[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126593-en":3,"doc-seo-126593-105":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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":11,"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},126593,687207020761,"Patrick","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Heuristic Algorithms for RIS-assisted Wireless Networks - Exploring Heuristic-aided Machine Learning","Reconfigurable intelligent surfaces (RISs) enable smarter radio environments, but their integration into wireless networks creates major challenges in network management due to large, complex solution spaces and coupled control variables. This work examines heuristic algorithms for optimizing RIS-aided networks, including greedy methods, meta-heuristics, and matching theory. It further combines heuristics with machine learning by proposing heuristic-aided ML algorithms, then validates the approach through a case study showing improved data rates and faster convergence for heuristic deep reinforcement learning.","Heuristic Algorithms for RIS-assisted Wireless Networks: Exploring Heuristic-aided  \nMachine Learning  \nHao Zhou, Melike Erol-Kantarci, Senior Member, IEEE, Yuanwei Liu, Senior Member, IEEE,  \nand H. Vincent Poor, Life Fellow, IEEE  \narXiv :2307 .0 1205v 1 [ cs .NI] 26 Jun 2023  \nAbstract—Reconfigurable intelligent surfaces (RISs) are a promising technology to enable smart radio environments. However, integrating RISs into wireless networks also leads to substantial complexity for network management. This work investigates heuristic algorithms and applications for optimizing RIS-aided wireless networks, including greedy algorithms, meta-heuristic algorithms, and matching theory. Moreover, we combine heuristic algorithms with machine learning (ML), and propose three heuristic-aided ML algorithms, namely heuristic deep reinforcement learning (DRL), heuristic-aided supervised learning, and heuristic hierarchical learning. Finally, a case study shows that heuristic DRL can achieve higher data rates and faster convergence than conventional DRL. This work aims to provide a new perspective for optimizing RIS-aided wireless networks by taking advantage of heuristic algorithms and ML.  \nIndex Terms—Reconfigurable intelligent surfaces, heuristic methods, machine learning, optimization.  \nI. INTRODUCTION  \nReconfigurable intelligent surfaces (RISs) have emerged asan attractive technology for envisioned 6G networks, enabling smart radio environments to improve energy efficiency, network coverage, channel capacity, and so on [1] . Many existing studies have demonstrated the capability of RISs, but incorporating RISs into existing wireless networks significantly increases the network management complexity. In particular, each small RIS element requires sophisticated phase-shift control, resulting in a very large solution space. In addition, due to their low hardware costs and energy consumption, RISscan be combined with other technologies, such as unmanned aerial vehicle (UAV) and non-orthogonal multiple access (NOMA), leading to joint optimization problems with coupled control variables. Therefore, efficient optimization techniques are crucial to realizing the full potential of RISs.  \nExisting RIS optimization techniques can be categorized into three main approaches: convex optimization, machine learning (ML), and heuristic algorithms [2] . Convex optimization algorithms have been widely applied for optimizing RIS-aided wireless networks, e.g., using block coordinate  \nH. Zhou and M. Erol-Kantarci are with the School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada.(emails:fhzhou098, [melike.erolkantarci](melike.erolkantarcig@uottawa.ca)[g](melike.erolkantarcig@uottawa.ca)[@uottawa.ca](melike.erolkantarcig@uottawa.ca)).  \nYuanwei Liu is with the School of Electronic Engineering and Computer Science, Queen Mary University of London, London E1 4NS, U.K.([email:yuanwei.liu@qmul.ac.uk](email:yuanwei.liu@qmul.ac.uk)).  \nH. Vincent Poor is with the Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544 USA (email: [poor@princeton.edu](poor@princeton.edu)).  \ndescent for joint active and passive beamforming, and applying fractional programming to decouple the received signal strength with interference and noise [3] . However, RIS-related optimization problems are usually non-convex and highly nonlinear, which makes the application of convex optimization requires case-by-case analysis, resulting in considerable difficulties for the algorithm design.  \nBy contrast, ML algorithms have fewer requirements on problem formulations. For instance, when using a Markov decision process (MDP) for RIS passive beamforming, channel state information (CSI), RIS phase shifts, and objective functions are defined as states, actions, and rewards, respectively. Then, reinforcement learning algorithm is deployed to maximize the reward by trying different action combinations. However, ML alg","cbCaiqfeD57rsTWL","https://ap.wps.com/l/cbCaiqfeD57rsTWL","pdf",8281263,2,1,"English","en",105,"# Introduction\n## RIS optimization approaches\n# Heuristic algorithms and applications\n## Greedy and meta-heuristic methods\n## Matching theory\n# Heuristic-aided machine learning\n## Heuristic deep reinforcement learning\n## Heuristic-aided supervised learning\n## Heuristic hierarchical learning\n# Case study and performance comparison\n## Data rate and convergence results","[{\"question\":\"Why is RIS integration difficult for wireless network management?\",\"answer\":\"RISs require sophisticated phase-shift control for many elements, creating a very large solution space. Joint optimization also introduces coupled control variables, increasing complexity.\"},{\"question\":\"What heuristic approaches are investigated for RIS-aided wireless networks?\",\"answer\":\"The work studies greedy algorithms, meta-heuristic algorithms, and matching theory to optimize RIS-aided networks efficiently.\"},{\"question\":\"How does heuristic-aided machine learning improve over conventional deep reinforcement learning?\",\"answer\":\"The proposed heuristic deep reinforcement learning achieves higher data rates and faster convergence than conventional deep reinforcement learning in the presented case study.\"}]","Heuristic Algorithms for RIS-assisted Wireless Networks - Exploring Heuristic-aided Machine Learning | PDF",1785933585,20,{"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},"heuristic-algorithms-for-ris-assisted-wireless-networks-exploring-heuristic-aided-machine-learning","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/heuristic-algorithms-for-ris-assisted-wireless-networks-exploring-heuristic-aided-machine-learning/126593/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is RIS integration difficult for wireless network management?","Question",{"text":75,"@type":76},"RISs require sophisticated phase-shift control for many elements, creating a very large solution space. Joint optimization also introduces coupled control variables, increasing complexity.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What heuristic approaches are investigated for RIS-aided wireless networks?",{"text":80,"@type":76},"The work studies greedy algorithms, meta-heuristic algorithms, and matching theory to optimize RIS-aided networks efficiently.",{"name":82,"@type":73,"acceptedAnswer":83},"How does heuristic-aided machine learning improve over conventional deep reinforcement learning?",{"text":84,"@type":76},"The proposed heuristic deep reinforcement learning achieves higher data rates and faster convergence than conventional deep reinforcement learning in the presented case study.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"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":29,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":29,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":29,"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"]