[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126239-en":3,"doc-seo-126239-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":20,"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},126239,2336475104042,"Skyler","https://ap-avatar.wpscdn.com/avatar/22000c4c32af1715be0?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786537525561427321",8,"Research & Report","Compensation of Phase Noise in 5G NR with Machine Learning","Mobile data growth driven by massive connected devices requires next-generation communications offering improved user experience and intelligent connectivity. 5G New Radio (NR) targets this decade, and UltraDense Networks at millimeter-wave frequencies boost capacity, but higher frequencies combined with OFDM increase sensitivity to phase noise. The work compensates phase noise using pilot-based estimation, then extends it with machine learning using Gaussian mixture model and weighted k-nearest neighbors to reduce pilot requirements while keeping complexity affordable.","This is a postprint version of the following published document:  \nSuarez, L. M.-M., & Armada, A. G. (2022) . Compensation of phase noise in 5G NR with machine learning. In: 2022 IEEE Globecom Workshops (GC Wkshps) .  \nDOI: [https://doi.org/10.1109/GCWkshps56602.2022.10008628](https://doi.org/10.1109/GCWkshps56602.2022.10008628)  \n© 2022 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 collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.  \nCompensation of Phase Noise in 5G NR with  \nMachine Learning  \nLianet Mndez-Monsanto Surez  \nDepartment of Signal Theory and Communications Universidad Carlos III de Madrid [100384026@alumnos.uc3m.es](100384026@alumnos.uc3m.es)  \nAna Garc´ıa Armada  \nDepartment of Signal Theory and Communications Universidad Carlos III de Madrid [anagar@ing.uc3m.es](anagar@ing.uc3m.es)  \nAbstract—The growth in mobile data traffic d ue t o t he immense increase in the number of connected personal devices requires a next generation of mobile communications capable of providing new services and applications. The fifth generation 5G New Radio (NR) is the one implemented this decade, with the objective of improving user experience and connecting society in an intelligent environment. One of the key technologies to meet the demands of higher system capacity is the use of UltraDense Networks (UDNs) in millimeter-wave (mmW) frequencies. However, the combination of higher frequencies and the OFDM waveform may increase the system sensitivity to phase noise (PN). In this work, we compensate PN by using classical pilot-based estimation and extend this method by using machine learning (ML) algorithms. Both Gaussian mixture model (GMM) and weighted k-nearest neighbors (KNN) techniques are proposed. We show that with them a reduction of the required amount of pilots is achieved, while maintaining an affordable complexity. 1  \nIndex Terms—phase noise, millimeter waves, ultra-dense networks, artificial intelligence, 5 G NR, PT-RS  \nI. INTRODUCTION  \nThe requirements of very high system capacity and enduser data rates in the fifth g eneration ( 5G) o f m obile communications can be achieved at localized environments by the dense deployment of small cells using millimeter-wave (mmW) frequencies [1], situated in the range of 24 to 52 GHz [2] . Furthermore, transmissions at frequencies higher than 100 GHz are being considered for next generations such as the sixth generation of mobile communications (6G) [3] . However, wireless transmissions at these frequency bands face technological challenges. One of the main disadvantages of mmWin combination with OFDM is the presence of severe phase noise (PN), whose effects are worse as the carrier frequency increases. Third Generation Partnership Project (3GPP) studies [4] conclude that transmissions at a frequency of 30 GHz are not feasible if PN is not mitigated, which is conventionally carried out by introducing pilot-based estimation. However, the required number of pilots for its compensation may be jeopardizing the throughput, which was the ultimate goal. This paper focuses on the following:  \n1This work has been supported by project IRENE-EARTH (PID2020- 115323RB-C33 / AEI / 10. 13039/501100011033) .  \n• Determining the number of pilots needed in the traditional compensation method to accurately mitigate PN in mm transceivers.  \n• Propose alternative methods for PN compensation using machine learning (ML) algorithms, trying to reduce (or eliminate) the above-mentioned number of pilots. Two approaches are analyzed. The first one is an unsupervised, parametric clustering algorithm, namely, a Gaussian mixture model (GMM) . The second one is a nonparametric, supervised algorithm given by a weighted knearest neighbor","cbCaikTKGiNGZYYM","https://ap.wps.com/l/cbCaikTKGiNGZYYM","pdf",1030340,7,1,"English","en",105,"# Introduction\n## Signal and Phase Noise Models\n## Phase Noise Compensation with Pilots and Machine Learning","[{\"question\":\"Why does phase noise become more problematic in 5G NR millimeter-wave OFDM?\",\"answer\":\"Higher carrier frequencies worsen the effects of phase noise, and when combined with OFDM the system becomes more sensitive to PN impairments.\"},{\"question\":\"How is phase noise compensation performed in the proposed approach?\",\"answer\":\"Phase noise is compensated first using classical pilot-based estimation, then extended using machine learning algorithms for improved efficiency.\"},{\"question\":\"Which machine learning techniques are proposed to reduce pilot overhead?\",\"answer\":\"The document proposes a Gaussian mixture model (GMM) and a weighted k-nearest neighbors (KNN) approach, targeting a reduction in the number of required pilots while maintaining feasible complexity.\"}]","Compensation of Phase Noise in 5G NR with Machine Learning | PDF",1785904000,18,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"compensation-of-phase-noise-in-5g-nr-with-machine-learning","",{"@graph":36,"@context":86},[37,54,69],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":21},"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/compensation-of-phase-noise-in-5g-nr-with-machine-learning/126239/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why does phase noise become more problematic in 5G NR millimeter-wave OFDM?","Question",{"text":76,"@type":77},"Higher carrier frequencies worsen the effects of phase noise, and when combined with OFDM the system becomes more sensitive to PN impairments.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is phase noise compensation performed in the proposed approach?",{"text":81,"@type":77},"Phase noise is compensated first using classical pilot-based estimation, then extended using machine learning algorithms for improved efficiency.",{"name":83,"@type":74,"acceptedAnswer":84},"Which machine learning techniques are proposed to reduce pilot overhead?",{"text":85,"@type":77},"The document proposes a Gaussian mixture model (GMM) and a weighted k-nearest neighbors (KNN) approach, targeting a reduction in the number of required pilots while maintaining feasible complexity.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},"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":107,"slug":138},19,"General","general"]