[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126665-en":3,"doc-seo-126665-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},126665,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Flexible Raman Amplifier Optimization Based on Machine Learning-Aided Physical Stimulated Raman Scattering Model","Raman amplifier optimization is investigated through a machine-learning-assisted physical model. A differentiable interpolation function for the Raman gain coefficient enables gradient-descent optimization of forward-propagating Raman pump frequency and power. The approach simultaneously optimizes an arbitrary number of forward pumps for any data-channel load and span length, then couples a forward propagation model with an experimentally trained ML model for backward pumping. Joint forward and backward optimization is validated on a 250 km unrepeatered transmission, achieving gain flatness under 1 dB across 4 THz using numerical simulation validation.","POLITECNICO DI TORINO  \nRepository ISTITUZIONALE  \nFlexible Raman Amplifier Optimization Based on Machine Learning-Aided Physical Stimulated Raman Scattering Model  \nOriginal  \nFlexible Raman Amplifier Optimization Based on Machine Learning-Aided Physical Stimulated Raman Scattering Model / Yankov, Mp; Da Ros, F; de Moura, Uc; Carena, A; Zibar, D. -In: JOURNAL OF LIGHTWAVE TECHNOLOGY. -ISSN 0733-8724. -STAMPA. -41:2(2023), pp. 508-514. [10 . 1109/JLT.2022.3218137]  \nAvailability:  \nThis version is available at: 11583/2984838 since: 2024-01-16T07:37:33Z  \nPublisher: IEEE  \nPublished  \nDOI:10.1109/JLT.2022.3218137  \nTerms of use:  \nThis article is made available under terms and conditions as specified in the corresponding bibliographic description in the repository  \nPublisher copyright  \nIEEE postprint/Author's Accepted Manuscript  \n©2023 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collecting works, for resale or lists, or reuse of any copyrighted component of this work in other works.  \n(Article begins on next page)  \n11 February 2024  \nThis article has been accepted for publication in IEEE/OSA Journal of Lightwave Technology. This is the author's version which has not been fully edited and content may change prior to final publication. Citation information: DOI 10. 1109/JLT.2022.3218137  \nJOURNAL OF LATEX CLASS FILES, VOL. 14, NO. 8, AUGUST 2015 1  \nFlexible Raman Ampliﬁer Optimization Based on Machine Learning-aided Physical Stimulated Raman  \nScattering Model  \nMetodi Plamenov Yankov, Member, IEEE, Francesco Da Ros, Senior Member, OSA, Senior Member, IEEE, Uiara Celine de Moura, Member, OSA, Andrea Carena, Senior Member, OSA, Senior Member, IEEE, and Darko Zibar  \nAbstract—The problem of Raman ampliﬁer optimization is studied. A differentiable interpolation function is obtained for the Raman gain coefﬁcient using machine learning (ML), which allows for the gradient descent optimization of forwardpropagating Raman pumps. Both the frequency and power of an arbitrary number of pumps in a forward pumping conﬁguration are then optimized for an arbitrary data channel load and span length. The forward propagation model is combined with an experimentally-trained ML model of a backward-pumping Raman ampliﬁer to jointly optimize the frequency and power of the forward ampliﬁer's pumps and the powers of the backward ampliﬁer's pumps. The joint forward and backward ampliﬁer optimization is demonstrated for an unrepeatered transmission of 250 km. A gain ﬂatness of \u003C 1 dB over 4 THz is achieved. The optimized ampliﬁers are validated using a numerical simulator.  \nIndex Terms—Stimulated Raman scattering, Raman ampliﬁer, frequency and power optimization, machine learning.  \nI. INTRODUCTION  \nRaman ampliﬁers (RAs) present a signiﬁcant advantage over erbium doped ﬁber ampliﬁers (EDFAs) in terms of noise ﬁgure and the potential for providing arbitrary gain proﬁles in a controlled way [1]. They are also a viable option for increasing the transmission bandwidth beyond the conventional C+L band and support S-band ampliﬁcation [2], [3] . Gain shaping over frequency is important for achieving uniformity of the quality of transmission for all channels in a wavelength division multiplexing (WDM) system. Gain nonuniformity is even more pronounced in ultra wide band systems due to different responses and losses of the optical components in different bands. Furthermore, in unrepeatered link scenarios, RAs are critical for providing ampliﬁcation from the receiver end, as well as remote pumping [4], [5], [6] . Broadband ampliﬁcation using RAs can be achieved by employing multiple Raman pumps at different frequencies. However, such conﬁgurations pose a challenge for the optimization of the pumps frequency and power due to the increased dimensionality of the prob","cbCaijH3CZW4FAtq","https://ap.wps.com/l/cbCaijH3CZW4FAtq","pdf",687879,1,"English","en",105,"# Introduction\n## Differentiable ML interpolation for Raman gain coefficient\n## Gradient-descent optimization of forward pump parameters\n## Joint forward-backward Raman amplifier optimization\n## Experimental ML model integration\n## Numerical validation and transmission demonstration","[{\"question\":\"What optimization problem does the paper address for Raman amplifiers?\",\"answer\":\"The paper studies how to optimize Raman amplifier pump frequency and power to achieve a desired gain profile under arbitrary channel load and span length, using forward and backward pumping configurations.\"},{\"question\":\"How does machine learning contribute to the optimization method?\",\"answer\":\"ML is used to learn a differentiable interpolation of the Raman gain coefficient and to model the gain behavior of a backward-pumping Raman amplifier from experimental training data.\"},{\"question\":\"What performance results are reported after joint forward and backward optimization?\",\"answer\":\"For a 250 km unrepeatered transmission, the optimized amplifiers achieve gain flatness better than 1 dB over a 4 THz bandwidth, validated using a numerical simulator.\"}]","Flexible Raman Amplifier Optimization Based on Machine Learning-Aided Physical Stimulated Raman Scattering Model | PDF",1785934104,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"flexible-raman-amplifier-optimization-based-on-machine-learning-aided-physical-stimulated-raman-scattering-model","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/flexible-raman-amplifier-optimization-based-on-machine-learning-aided-physical-stimulated-raman-scattering-model/126665/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What optimization problem does the paper address for Raman amplifiers?","Question",{"text":74,"@type":75},"The paper studies how to optimize Raman amplifier pump frequency and power to achieve a desired gain profile under arbitrary channel load and span length, using forward and backward pumping configurations.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does machine learning contribute to the optimization method?",{"text":79,"@type":75},"ML is used to learn a differentiable interpolation of the Raman gain coefficient and to model the gain behavior of a backward-pumping Raman amplifier from experimental training data.",{"name":81,"@type":72,"acceptedAnswer":82},"What performance results are reported after joint forward and backward optimization?",{"text":83,"@type":75},"For a 250 km unrepeatered transmission, the optimized amplifiers achieve gain flatness better than 1 dB over a 4 THz bandwidth, validated using a numerical simulator.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]