[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121923-en":3,"doc-seo-121923-105":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},121923,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Long-term Traffic Forecasting in Optical Networks Using Machine Learning","Future traffic knowledge in backbone optical networks enables Communications Service Providers to make better planning and control decisions. The study formulates long-term traffic forecasting as an ordinal classification problem and predicts traffic levels rather than exact volumes, reflecting network characteristics. Multiple machine learning approaches are compared with time-series methods. Model quality is assessed with a resource-usage-oriented metric using real traffic datasets from the Internet Exchange Point in Seattle, showing high metric values for ML models.","INTL JOURNAL OF ELECTRONICS AND TELECOMMUNICATIONS, 2023, VOL. 69, NO. 4, PP. 751-762  \nManuscript received July 2, 2023; revised October, 2023. DOI: 10.24425/ijet.2023.147697  \nLong-term Traffic Forecasting in Optical Networks Using Machine Learning  \nKrzysztof Walkowiak, Daniel Szostak, Adam Włodarczyk, and Andrzej Kasprzak  \nAbstract—Knowledge about future traffic in backbone optical networks may greatly improve a range of tasks that Communications Service Providers (CSPs) have to face. This work proposes a procedure for long-term traffic forecasting in optical networks. We formulate a long-terT traffic forecasting problem asan ordinal classification task. Due to the optical networks’ (and other network technologies’) characteristics, traffic forecasting has been realized by predicting future traffic levels rather than the exact traffic volume. We examine different machine learning (ML) algorithms and compare them with time series algorithms methods. To evaluate the developed ML models, we use a quality metric, which considers the network resource usage. Datasets used during research are based on real traffic patterns presented by Internet Exchange Point in Seattle. Our study shows that ML algorithms employed for long-term traffic forecasting problem obtain high values of quality metrics. Additionally, the final choice of the ML algorithm for the forecasting task should depend on CSPs expectations.  \nKeywords—Traffic forecasting; Machine Learning; Classification; Regression  \nI. INTRODUCTION  \nCOMPUTER networks are an integral part of contemporary  \nlife. Quick and global development of telecommunication technologies such as VoD, a cloud computing or the Internet of things causes rapid growth of endpoint devices [1] . According to the Cisco Annual Internet Report, the number of Internet users will reach 5.3 billion by the end of 2023 [2] . Moreover, the Nokia report [3] shows that as a result of the COVID-19 pandemic, in the first weeks of lockdown, compared to prepandemic time, network traffic increased by 30-50% . Additionally, by September 2020, traffic has stabilized at 20- 30% above pre pandemic level. To prevent the possible capacity crunch problem on the Internet, network operators constantly improve backbone networks using various optical technologies [4], [5] . However, constantly growing network traffic, the increase of which is sometimes rapid in a short time, presents new challenges to Communications Service Providers (CSPs) . To improve the performance of future optical networks compared to mechanisms currently used in optical networks, the concept of a cognitive optical network [6] has been proposed. In more detail, a cognitive optical network is based on a cognitive process that monitors current network conditions and adjusts the network operation to observed conditions. The cognitive  \nThis work was supported by National Science Centre, Poland under Grant 2017/27/B/ST7/00888 .  \nprocess, which often uses history to improve operation, usually applies Machine Learning (ML) algorithms [7] . ML techniques can be successfully applied to analyze and find dependencies in historical data, e.g., traffic flows. Gained knowledge can be used to forecast future traffic in the network and later as valuable information for different network optimization tasks, e.g., traffic flow control, network operational cost reduction, anomaly detection, or physical network expansion [8], [9] . In this paper, we present a procedure for long-term traffic forecasting in backbone networks.  \nNowadays, the means of communication used as backbone networks, carrying voluminous, aggregated user data traffic, are optical networks [10] . They use fibers linked into one physical cable as a transmission medium. Using the wavelength division multiplexing (WDM) technique, data is transferred using optical channels transmitted at different wavelengths. Currently, in WDM one wavelength offers capacity of 100 Gbps. Optical networks are constantly bein","cbCaipNxBtuB4aO1","https://ap.wps.com/l/cbCaipNxBtuB4aO1","pdf",1334614,1,12,"English","en",105,"# Introduction\n## Cognitive optical networks and ML-driven forecasting\n## Optical transport technologies and provisioning granularity\n# Methodology\n## Problem formulation as ordinal classification\n## Feature preprocessing and dataset analysis\n# Model Evaluation\n## Resource-usage quality metric\n## Comparison with time series algorithms\n# Results and Discussion\n## Quality metrics and algorithm selection for CSP expectations","[{\"question\":\"Why does the paper predict traffic levels instead of exact traffic volume?\",\"answer\":\"Because optical network characteristics make level-based prediction more suitable than exact volume forecasting.\"},{\"question\":\"How is the long-term traffic forecasting problem formulated?\",\"answer\":\"It is cast as an ordinal classification task.\"},{\"question\":\"What data and evaluation metric are used to assess the ML models?\",\"answer\":\"Experiments rely on real traffic patterns from the Internet Exchange Point in Seattle, and models are evaluated with a quality metric that accounts for network resource usage.\"}]","Long-term Traffic Forecasting in Optical Networks Using Machine Learning | PDF",1785807766,30,{"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},"long-term-traffic-forecasting-in-optical-networks-using-machine-learning","",{"@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/long-term-traffic-forecasting-in-optical-networks-using-machine-learning/121923/",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},"Why does the paper predict traffic levels instead of exact traffic volume?","Question",{"text":75,"@type":76},"Because optical network characteristics make level-based prediction more suitable than exact volume forecasting.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the long-term traffic forecasting problem formulated?",{"text":80,"@type":76},"It is cast as an ordinal classification task.",{"name":82,"@type":73,"acceptedAnswer":83},"What data and evaluation metric are used to assess the ML models?",{"text":84,"@type":76},"Experiments rely on real traffic patterns from the Internet Exchange Point in Seattle, and models are evaluated with a quality metric that accounts for network resource usage.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"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":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]