Machine Learning–Enhanced NOMA With AI- Driven Power Allocation for Multi-RIS Assisted 6G Terahertz Networks

Machine Learning–Enhanced NOMA With AI- Driven Power Allocation for Multi-RIS Assisted 6G Terahertz Networks | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Machine Learning–Enhanced NOMA With AI- Driven Power Allocation for Multi-RIS Assisted 6G Terahertz Networks Mohanad Mezher, Mustafa Mohammed Abdulkareem This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9172999/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Terahertz (THz) communication stands as an essential technology for physical layers in sixth-generation (6G) wireless networks. The system delivers extremely high bandwidth that reaches 10 GHz per channel together with data rates exceeding 1 Tbps. The coverage of THz systems together with link reliability suffers from three main factors which include distance-dependent path loss, specific frequency molecular absorption, and the ability of signals to face obstacles. Reconfigurable intelligent surfaces (RISs) create a new method to modify wireless signal patterns through their ability to control signal propagation using their programmable passive beamforming technology. Non-orthogonal multiple access (NOMA) enables multiple users to share the same time-frequency resources through power-domain superposition coding and successive interference cancellation (SIC) which results in improved spectral efficiency. The paper introduces a machine learning (ML)-augmented NOMA framework that uses AI-driven power allocation to optimize multi-RIS-assisted THz networks. The offline-trained supervised neural network (SNN) develops the ability to convert cascaded channel state information (CSI) into optimal NOMA power coefficients by using CVX solver solutions as its training data. The study establishes closed-form solutions to determine both the signal-to-interference-plus-noise ratio (SINR) and maximum sum-rate results which utilize SIC decoding. The recommended AI-based approach achieves sum rates that reach 1.5% to 3.1% of the CVX optimal benchmark according to 10,000 Monte Carlo simulations. The system achieves a reduction in computation delay which reaches 249 times from 847 ms to just 3.4 ms per scheduling slot. The 4-panel multi-RIS THz system demonstrates performance gains that reach 27.2% when compared to equal power allocation (EPA) and 15.9% against heuristic allocation. The scalability study confirms the linearity of the inference complexity O(L·D), meaning the framework can be acceptable for real-time deployment into the 6th generation THz era. 6G communications terahertz networks reconfigurable intelligent surfaces NOMA machine learning power allocation SIC Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-9172999","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":633570202,"identity":"4ab91bb2-34bc-4479-9fb5-8432826beccb","order_by":0,"name":"Mohanad Mezher","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/UlEQVRIiWNgGAWjYFACHhDBzMAgAWIb2MAFeYjUUpAG4ZOg5cNhuBacQLe99+DnghprBv7Z3YkP3hicj7aXSGB88LaNQYbvAHYtZmfOJUvPOJbOIHHn7GbDOQa3c3skEpgN57Yx8Eji0nIjx0Cah+0wA8ON3G3SPBAtbNK8QC0GuLUY/+b5d5hB/kbu9t88BudAWth/E9BiBjTzMIMB0BZmoDKwLcx4tZw5Y2bN25fOY3gjd7PkHIPk3J4zD5sl55yTwO2X4z3Gt3m+WcvJ3cjd+OHNH7vc9vbkgx/elNnY4woxGECOCMYGBnA0EdCCDZChZRSMglEwCoYlAAAKAFlxQ7tWogAAAABJRU5ErkJggg==","orcid":"","institution":"Middle Technical University","correspondingAuthor":true,"prefix":"","firstName":"Mohanad","middleName":"","lastName":"Mezher","suffix":""},{"id":633570203,"identity":"83bc77e2-1f5f-4433-8fe6-b41a585198c5","order_by":1,"name":"Mustafa Mohammed Abdulkareem","email":"","orcid":"","institution":"University of Information Technology and Communications","correspondingAuthor":false,"prefix":"","firstName":"Mustafa","middleName":"Mohammed","lastName":"Abdulkareem","suffix":""}],"badges":[],"createdAt":"2026-03-19 21:23:18","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9172999/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9172999/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":109244798,"identity":"f6d0cb95-107e-4f74-8593-91f21c9c43b9","added_by":"auto","created_at":"2026-05-14 07:41:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":526492,"visible":true,"origin":"","legend":"","description":"","filename":"MLEnhancedNOMA6GTHzCorrected.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9172999/v1_covered_5e2bd7aa-b64d-45ec-97bd-5dececda1a65.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Machine Learning–Enhanced NOMA With AI- Driven Power Allocation for Multi-RIS Assisted 6G Terahertz Networks","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"6G communications, terahertz networks, reconfigurable intelligent surfaces, NOMA, machine learning, power allocation, SIC","lastPublishedDoi":"10.21203/rs.3.rs-9172999/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9172999/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Terahertz (THz) communication stands as an essential technology for physical layers in sixth-generation (6G) wireless networks. The system delivers extremely high bandwidth that reaches 10 GHz per channel together with data rates exceeding 1 Tbps. The coverage of THz systems together with link reliability suffers from three main factors which include distance-dependent path loss, specific frequency molecular absorption, and the ability of signals to face obstacles. Reconfigurable intelligent surfaces (RISs) create a new method to modify wireless signal patterns through their ability to control signal propagation using their programmable passive beamforming technology. Non-orthogonal multiple access (NOMA) enables multiple users to share the same time-frequency resources through power-domain superposition coding and successive interference cancellation (SIC) which results in improved spectral efficiency. The paper introduces a machine learning (ML)-augmented NOMA framework that uses AI-driven power allocation to optimize multi-RIS-assisted THz networks. The offline-trained supervised neural network (SNN) develops the ability to convert cascaded channel state information (CSI) into optimal NOMA power coefficients by using CVX solver solutions as its training data. The study establishes closed-form solutions to determine both the signal-to-interference-plus-noise ratio (SINR) and maximum sum-rate results which utilize SIC decoding. The recommended AI-based approach achieves sum rates that reach 1.5% to 3.1% of the CVX optimal benchmark according to 10,000 Monte Carlo simulations. The system achieves a reduction in computation delay which reaches 249 times from 847 ms to just 3.4 ms per scheduling slot. The 4-panel multi-RIS THz system demonstrates performance gains that reach 27.2% when compared to equal power allocation (EPA) and 15.9% against heuristic allocation. The scalability study confirms the linearity of the inference complexity O(L·D), meaning the framework can be acceptable for real-time deployment into the 6th generation THz era.","manuscriptTitle":"Machine Learning–Enhanced NOMA With AI- Driven Power Allocation for Multi-RIS Assisted 6G Terahertz Networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-04 18:06:02","doi":"10.21203/rs.3.rs-9172999/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"e7da13d2-a2d6-4e8e-9fa0-8576beb55700","owner":[],"postedDate":"May 4th, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Withdrawn","date":"2026-05-14T07:32:56+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-12T13:50:08+00:00","index":31,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-11T11:19:33+00:00","index":30,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-02T15:28:18+00:00","index":29,"fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-05-01T06:57:38+00:00","index":28,"fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-14T07:41:06+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-04 18:06:02","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9172999","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9172999","identity":"rs-9172999","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}