[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126736-en":3,"doc-seo-126736-105":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},126736,962084925782,"Ava Thompson","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Machine Learning-Assisted mmWave Beam Management - Dissertation Overview","Millimeter wave (mmWave) communication relies on highly directional beamforming to overcome high isotropic path loss, yet narrow beams are vulnerable to blockage and reflections. This dissertation develops machine learning-assisted beam management methods that identify near-optimal beams with low overhead and latency. Three solutions are presented: ML-aided beam alignment using UE location context, a 5G-compatible site-specific probing codebook approach, and a grid-free probing method that computes continuous beamforming weights from a few measurements. Extensive dataset creation and evaluation address realistic dynamics, robustness, and trade-offs among speed and SNR.","Copyright by  \nYuqiang Heng 2022  \nThe Dissertation Committee for Yuqiang Heng certifies that this is the approved version of the following dissertation:  \nMachine Learning-Assisted mmWave Beam Management  \nCommittee:  \n\n| Jeffrey G. Andrews, Supervisor |\n| --- |\n| Brian L. Evans |\n| Alex Dimakis |\n| Hyeji Kim |\n\nVikram Chandrasekhar  \nMachine Learning-Assisted mmWave Beam Management  \nby  \nYuqiang Heng  \nDISSERTATION  \nPresented to the Faculty of the Graduate School of The University of Texas at Austin in Partial Fulfillment of the Requirements for the Degree of  \nDOCTOR OF PHILOSOPHY  \nTHE UNIVERSITY OF TEXAS AT AUSTIN  \nDecember 2022  \nAcknowledgments  \nI wish to thank my advisor Prof. Jeffrey G. Andrews. He inspires me to work on challenging problems and allows me great freedom to explore my research interests. His constant support and insightful advice – both in research and in my professional career – make this journey as pleasant and exciting as possible. I am lucky to have many outstanding colleagues at UT Austin, including Manan Gupta, Ian Roberts, Ahmad AlAmmouri, Hongxiang Xie and many others. Our many discussions have helped me both in research and personally. I would also like to thank Prof. Brian L. Evans, Prof. Alex Dimakis, Prof. Hyeji Kim and Dr. Vikram Chandrasekhar for serving as my committee members and providing valuable feedback. I wish to thank my colleagues at Samsung Research America, Charlie Zhang, Boon Loong Ng, Jianhua Mo and Vutha Va, whose guidance made my internship experiences exciting and fruitful.  \nLast but not least, I would like to thank my parents for their unconditional love and support.  \nMachine Learning-Assisted mmWave Beam Management  \nPublication No.    \nYuqiang Heng, Ph.D.  \nThe University of Texas at Austin, 2022  \nSupervisor: Jeffrey G. Andrews  \nMillimeter wave (mmWave) devices need to leverage highly directional beamforming (BF) to overcome the higher isotropic path loss. On the other hand, such narrow beams are sensitive to the propagation conditions including blockage and reflections. As a result, beam management – finding and maintaining good analog BF directions – is critical to enabling communication at the mmWave spectrum. This dissertation will focus on designing beam management solutions for mmWave systems that can find near-optimal beams with low overhead and latency.  \nIn the first part of this dissertation, a machine learning (ML)-aided beam alignment method is proposed where ML models are trained to predict candidate beams and serving base stations (BSs) using only the location information of user equipments (UEs) as context information. At the cost of only a small overhead in uplink feedback of a UE’s coordinates through  \nlower-frequency links, the proposed method can reduce the search space by approximately 4× for the optimal BS and over 10 × for the optimal beam, even in a dynamic environment with imperfect UE coordinates. A dataset modeling a realistic, generalizable environment is created using a state-of-the-art commercial ray-tracing software and published to train and validate the ML models.  \nTo further enhance the ease of adoption without modifications to the existing cellular network standards, a 5G-compatible beam alignment method that uses a site-specific probing codebook to predict candidate beams is proposed in the second part of this dissertation. The probing codebook and the beam predictor are jointly trained with a novel neural network (NN) architecture. By sweeping a small learned codebook that is adapted to the propagation environment, the proposed NN beam predictor can accurately select the optimal narrow beam while reducing the beam sweeping overhead by as much as 14× in challenging non-line-of-sight scenarios.  \nThe third part of this dissertation further explores the idea of sitespecific probing, and proposes a grid-free beam alignment approach that uses the measurements of a few probing beams to directly compute arbitrary BF weights for each","cbCaieA4ImpVVD3B","https://ap.wps.com/l/cbCaieA4ImpVVD3B","pdf",10669018,1,187,"English","en",105,"# Acknowledgments\n# Abstract\n# List of Tables\n# List of Figures\n# Chapter 1 - Introduction\n## Background and Related Work\n## Overview of Contributions\n## Notation\n## Organization of Dissertation\n# Chapter 2 - Machine Learning-Assisted Beam Alignment for mmWave Systems\n## Proposed Contributions\n## The Proposed Method and Metrics\n## System Model and Data Collection\n## Evaluation\n## Conclusion\n# Chapter 3 - Learning Site-Specific Probing Beams for Fast mmWave Beam Alignment\n## Proposed Contributions","[{\"question\":\"Why is beam management critical for mmWave communication?\",\"answer\":\"mmWave systems use highly directional beamforming to counter high isotropic path loss, but narrow beams are highly sensitive to propagation changes such as blockage and reflections. Effective beam management is needed to find and maintain good analog beam directions for reliable communication.\"},{\"question\":\"How does the first part’s ML-aided beam alignment reduce overhead and search complexity?\",\"answer\":\"It trains machine learning models to predict candidate beams and serving base stations using only UE location information as context. With small uplink feedback overhead via lower-frequency coordinate links, it reduces the search space significantly for both the optimal base station and optimal beam, even with imperfect UE coordinates.\"},{\"question\":\"What distinguishes the second and third parts of the dissertation?\",\"answer\":\"The second part proposes a 5G-compatible method using a site-specific probing codebook and a jointly trained beam predictor to reduce beam sweeping overhead, especially in non-line-of-sight scenarios. The third part extends site-specific probing by using measurements from a few probing beams to compute continuous beamforming weights (grid-free), improving speed and SNR trade-offs compared with exhaustive search and standard codebooks.\"}]","Machine Learning-Assisted mmWave Beam Management - Dissertation Overview | PDF",1785934523,471,{"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-assisted-mmwave-beam-management-dissertation-overview","",{"@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-assisted-mmwave-beam-management-dissertation-overview/126736/",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","2026-08-05",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 management critical for mmWave communication?","Question",{"text":75,"@type":76},"mmWave systems use highly directional beamforming to counter high isotropic path loss, but narrow beams are highly sensitive to propagation changes such as blockage and reflections. Effective beam management is needed to find and maintain good analog beam directions for reliable communication.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the first part’s ML-aided beam alignment reduce overhead and search complexity?",{"text":80,"@type":76},"It trains machine learning models to predict candidate beams and serving base stations using only UE location information as context. With small uplink feedback overhead via lower-frequency coordinate links, it reduces the search space significantly for both the optimal base station and optimal beam, even with imperfect UE coordinates.",{"name":82,"@type":73,"acceptedAnswer":83},"What distinguishes the second and third parts of the dissertation?",{"text":84,"@type":76},"The second part proposes a 5G-compatible method using a site-specific probing codebook and a jointly trained beam predictor to reduce beam sweeping overhead, especially in non-line-of-sight scenarios. The third part extends site-specific probing by using measurements from a few probing beams to compute continuous beamforming weights (grid-free), improving speed and SNR trade-offs compared with exhaustive search and standard codebooks.","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"]