Dynamic Resource Allocation for Network Slicing via GAT based Reinforcement Learning

Dynamic Resource Allocation for Network Slicing via GAT based Reinforcement Learning | 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 Dynamic Resource Allocation for Network Slicing via GAT based Reinforcement Learning Xin Ning, Lina Zheng, Mingwei Gong, Bo Zhao, Aniket Mahanti This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8516736/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 4 You are reading this latest preprint version Abstract With the rapid growth of emerging network transmission services, communication networks face increasing challenges. Network slicing addresses these challenges by enabling resource isolation and service customization through multiple virtual slices on a shared physical infrastructure. However, resource allocation and path selection in slice management are NP-hard problems that must adapt to dynamic network states and service demands, making static optimization methods inadequate. Moreover, existing reinforcement learning approaches for slice management still face limitations in scheduling control, system modeling, and state encoding. To address these issues, this paper proposes a novel network slicing resource allocation framework that integrates Graph Attention Networks (GAT) for dynamic state encoding and a Deep Deterministic Policy Gradient algorithm for continuous control. The framework jointly optimizes bandwidth allocation factors and path weights, effectively capturing dynamic topologies and link attributes. Experimental results demonstrate that the proposed method achieves superior performance over baseline approaches, improving resource fairness and reducing delay by 14%. The proposed scheduling framework enhances service differentiation by prioritizing traffic in real time, thereby improving reliability, responsiveness, and overall user experience. Dynamic resource allocation network slicing reinforcement learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 27 Feb, 2026 Editor assigned by journal 27 Feb, 2026 Submission checks completed at journal 07 Jan, 2026 First submitted to journal 04 Jan, 2026 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-8516736","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":598204025,"identity":"988835de-f9c1-4fe7-8efa-1b23f193a827","order_by":0,"name":"Xin Ning","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Xin","middleName":"","lastName":"Ning","suffix":""},{"id":598204026,"identity":"4d2415de-4c36-46ff-bc0f-876646b488a1","order_by":1,"name":"Lina Zheng","email":"","orcid":"","institution":"Shandong University","correspondingAuthor":false,"prefix":"","firstName":"Lina","middleName":"","lastName":"Zheng","suffix":""},{"id":598204027,"identity":"5fce82b0-4adb-4dc9-8cba-d664c4cd43fa","order_by":2,"name":"Mingwei Gong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAwUlEQVRIiWNgGAWjYNCCCij9gHgtZxgkwHQC0ToY20jRotu/+NjDr/O21Zm39xh+SGCwkyeoxezGs3Rj2W23JWTOnDGWSGBINmwgrOWMmbQkUIuERI4BUMsBRiK1zAFrMf4B1GJPWMv5HjPJjw1gLWYgWxKJsIUtTZrh2G3JGTzHyiwSDJKTibDl8DHJHzW3+SXYmzff+FBhZ0tQCwPQMcw8YBaHAQODAUH1QMB/gIHxB5jF/oAY9aNgFIyCUTACAQC8jz3iS2eaWQAAAABJRU5ErkJggg==","orcid":"","institution":"Mount Royal University","correspondingAuthor":true,"prefix":"","firstName":"Mingwei","middleName":"","lastName":"Gong","suffix":""},{"id":598204028,"identity":"b9ed15aa-9eb7-40e0-9f1f-92c220b07a58","order_by":3,"name":"Bo Zhao","email":"","orcid":"","institution":"Northwestern Polytechnical University","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Zhao","suffix":""},{"id":598204029,"identity":"adfb2d8c-71a4-4f01-bd3e-143f636f664a","order_by":4,"name":"Aniket Mahanti","email":"","orcid":"","institution":"University of Auckland","correspondingAuthor":false,"prefix":"","firstName":"Aniket","middleName":"","lastName":"Mahanti","suffix":""}],"badges":[],"createdAt":"2026-01-05 04:08:29","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8516736/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8516736/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108007246,"identity":"8aa97a03-d7e5-4ae5-88a7-56c47c94e467","added_by":"auto","created_at":"2026-04-28 12:59:09","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1123661,"visible":true,"origin":"","legend":"","description":"","filename":"SpringerNatureLaTeXTemplate.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8516736/v1_covered_a50e600b-3703-4714-9ae2-dd04db91eb3d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dynamic Resource Allocation for Network Slicing via GAT based Reinforcement Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"journal-of-network-and-systems-management","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jons","sideBox":"Learn more about [Journal of Network and Systems Management](http://link.springer.com/journal/10922)","snPcode":"10922","submissionUrl":"https://submission.nature.com/new-submission/10922/3","title":"Journal of Network and Systems Management","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Dynamic resource allocation, network slicing, reinforcement learning","lastPublishedDoi":"10.21203/rs.3.rs-8516736/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8516736/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the rapid growth of emerging network transmission services, communication networks face increasing challenges. Network slicing addresses these challenges by enabling resource isolation and service customization through multiple virtual slices on a shared physical infrastructure. However, resource allocation and path selection in slice management are NP-hard problems that must adapt to dynamic network states and service demands, making static optimization methods inadequate. Moreover, existing reinforcement learning approaches for slice management still face limitations in scheduling control, system modeling, and state encoding. To address these issues, this paper proposes a novel network slicing resource allocation framework that integrates Graph Attention Networks (GAT) for dynamic state encoding and a Deep Deterministic Policy Gradient algorithm for continuous control. The framework jointly optimizes bandwidth allocation factors and path weights, effectively capturing dynamic topologies and link attributes. Experimental results demonstrate that the proposed method achieves superior performance over baseline approaches, improving resource fairness and reducing delay by 14\\%. The proposed scheduling framework enhances service differentiation by prioritizing traffic in real time, thereby improving reliability, responsiveness, and overall user experience.","manuscriptTitle":"Dynamic Resource Allocation for Network Slicing via GAT based Reinforcement Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-28 12:17:46","doi":"10.21203/rs.3.rs-8516736/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-02-27T14:09:25+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-27T14:08:58+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-01-07T15:26:00+00:00","index":"","fulltext":""},{"type":"submitted","content":"Journal of Network and Systems Management","date":"2026-01-05T03:58:10+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"journal-of-network-and-systems-management","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jons","sideBox":"Learn more about [Journal of Network and Systems Management](http://link.springer.com/journal/10922)","snPcode":"10922","submissionUrl":"https://submission.nature.com/new-submission/10922/3","title":"Journal of Network and Systems Management","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"8e585b97-b146-47b4-8e2a-228f6f0d3f38","owner":[],"postedDate":"April 28th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-04-28T12:17:46+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-28 12:17:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8516736","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8516736","identity":"rs-8516736","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}