[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122661-en":3,"doc-seo-122661-105":30,"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":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122661,549758146520,"Patrick","https://ap-avatar.wpscdn.com/avatar/80002397d8c0411e94?_k=1775819394049821470",8,"Research & Report","Fault Monitoring in Passive Optical Networks using Machine Learning Techniques","Passive optical network (PON) systems face multiple failure types, including fiber cuts and optical network unit (ONU) transmitter/receiver failures. Fiber-cut events can cause major downtime and financial losses, while nearly equidistant branch terminations make it difficult to identify the faulty ONU because overlapping reflections hide which branch is responsible. As network size increases, fault-monitoring complexity grows and reliability decreases. This paper proposes machine learning approaches for PON fault monitoring and validates them using experimental optical time domain reflectometry (OTDR) data.","Fault Monitoring in Passive Optical Networks using Machine  \nLearning Techniques  \nKhouloud Abdelli 1, Carsten Tropschug2, Helmut Griesser3, and Stephan Pachnicke4  \n1 Nokia Bell Labs, Germany  \n2 ADVA Optical Networking SE, Germany  \n3 ADVA Network Security GmbH, Germany  \n4 Christian-Albrechts-Universität zu Kiel, Kaiserstr. 2, 24143 Kiel, Germany  \n[e-mail: Khouloud.Abdelli@nokia.com](e-mail: Khouloud.Abdelli@nokia.com)  \nABSTRACT  \nPassive optical network (PON) systems are vulnerable to a variety of failures, including fiber cuts and optical network unit (ONU) transmitter/receiver failures. Any service interruption caused by a fiber cut can result in huge financial losses for service providers or operators. Identifying the faulty ONU becomes difficult in the case of nearly equidistant branch terminations because the reflections from the branches overlap, making it difficult to distinguish the faulty branch given the global backscattering signal. With increasing network size, the complexity of fault monitoring in PON systems increases, resulting in less reliable monitoring. To address these challenges, we propose in this paper various machine learning (ML) approaches for fault monitoring in PON systems, and we validate them using experimental optical time domain reflectometry (OTDR) data.  \nKeywords: Passive optical networks, fault monitoring, machine learning, optical time domain reflectometry  \n1. INTRODUCTION  \nPassive optical networks (PONs) have gained popularity as a broadband fiber access network solution due to their service transparency, cost effectiveness, and scalability among other benefits [1] . Because of their high capacity and extensive coverage, PON systems are becoming increasingly vulnerable to a variety of failures including failures in the optical distribution network (e.g., fiber cuts), optical network unit (ONU) transmitter/receiver failures, and dirty/cut/bent patch cords or connectors. Such failures, particularly fiber cuts, can result in network disruption and massive financial losses for service providers or operators. Fault detection in PONs requires complex manual intervention, as well as extensive expert knowledge and probing time until a failure is identified, located, and repaired, resulting in increased OPEX and customer dissatisfaction. As a result, implementing an accurate and efficient fault monitoring scheme in PON systems is extremely beneficial to reduce maintenance costs, to minimize downtime, and to improve service quality.  \nOptical time domain reflectometry (OTDR), a technique based on Rayleigh backscattering, has primarily been used to monitor optical fiber networks. However, using OTDR to monitor PON systems can be challenging because the backscattered signals from each branch are added together, making it difficult to distinguish between the individual branches' backward signals [2] . Event analysis becomes more difficult in the case of (almost) equidistant branch terminations because the reflected signals from the same length branches overlap and add up. Furthermore, the high loss of the optical splitters at the remote node causes a significant reduction in the backscattered signal, which may have an adverse effect on the event analysis. One proposed solution to address the aforementioned challenges is to use a tunable OTDR in conjunction with wavelength multiplexers to allow fora dedicated monitoring wavelength for each branch [3] . Such a solution, however, is prohibitively expensive due to the high cost of a tunable OTDR instrument, and its scalability is limited due to practical limitations and poor spectrum efficiency. Installing optical reference reflectors at the ends of each branch to check its integrity is another simple and effective solution [2]. However, this approach necessitates varying branch lengths, which limits its applicability to real-world installed networks. Recently, machine learning (ML)-based approaches have demonstrated great promise for improving faul","cbCaijDHx4qpxEdT","https://ap.wps.com/l/cbCaijDHx4qpxEdT","pdf",902043,1,4,"English","en",105,"# Introduction\n## Challenges in OTDR-based PON monitoring\n## Proposed direction using machine learning\n# A Network-dependent Approach\n## Experimental Data","[{\"question\":\"Why is faulty ONU identification difficult in PONs with nearly equidistant branch lengths?\",\"answer\":\"Overlapping reflections from similarly long branches can merge into a global backscattering signal, making it hard to distinguish which branch is faulty.\"},{\"question\":\"What failures are considered in the proposed fault monitoring context?\",\"answer\":\"The work targets failures such as fiber cuts and ONU transmitter/receiver failures, along with issues affecting distribution components like patch cords or connectors.\"},{\"question\":\"How do the proposed machine learning methods leverage OTDR data?\",\"answer\":\"They learn patterns from OTDR monitoring traces to identify faulty branch identifiers without requiring trained personnel intervention or extra monitoring infrastructure, and are validated with experimental OTDR data.\"}]","Fault Monitoring in Passive Optical Networks using Machine Learning Techniques | PDF",1785812026,10,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":28},"fault-monitoring-in-passive-optical-networks-using-machine-learning-techniques","",{"@graph":36,"@context":84},[37,53,67],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":21},"https://docshare.wps.com/document/fault-monitoring-in-passive-optical-networks-using-machine-learning-techniques/122661/",{"url":52,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",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},"Why is faulty ONU identification difficult in PONs with nearly equidistant branch lengths?","Question",{"text":74,"@type":75},"Overlapping reflections from similarly long branches can merge into a global backscattering signal, making it hard to distinguish which branch is faulty.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What failures are considered in the proposed fault monitoring context?",{"text":79,"@type":75},"The work targets failures such as fiber cuts and ONU transmitter/receiver failures, along with issues affecting distribution components like patch cords or connectors.",{"name":81,"@type":72,"acceptedAnswer":82},"How do the proposed machine learning methods leverage OTDR data?",{"text":83,"@type":75},"They learn patterns from OTDR monitoring traces to identify faulty branch identifiers without requiring trained personnel intervention or extra monitoring infrastructure, and are validated with experimental OTDR data.","https://schema.org",{"og:url":52,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,133],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":131,"show_sort_weight":29,"slug":132},"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":46,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]