Enhancing Federated Learning Performance under Poor Network Conditions through a Modified UDP Protocol in the NS-3

Enhancing Federated Learning Performance under Poor Network Conditions through a Modified UDP Protocol in the NS-3 | 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 Enhancing Federated Learning Performance under Poor Network Conditions through a Modified UDP Protocol in the NS-3 Bright K Mahembe, Omowunmi Isafiade, Clement N Nyirenda This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8252530/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 Federated Learning (FL) enables decentralized machine learn ing while preserving data privacy, but its performance can degrade under poor network conditions. This study integrates the NS-3 network simula tor with TensorFlow to create a realistic environment for evaluating FL applications. A modified User Datagram Protocol (UDP) is proposed to improve efficiency and reliability in adverse network conditions. The NS 3-based FL simulator is implemented and evaluated using the CIFAR-10 dataset. Results show that the modified UDP maintains 78% accuracy under poor network conditions, a marginal 2% reduction from ideal con ditions due to enhanced packet retrieval mechanisms. In contrast, stan dard UDP experiences a severe drop to 10% accuracy, representing a 69% decline. Future work will focus on scalability, including higher er ror rates, larger node counts, extended training rounds, and evaluation across different NS-3 device types and datasets. Artificial Intelligence and Machine Learning Systems and Networking Federated Learning Deep Learning Networking Protocols User Datagram Protocol Transmission Control Protocol Classification 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-8252530","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":553566126,"identity":"b9fb77b8-bca6-4c3e-a10e-970a34777714","order_by":0,"name":"Bright K Mahembe","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYBACCQYGA4bEBgYeIIvxAVCAh48ELczMBiAtbERpYWwAsZjZJEAiBLVIzkje/OHhjnsy8tH9xyq/5tjJsDEwP3x0A48WaYm0AoPEM8U8hncOs92W3ZYMdBibsXEOHi1yEjkGCYltCTyGM5LZbktuYwZq4WGTJqTlAExLseS2esJapCVyDBtAWuQlktkYP247TFiLZM+zYobEMwk8BhLJxtKM247zsDET8IvE8eTNH3/uSLCXn5H48OPPbdX2/OzNDx/j0wIHBgcYGJh5QCxmYpSDgHwDAwPjD2JVj4JRMApGwYgCAOmRQl9tI/rLAAAAAElFTkSuQmCC","orcid":"","institution":"University of the Western Cape","correspondingAuthor":true,"prefix":"","firstName":"Bright","middleName":"K","lastName":"Mahembe","suffix":""},{"id":553566129,"identity":"b5b62fbd-cfc3-45fa-bb60-cd865094bbfe","order_by":1,"name":"Omowunmi Isafiade","email":"","orcid":"","institution":"University of the Western Cape","correspondingAuthor":false,"prefix":"","firstName":"Omowunmi","middleName":"","lastName":"Isafiade","suffix":""},{"id":553566130,"identity":"32a583d8-800e-4d1f-8f13-56732ef811cf","order_by":2,"name":"Clement N Nyirenda","email":"","orcid":"","institution":"University of the Western Cape","correspondingAuthor":false,"prefix":"","firstName":"Clement","middleName":"N","lastName":"Nyirenda","suffix":""}],"badges":[],"createdAt":"2025-12-01 16:32:31","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-8252530/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8252530/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97367375,"identity":"ba36b04f-a71f-418f-a655-9a82631ea752","added_by":"auto","created_at":"2025-12-03 16:18:19","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":302812,"visible":true,"origin":"","legend":"","description":"","filename":"ICTCS20251.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8252530/v1_covered_d0c8623d-1f9e-4fcf-b748-f20e313d7fef.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEnhancing Federated Learning Performance under Poor Network Conditions through a Modified UDP Protocol in the NS-3\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"University of the Western Cape","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":" Federated Learning, Deep Learning, Networking Protocols, User Datagram Protocol, Transmission Control Protocol, Classification","lastPublishedDoi":"10.21203/rs.3.rs-8252530/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8252530/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eFederated Learning (FL) enables decentralized machine learn ing while preserving data privacy, but its performance can degrade under \u0026nbsp;poor network conditions. This study integrates the NS-3 network simula tor with TensorFlow to create a realistic environment for evaluating FL \u0026nbsp;applications. A modified User Datagram Protocol (UDP) is proposed to \u0026nbsp;improve efficiency and reliability in adverse network conditions. The NS 3-based FL simulator is implemented and evaluated using the CIFAR-10 \u0026nbsp;dataset. Results show that the modified UDP maintains 78% accuracy \u0026nbsp;under poor network conditions, a marginal 2% reduction from ideal con ditions due to enhanced packet retrieval mechanisms. In contrast, stan dard UDP experiences a severe drop to 10% accuracy, representing a \u0026nbsp;69% decline. Future work will focus on scalability, including higher er ror rates, larger node counts, extended training rounds, and evaluation \u0026nbsp;across different NS-3 device types and datasets.\u003c/p\u003e","manuscriptTitle":"Enhancing Federated Learning Performance under Poor Network Conditions through a Modified UDP Protocol in the NS-3","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-02 14:27:31","doi":"10.21203/rs.3.rs-8252530/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":"c1857348-e8b5-4219-885c-ac21a3a3f7fd","owner":[],"postedDate":"December 2nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":58905312,"name":"Artificial Intelligence and Machine Learning"},{"id":58905313,"name":"Systems and Networking"}],"tags":[],"updatedAt":"2025-12-02T14:27:31+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-02 14:27:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8252530","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8252530","identity":"rs-8252530","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}