 波段或交错数据通道和拉曼泵相比，使用 S 波段对 C + L 波段系统进行补充可提高系统总容量。
{"title":"Raman amplifier design and launch power optimization in multi-band optical systems","authors":"Andre Souza;Nelson Costa;Joao Pedro;Joao Pires","doi":"10.1364/JOCN.534006","DOIUrl":"https://doi.org/10.1364/JOCN.534006","url":null,"abstract":"We propose an innovative optimization framework using a multi-objective genetic algorithm to simultaneously optimize the launch power profile and design Raman amplifiers. Its flexibility allows us to find better solutions and reduce the number of Raman pumps. Moreover, we utilize the framework to compare the potential of four multi-band transmission systems leveraging hybrid fiber amplification. Simulation results highlight that complementing a C + L-band system with the S-band leads to higher total system capacity than using the E-band or interleaving data channels and Raman pumps.","PeriodicalId":50103,"journal":{"name":"Journal of Optical Communications and Networking","volume":"17 1","pages":"A13-A22"},"PeriodicalIF":4.0,"publicationDate":"2024-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142518227","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：