[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123214-en":3,"doc-seo-123214-105":30,"detail-sidebar-cat-0-en-105":91},{"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},123214,1374391975076,"Riley","https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051",8,"Research & Report","Machine Learning Approaches For Predicting Link Failures In Production Networks - Thesis Abstract","Proactive prediction of flapping links—links that go down multiple times per day—using machine learning models trained on metrics from IP and optical layers of a real production topology. The study evaluates how optical metrics, temporal dependencies, and topological relations contribute to forecasting link failures through Interior Gateway Protocol configuration changes as a proxy. Optical features such as maximum/minimum power and unavailable or errored seconds improve performance by about 9 percentage points, while temporal and spatial features add about 8 and 7.","Machine Learning Approaches For Predicting Link Failures In Production Networks  \nby  \nBruck Wendwessen Wubete  \nA thesis submitted to Carleton University Faculty of Graduate and Postdoctoral Affairs in partial fulfillment of the requirements for  \nthe degree of  \nMaster of Applied Science  \nin  \nElectrical and Computer Engineering with specialization in Data Science  \nCarleton University  \nOttawa, Ontario, Canada  \n© Bruck Wubete 2023  \nAbstract  \nTo proactively address the problem of identifying flapping links (links that go down multiple times a day), we used Machine Learning (ML) tools to study metrics reported from Internet Protocol (IP) and optical layers of a topology provided by a real network operator. We studied the relevance of optical metrics, the underlying temporal relations, and the topological relations that help forecast link failures using Interior Gateway Protocol (IGP) configuration changes as a proxy. We discovered that optical features such as optical maximum and minimum power or unavailable and errored seconds increased the model’s performance by about 9 percentage points while temporal and spatial features improved it by 8 and 7 percentage points respectively. Furthermore, we used time series and graph neural networks to show that the smallest look-back window required to get better results was five days and that neighboring links up to two hops away could have relevant information.  \nAcknowledgements  \nThanks to Prof. Babak Esfandiari, Prof. Thomas Kunz, Dr. David Cote, Dr. Thomas Triplet, Dr. Christopher Barber, Dr. Minming Ni, my fiancé, my family, Ciena Inc., and all others who helped me succeed in this thesis.  \nTable of Contents  \nAbstract.............................................................................................................................. ii  \nAcknowledgements .......................................................................................................... iii  \nTable of Contents ............................................................................................................. iv  \nList of Tables ................................................................................................................... vii  \nList of Figures................................................................................................................. viii  \nList of Equations ............................................................................................................... x  \nList of Acronyms .............................................................................................................. xi  \nList of Appendices........................................................................................................... xii  \nChapter 1: Introduction .................................................................................................. 1  \n1.1 Contributions .................................................................................................................. 5  \n1.2 Publications .................................................................................................................... 6  \n1.3 Structure ......................................................................................................................... 7  \nChapter 2: Background ................................................................................................... 8  \n2.1 Network Topology.......................................................................................................... 8  \n2.2 Intermediate Service to Intermediate Service Routing Protocol .................................. 13  \n2.3 ML Models and Algorithms ......................................................................................... 15  \n2.3.1 Extreme Gradient Boosting ...................................................................................... 16  \n2.3.2 Random Convolutional Kernel Transform........................................","cbCaieZmg66hZh2d","https://ap.wps.com/l/cbCaieZmg66hZh2d","pdf",3927830,1,143,"English","en",105,"# Abstract\n# Acknowledgements\n# Table of Contents\n# List of Tables\n# List of Figures\n# List of Equations\n# List of Acronyms\n# List of Appendices\n# Chapter 1: Introduction\n## 1.1 Contributions\n## 1.2 Publications\n## 1.3 Structure\n# Chapter 2: Background\n## 2.1 Network Topology\n## 2.2 Intermediate Service to Intermediate Service Routing Protocol\n## 2.3 ML Models and Algorithms\n## 2.4 Summary\n# Chapter 3: Related Work\n## 3.1 Machine Learning Approaches for Intelligent Networks\n## 3.2 The Use of Optical Metrics in Smart Networks\n## 3.3 Leveraging Spatiotemporal Relations in Network Management\n## 3.4 Summary\n# Chapter 4: Methodology\n## 4.1 Data Exploration\n## 4.2 Data Combination and Windowing\n## 4.3 Some General Statistics","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"It targets identifying flapping links—links that go down multiple times per day—before failures impact operations.\"},{\"question\":\"Which data sources and proxy are used for training and labeling?\",\"answer\":\"Models learn from metrics reported from IP and optical layers of a real network topology, using Interior Gateway Protocol (IGP) configuration changes as a proxy for failures.\"},{\"question\":\"How do optical, temporal, and topological features affect prediction performance?\",\"answer\":\"Optical features such as optical maximum/minimum power and unavailable or errored seconds raise performance by about 9 percentage points, while temporal and spatial features improve results by about 8 and 7 points respectively.\"}]","Machine Learning Approaches For Predicting Link Failures In Production Networks - Thesis Abstract | PDF",1785815257,360,{"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":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-approaches-for-predicting-link-failures-in-production-networks-thesis-abstract","",{"@graph":36,"@context":85},[37,54,68],{"@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":53},"https://docshare.wps.com/document/machine-learning-approaches-for-predicting-link-failures-in-production-networks-thesis-abstract/123214/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"It targets identifying flapping links—links that go down multiple times per day—before failures impact operations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which data sources and proxy are used for training and labeling?",{"text":80,"@type":76},"Models learn from metrics reported from IP and optical layers of a real network topology, using Interior Gateway Protocol (IGP) configuration changes as a proxy for failures.",{"name":82,"@type":73,"acceptedAnswer":83},"How do optical, temporal, and topological features affect prediction performance?",{"text":84,"@type":76},"Optical features such as optical maximum/minimum power and unavailable or errored seconds raise performance by about 9 percentage points, while temporal and spatial features improve results by about 8 and 7 points respectively.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]