Multi-Device Task Offloading Optimization in Edge Computing Systems with Reinforcement Learning: A Case Study on Video Object Tracking

Multi-Device Task Offloading Optimization in Edge Computing Systems with Reinforcement Learning: A Case Study on Video Object Tracking | 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 Article Multi-Device Task Offloading Optimization in Edge Computing Systems with Reinforcement Learning: A Case Study on Video Object Tracking Shengning Zhang, Yusuf Sambo, Muhammad Ali Imran, Wasim Ahmad This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6700128/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 This paper presents a novel framework for multi-device task offloading optimization in edge computing systems using reinforcement learning, demonstrated through a case study on video object tracking. Distributing computational tasks efficiently between resource-constrained devices and edge servers remains difficult when dealing with heterogeneous client devices. We address this problem by proposing a system in which multiple devices independently optimize their offloading decisions to a shared edge server using device-specific Deep Q-Networks (DQNs). Our framework incorporates comprehensive energy measurement methodologies. For quantifying communication energy consumption using external hardware monitoring and statistical modeling, experiments conducted across three devices with distinct computational profiles to demonstrate substantial improvements in performance. Results show up to 95.94% reduction in client energy consumption and 92.60% reduction in processing latency for resource-constrained devices, with benefits diminishing proportionally to increasing local computational power. This work bridges the gap between theoretical offloading models and practical implementations, providing a case and analysis for developing adaptive edge computing systems capable of operating with heterogeneous devices under realistic conditions. Physical sciences/Engineering/Electrical and electronic engineering Physical sciences/Mathematics and computing/Computer science Physical sciences/Mathematics and computing/Software 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-6700128","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":469499839,"identity":"a17e5724-2e68-4aff-bb6e-081cbfdf9e20","order_by":0,"name":"Shengning Zhang","email":"data:image/png;base64,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","orcid":"","institution":"University of Glasgow","correspondingAuthor":true,"prefix":"","firstName":"Shengning","middleName":"","lastName":"Zhang","suffix":""},{"id":469499840,"identity":"4656746e-cabe-41bf-8bea-2a8f94a8669a","order_by":1,"name":"Yusuf Sambo","email":"","orcid":"","institution":"University of Glasgow","correspondingAuthor":false,"prefix":"","firstName":"Yusuf","middleName":"","lastName":"Sambo","suffix":""},{"id":469499841,"identity":"c10afc11-ca49-4a2f-a4d6-4ff8b784d7f2","order_by":2,"name":"Muhammad Ali Imran","email":"","orcid":"","institution":"University of Glasgow","correspondingAuthor":false,"prefix":"","firstName":"Muhammad","middleName":"Ali","lastName":"Imran","suffix":""},{"id":469499842,"identity":"c6788999-c592-4b19-aaad-6f6e9323c19a","order_by":3,"name":"Wasim Ahmad","email":"","orcid":"","institution":"University of Glasgow","correspondingAuthor":false,"prefix":"","firstName":"Wasim","middleName":"","lastName":"Ahmad","suffix":""}],"badges":[],"createdAt":"2025-05-19 14:53:32","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-6700128/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6700128/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":85787158,"identity":"e9ec11c3-0163-4622-8c6f-48dd6410bcce","added_by":"auto","created_at":"2025-07-01 16:31:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":4904457,"visible":true,"origin":"","legend":"","description":"","filename":"MultiDeviceTaskOffloadingOptimizationinEdgeComputingSystemswithReinforcementLearningACaseStudyonVideoObjectTracking.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6700128/v1_covered_97c38dda-8570-4497-b715-3b5ad0ea1c64.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Multi-Device Task Offloading Optimization in Edge Computing Systems with Reinforcement Learning: A Case Study on Video Object Tracking","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":"","lastPublishedDoi":"10.21203/rs.3.rs-6700128/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6700128/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This paper presents a novel framework for multi-device task offloading optimization in edge computing systems using reinforcement learning, demonstrated through a case study on video object tracking. Distributing computational tasks efficiently between resource-constrained devices and edge servers remains difficult when dealing with heterogeneous client devices. We address this problem by proposing a system in which multiple devices independently optimize their offloading decisions to a shared edge server using device-specific Deep Q-Networks (DQNs). Our framework incorporates comprehensive energy measurement methodologies. For quantifying communication energy consumption using external hardware monitoring and statistical modeling, experiments conducted across three devices with distinct computational profiles to demonstrate substantial improvements in performance. Results show up to 95.94% reduction in client energy consumption and 92.60% reduction in processing latency for resource-constrained devices, with benefits diminishing proportionally to increasing local computational power. This work bridges the gap between theoretical offloading models and practical implementations, providing a case and analysis for developing adaptive edge computing systems capable of operating with heterogeneous devices under realistic conditions.","manuscriptTitle":"Multi-Device Task Offloading Optimization in Edge Computing Systems with Reinforcement Learning: A Case Study on Video Object Tracking","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-06-12 12:39:41","doi":"10.21203/rs.3.rs-6700128/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":"cf027042-f3f3-4472-9f45-b63c0872abf3","owner":[],"postedDate":"June 12th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":49849823,"name":"Physical sciences/Engineering/Electrical and electronic engineering"},{"id":49849824,"name":"Physical sciences/Mathematics and computing/Computer science"},{"id":49849825,"name":"Physical sciences/Mathematics and computing/Software"}],"tags":[],"updatedAt":"2025-07-01T16:23:11+00:00","versionOfRecord":[],"versionCreatedAt":"2025-06-12 12:39:41","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6700128","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6700128","identity":"rs-6700128","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}