[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120378-en":3,"doc-seo-120378-105":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},120378,687197207057,"Sage","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Comparison of Machine Learning Techniques for Beam Management in 5G NR - Master’s thesis","Beam alignment during the initial access phase in beam management is a demanding, time-consuming task, especially as the antenna array size increases to offset millimeter-wave path loss. Machine learning approaches can select beam pairs more effectively than traditional exhaustive search. This thesis evaluates decision tree, random forest, AdaBoost, SVM, MLP, Q-learning, DQN, and DDQN with scenario-specific preprocessing. Three 3GPP-defined environments (UMi, UMa, RMa) are generated using QuaDRiGa, and random forest and AdaBoost achieve up to 90% accuracy.","Comparison of Machine Learning Techniques for Beam Management in 5G New Radio (NR)  \nMaster’s thesis in Master Programme of Data Science and AI  \nAXEL LUNDBERG SIMON SVENSSON  \nDEPARTMENT OF ELECTRICAL ENGINEERING  \nCHALMERS UNIVERSITY OF TECHNOLOGY Gothenburg, Sweden 2023  \n[www.chalmers.se](www.chalmers.se)  \nMaster’s thesis 2023  \nComparison of Machine Learning Techniques for Beam Management in 5G NR  \nAXEL LUNDBERG  \nSIMON SVENSSON  \nDepartment of Electrical Engineering Division of Communications, Antennas, and Optical Networks Communication Systems Group Chalmers University of Technology Gothenburg, Sweden 2023  \nComparison of Machine Learning Techniques for Beam Management in 5G NR AXEL LUNDBERG  \nSIMON SVENSSON  \n© AXEL LUNDBERG, 2023 .  \n© SIMON SVENSSON, 2023 .  \nSupervisor: Bengt Hallinger Tietoevry  \nAzadeh Tabeshnezhad Department of Electrical Engineering, Chalmers Examiner: Giuseppe Durisi Department of Electrical Engineering, Chalmers  \nMaster’s Thesis 2023  \nDepartment of Electrical Engineering  \nDivision of Communications, Antennas, and Optical Networks Chalmers University of Technology  \nSE-412 96 Gothenburg Telephone +46 31 772 1000  \nCover: Base station and user equipment searching for the optimal beam pair.  \nTypeset in LATEX  \nPrinted by Chalmers Reproservice Gothenburg, Sweden 2023  \nComparison of Machine Learning Techniques for Beam Management in 5G NR AXEL LUNDBERG  \nSIMON SVENSSON  \nDepartment of Electrical Engineering Chalmers University of Technology  \nAbstract  \nAligning beams in the initial access of beam management is a challenging and timeconsuming process. Especially, when the number of antenna elements grow large to compensate for high path loss of millimeter waves. Machine learning methods have successfully been applied to the problem of beam selection and perform much better than traditional methods like exhaustive search. In this thesis, some different machine learning approaches are investigated: decision tree, random forest, Adaptive Boosting (AdaBoost) , Support Vector Machine (SVM) , Multi-level Perceptron (MLP), Q-learning, Deep Q-Network (DQN) and Double Deep Q-Network (DDQN) . Each model is adapted to specific scenarios with different preprocessing steps. A total of three scenarios are explored which have been defined by the 3rd Generation Partnership Project (3GPP) : Urban Micro (UMi) , Urban Macro (UMa) and Rural Macro (RMa) . The UMi and UMa scenarios are both implemented with an explicit city layout containing static receivers. The RMa scenario is uniformly distributed and divided into two datasets: one for static receivers and one for dynamic receivers along tracks. Each scenario has been generated by the stochastic channel model called QuaDRiGa. The aim of the thesis is to provide a fair comparison of machine learning models by testing them on data from one simulator. Results show that random forest and AdaBoost perform best overall on all datasets with up to 90% accuracy when predicting the optimal beam pair, which suggests that the search space can be significantly reduced.  \nKeywords: 5G NR, Machine learning, Supervised learning, Reinforcement learning, Beam management, QuaDRiGa simulation, Beam alignment.  \nAcknowledgements  \nWe would like to express our gratitude to Tietoevry for letting us write our thesis there and to our supervisor at Tietoevry, Bengt Hallinger, who has provided us with his expertise in telecommunication and helped us look at problems from a new perspective at times where we progressed slowly. We want to thank our supervisor at Chalmers, Azadeh Tabeshnezhad, who has guided us with administrative tasks, questions about how the report should be structured and proofreading our drafts during the semester. Also, we would like to thank Giuseppe Durisi for taking on the role of examiner for our project. Without him the project would not have happened.  \nAxel Lundberg, Simon Svensson, Gothenburg, June 2023  \nContents  \nGlossary xi  \nAcronyms xiii  \nNomenclature ","cbCaisZRIw79HFOa","https://ap.wps.com/l/cbCaisZRIw79HFOa","pdf",4043447,1,83,"English","en",105,"# Abstract\n# Contents\n## Introduction\n## Communication Theory\n## Machine Learning","[{\"question\":\"Why is beam alignment in 5G NR beam management difficult?\",\"answer\":\"Beam alignment in the initial access phase is challenging and time-consuming, and the difficulty increases with larger antenna element counts used to compensate for millimeter-wave path loss.\"},{\"question\":\"Which machine learning models are compared in this thesis?\",\"answer\":\"The thesis evaluates decision tree, random forest, AdaBoost, SVM, MLP, Q-learning, DQN, and DDQN, each adapted to scenario-specific preprocessing.\"},{\"question\":\"How are evaluation scenarios generated?\",\"answer\":\"Three 3GPP scenarios—UMi, UMa, and RMa—are generated using the QuaDRiGa stochastic channel model, with UMi and UMa using explicit city layouts and RMa split into static and dynamic datasets.\"}]","Comparison of Machine Learning Techniques for Beam Management in 5G NR - Master’s thesis | PDF",1785729732,209,{"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},"comparison-of-machine-learning-techniques-for-beam-management-in-5g-nr-masters-thesis","",{"@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/comparison-of-machine-learning-techniques-for-beam-management-in-5g-nr-masters-thesis/120378/",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","2026-08-03",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 is beam alignment in 5G NR beam management difficult?","Question",{"text":75,"@type":76},"Beam alignment in the initial access phase is challenging and time-consuming, and the difficulty increases with larger antenna element counts used to compensate for millimeter-wave path loss.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning models are compared in this thesis?",{"text":80,"@type":76},"The thesis evaluates decision tree, random forest, AdaBoost, SVM, MLP, Q-learning, DQN, and DDQN, each adapted to scenario-specific preprocessing.",{"name":82,"@type":73,"acceptedAnswer":83},"How are evaluation scenarios generated?",{"text":84,"@type":76},"Three 3GPP scenarios—UMi, UMa, and RMa—are generated using the QuaDRiGa stochastic channel model, with UMi and UMa using explicit city layouts and RMa split into static and dynamic datasets.","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"]