[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83272-en":3,"doc-seo-83272-105":29,"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":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":13,"seo_description":14,"update_tm":27,"read_time":28},83272,13056703019662,"Evangeline","https://ap-avatar.wpscdn.com/avatar/be000253a8e92610077?_k=1778726343310543188",8,"Research & Report","PHaul: A PPO-Based Forwarding Agent for Sub6 Enhanced Integrated Access and Backhaul Networks","3GPP Integrated Access and Backhaul (IAB) enables cost-efficient deployment of outdoor mm-wave access by reusing spectrum for both access and backhaul, yet wireless backhaul becomes the main performance bottleneck. mm-wave backhaul performance depends heavily on line-of-sight conditions, so the paper augments IAB backhaul with additional Sub6 links to improve capacity and robustness. It introduces PHaul, a forwarding engine that uses offline path selection plus an online PPO-based deep reinforcement learning agent with execution under 10 seconds and evaluates throughput efficiency and fairness gains up to 36% and 20%.","This article has been accepted for publication in IEEE Transactions on Network and Service Management. This is the author’s version which has not been fully edited and content may change prior to final publication. Citation information: DOI  \n10.1109/TNSM.2024.3435505 .  \nPHaul: A PPO-based forwarding agent for Sub6 enhanced Integrated Acess and Backhaul networks  \nJorge Pueyo  \nI2CAT Foundation [jorge.pueyo@i2cat.net](jorge.pueyo@i2cat.net)  \nDaniel Camps-Mur  \nI2CAT Foundation [daniel.camps@i2cat.net](daniel.camps@i2cat.net)  \nMiguel Catalan-Cid  \nI2CAT Foundation [miguel.catalan@i2cat.net](miguel.catalan@i2cat.net)  \narXiv :2607 .07584v 1 [ cs .NI] 8 Jul 2026  \nAbstract—3GPP Integrated Access and Backhaul (IAB) allows operators to deploy outdoor mm-wave access networks ina cost-eﬀicient manner, by reusing the same spectrum in access and backhaul. In IAB networks the performance bottleneck is the wireless backhaul segment, where eﬀicient forwarding strategies are needed to effectively use the available capacity. In addition, the performance of the mm-wave IAB backhaul segment is contingent on the availability of line of sight (LoS) conditions in the selected deployment sites. To mitigate LoS dependence, in this paper, we propose to complement the mmwave backhaul segment of IAB networks with additional Sub6 backhaul links, which contribute to the capacity and robustness of the backhaul network. We refer to IAB networks combining Sub6 and mm-wave links in the backhaul as Sub6 enhanced IAB networks. In this context, the main contribution of this paper is PHaul, a forwarding engine for Sub6 enhanced IAB networks that accomodates different traﬀic engineering criteria, and combines an offline path selection heuristic with an online Deep Reinforcement Learning (DRL) agent based on Proximal Policy Optimization (PPO) . By leveraging a network digital twin of the IAB wireless backhaul, PHaul periodically samples the input traﬀic of the backhaul network and updates flow to path mappings, with execution times below 10 seconds in realistic backhaul topologies. We present an exhaustive performance evaluation, where we demonstrate that PHaul can achieve gains of up to 36% in throughput eﬀiciency and of up to 20% in fairness, when compared against two alternative heuristics in a wide range of network configurations. We also demonstrate that PHaul is robust to differences between the network topologies considered in the training and inference phases, which can occur in practice due to link failures.  \nIndex Terms—3GPP IAB, Sub6 and mm-wave, Deep Reinforcement Learning (DRL), Proximal Policy Optimization (PPO)  \nI. Introduction  \nAddressing the data rate demands of future communication services will require heterogeneous 5G-Advanced (5GA) networks with a dense high-capacity layer composed of outdoor mm-wave (26/28 GHz) small cells [1] . This trend is expected to continue in 6G networks, where the SubTHz band (90GHz-300GHz) is being considered to deliver even greater access capacities [2] .  \nLaying out dedicated fibre for backhauling is a roadblock to enabling a massive deployment of outdoor small  \nThis work was funded by the European Commission through the SNS JU project NANCY (grant agreement No. 101096456) . The authors acknowledge CERCA Programme/Generalitat de Catalunya for sponsoring part of this work.  \ncells. To address this challenge 3GPP introduced the Integrated Access and Backhaul (IAB) technology in Release 16 [3] . The idea of IAB is to enable an operator to start by deploying a small number of fibre connected mm-wave small cells, known as donor nodes in IAB terminology, and to extend service coverage by deploying additional IAB nodes that are wirelessly backhauled through donor nodes, and can provide direct service to User Equipments (UEs), or act as parent nodes for other IAB nodes. When service demand grows, an operator can add fibre connectivity to IAB nodes, upgrading them to donor nodes, thus increasing the effective back","cbCaivPlQTaX3vLG","https://ap.wps.com/l/cbCaivPlQTaX3vLG","pdf",1379242,1,18,"English","en",105,"# Introduction\n## Integrated Access and Backhaul (IAB)\n## Sub6-enhanced IAB backhaul design\n## Motivation for adaptive routing and efficient forwarding","[{\"question\":\"What problem does PHaul address in IAB networks?\",\"answer\":\"PHaul targets inefficient wireless backhaul forwarding, where performance is limited by the backhaul segment and where mm-wave links suffer from line-of-sight dependence.\"},{\"question\":\"How does PHaul reduce reliance on line-of-sight conditions?\",\"answer\":\"It complements the mm-wave backhaul with additional Sub6 backhaul links, forming Sub6 enhanced IAB networks that increase capacity and robustness.\"},{\"question\":\"How is forwarding decided in PHaul?\",\"answer\":\"PHaul combines an offline path selection heuristic with an online deep reinforcement learning agent based on Proximal Policy Optimization (PPO), updating flow-to-path mappings by sampling input traffic from a network digital twin.\"}]",1784186421,45,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"phaul-a-ppo-based-forwarding-agent-for-sub6-enhanced-integrated-access-and-backhaul-networks","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/phaul-a-ppo-based-forwarding-agent-for-sub6-enhanced-integrated-access-and-backhaul-networks/83272/",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":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",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},"What problem does PHaul address in IAB networks?","Question",{"text":75,"@type":76},"PHaul targets inefficient wireless backhaul forwarding, where performance is limited by the backhaul segment and where mm-wave links suffer from line-of-sight dependence.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does PHaul reduce reliance on line-of-sight conditions?",{"text":80,"@type":76},"It complements the mm-wave backhaul with additional Sub6 backhaul links, forming Sub6 enhanced IAB networks that increase capacity and robustness.",{"name":82,"@type":73,"acceptedAnswer":83},"How is forwarding decided in PHaul?",{"text":84,"@type":76},"PHaul combines an offline path selection heuristic with an online deep reinforcement learning agent based on Proximal Policy Optimization (PPO), updating flow-to-path mappings by sampling input traffic from a network digital twin.","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},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":45,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":45,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]