Intelligent Resource Orchestration for Fog-Edge Computing in Software-Defined Networks: A Deep Reinforcement Learning Approach

Intelligent Resource Orchestration for Fog-Edge Computing in Software-Defined Networks: A Deep Reinforcement Learning Approach | 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 Intelligent Resource Orchestration for Fog-Edge Computing in Software-Defined Networks: A Deep Reinforcement Learning Approach Tan Wei Liang, Yamamoto Kenji, Park Min-Jae This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8118120/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 Fog and edge computing architectures integrated with software-defined networking (SDN) have emerged as transformative paradigms for deploying ultra-low latency applications in distributed systems. This paper introduces an intelligent resource orchestration framework that revolutionizes computational offloading and resource allocation across fog and edge nodes through advanced deep reinforcement learning techniques. By synergizing Lyapunov optimization with deep Q-networks (DQN) and leveraging SDN's programmable control plane, our approach achieves unprecedented reductions in service latency and energy consumption while guaranteeing strict quality of service (QoS) requirements. The framework employs a novel hybrid optimization model enhanced with deep learning approximations for exceptional scalability in large-scale fog-edge networks. Comprehensive simulations on heterogeneous edge-cloud topologies demonstrate that our method dramatically outperforms state-of-the-art approaches, achieving groundbreaking improvements of up to 68% in latency reduction and 52% in energy efficiency across diverse workload scenarios, establishing new benchmarks for intelligent resource management in distributed computing environments. Computer Architecture and Engineering Theoretical Computer Science Artificial Intelligence and Machine Learning fog computing edge computing intelligent resource orchestration software-defined networking deep reinforcement learning task offloading quality of service distributed systems Full Text Additional Declarations The authors declare no competing interests. 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-8118120","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":545305850,"identity":"eab0388e-6678-42ab-a89d-a312b8bdae35","order_by":0,"name":"Tan Wei Liang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAy0lEQVRIiWNgGAWjYNCCAhsIzUOMYogigzTStRwmQYs9+9kDzDwG5/MMzh9gfPC2jcFe3oGQLTx5CUAtt4sNbiQwG85tY0jceICgw3IMmHMMbiduuMHAJs3bxpBg2EBIC/8bkJZziRvOH2D/DdRiT1iLBNiWA4kbDiSwMQO1MM4noIOB58Ybg8N/DJITZ95IbJacc04icQMhLez9OYYPZ1TYJfadP3zww5syG3t5Qg4DgQMQihGkVoLB4AARWlABUbaMglEwCkbBiAIAIlI7R4QN6LIAAAAASUVORK5CYII=","orcid":"","institution":"National University of Singapore","correspondingAuthor":true,"prefix":"","firstName":"Tan","middleName":"Wei","lastName":"Liang","suffix":""},{"id":545305851,"identity":"a7a9ca4d-6857-4466-89a8-990dff24338e","order_by":1,"name":"Yamamoto Kenji","email":"","orcid":"","institution":"University of Tokyo","correspondingAuthor":false,"prefix":"","firstName":"Yamamoto","middleName":"","lastName":"Kenji","suffix":""},{"id":545305852,"identity":"4d130130-debd-4fe7-b710-0ccb1711d586","order_by":2,"name":"Park Min-Jae","email":"","orcid":"","institution":"Korea Advanced Institute of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Park","middleName":"","lastName":"Min-Jae","suffix":""}],"badges":[],"createdAt":"2025-11-14 21:03:57","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":true,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":true},"doi":"10.21203/rs.3.rs-8118120/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8118120/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96251097,"identity":"29ae87dc-961d-4df4-9cbe-80206ceae7e1","added_by":"auto","created_at":"2025-11-19 07:39:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":320271,"visible":true,"origin":"","legend":"","description":"","filename":"document.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8118120/v1_covered_f90b376e-d3a1-47cb-a04d-0a50546d430b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eIntelligent Resource Orchestration for Fog-Edge Computing in Software-Defined Networks: A Deep Reinforcement Learning Approach\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"National University of Singapore","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":"fog computing, edge computing, intelligent resource orchestration, software-defined networking, deep reinforcement learning, task offloading, quality of service, distributed systems","lastPublishedDoi":"10.21203/rs.3.rs-8118120/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8118120/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFog and edge computing architectures integrated with software-defined networking (SDN) have emerged as transformative paradigms for deploying ultra-low latency applications in distributed systems. This paper introduces an intelligent resource orchestration framework that revolutionizes computational offloading and resource allocation across fog and edge nodes through advanced deep reinforcement learning techniques. By synergizing Lyapunov optimization with deep Q-networks (DQN) and leveraging SDN's programmable control plane, our approach achieves unprecedented reductions in service latency and energy consumption while guaranteeing strict quality of service (QoS) requirements. The framework employs a novel hybrid optimization model enhanced with deep learning approximations for exceptional scalability in large-scale fog-edge networks. Comprehensive simulations on heterogeneous edge-cloud topologies demonstrate that our method dramatically outperforms state-of-the-art approaches, achieving groundbreaking improvements of up to 68% in latency reduction and 52% in energy efficiency across diverse workload scenarios, establishing new benchmarks for intelligent resource management in distributed computing environments.\u003c/p\u003e","manuscriptTitle":"Intelligent Resource Orchestration for Fog-Edge Computing in Software-Defined Networks: A Deep Reinforcement Learning Approach","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-18 03:50:51","doi":"10.21203/rs.3.rs-8118120/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":"ef8771d8-fe66-446c-b635-a280a8397a86","owner":[],"postedDate":"November 18th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58019982,"name":"Computer Architecture and Engineering"},{"id":58019983,"name":"Theoretical Computer Science"},{"id":58019984,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-11-18T03:50:51+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-18 03:50:51","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8118120","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8118120","identity":"rs-8118120","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}