An Energy-efficient Task Offloading Model based on Trust Mechanism and Multi-agent Reinforcement Learning

An Energy-efficient Task Offloading Model based on Trust Mechanism and Multi-agent 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 An Energy-efficient Task Offloading Model based on Trust Mechanism and Multi-agent Reinforcement Learning Shang Fengjun, Jia Guo This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4505335/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 A task offloading model based on deep reinforcement learning and user experience degree is proposed. Firstly, after users generate blockchain tasks, Proof of Work (PoW) consensus mechanism is introduced to pack the transaction information into blocks to ensure the real reliability of the interaction information in the system. Then, the user experience degree is defined by introducing the total system consumption delay and user gain, and the goal of optimal user experience degree is constructed. Furthermore, the deep reinforcement learning algorithm is used to optimize the offloading model, and the deep reinforcement learning model is constructed by taking the size of the transaction data and the difficulty of the PoW consensus process as the network state, the task offloading and resource allocation relationship between the user and the edge server as the network action, and the user experience as the network reward. Finally, the gradient descent method and back propagation algorithm are used to train the depth network until convergence, and the optimal offloading and resource allocation decision is obtained, and the superiority of the offloading model and algorithm proposed in this thesis is verified by simulation. Edge Computing Task Offloading Deep Reinforcement Learning User Experience Trust Mechanism 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-4505335","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":309295505,"identity":"3e64901a-8e5b-4dd6-b2cd-c4e464c315e1","order_by":0,"name":"Shang Fengjun","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5ElEQVRIiWNgGAWjYDACCRBhwyYH4zM2EKcljc0YzDlAghaGxAaitcjPbn728EsCX3p/e47Z4w8MNrIbDjA/e4BPi8GdY+bGMglsuTPOvDE3OMCQZrzhAJu5AV4tEglm0pI/2HI3SOSYSRxgOJy44QAPmwReh81I/yYtkcCWbgDR8p+wFoYbOWaSHxLYEqBaDhDWYnAjp0yaIYHNcMaZZ+UGZwySjWceZjMj5LBtkj8Sjsnztydve1BRYSfbd7z5GX6HAQEzD8MxIJXABrQUxCWkHggYfzDUQLWMglEwCkbBKMACAL0aSJkCcGaSAAAAAElFTkSuQmCC","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":true,"prefix":"","firstName":"Shang","middleName":"","lastName":"Fengjun","suffix":""},{"id":309295506,"identity":"f17f91c1-0c3f-4600-a981-52deb8a3fb6f","order_by":1,"name":"Jia Guo","email":"","orcid":"","institution":"Chongqing University of Posts and Telecommunications","correspondingAuthor":false,"prefix":"","firstName":"Jia","middleName":"","lastName":"Guo","suffix":""}],"badges":[],"createdAt":"2024-05-30 23:23:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4505335/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4505335/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":68895404,"identity":"4b77af6d-3c67-496e-9114-d3db1c6a488c","added_by":"auto","created_at":"2024-11-13 08:32:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":513890,"visible":true,"origin":"","legend":"","description":"","filename":"Ziliao2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4505335/v1_covered_e2b18743-6c62-4bd2-96b8-d2be036bdabb.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Energy-efficient Task Offloading Model based on Trust Mechanism and Multi-agent Reinforcement Learning","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":"Edge Computing, Task Offloading, Deep Reinforcement Learning, User Experience, Trust Mechanism","lastPublishedDoi":"10.21203/rs.3.rs-4505335/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4505335/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eA task offloading model based on deep reinforcement learning and user experience degree is proposed. Firstly, after users generate blockchain tasks, Proof of Work (PoW) consensus mechanism is introduced to pack the transaction information into blocks to ensure the real reliability of the interaction information in the system. Then, the user experience degree is defined by introducing the total system consumption delay and user gain, and the goal of optimal user experience degree is constructed. Furthermore, the deep reinforcement learning algorithm is used to optimize the offloading model, and the deep reinforcement learning model is constructed by taking the size of the transaction data and the difficulty of the PoW consensus process as the network state, the task offloading and resource allocation relationship between the user and the edge server as the network action, and the user experience as the network reward. Finally, the gradient descent method and back propagation algorithm are used to train the depth network until convergence, and the optimal offloading and resource allocation decision is obtained, and the superiority of the offloading model and algorithm proposed in this thesis is verified by simulation.\u003c/p\u003e","manuscriptTitle":"An Energy-efficient Task Offloading Model based on Trust Mechanism and Multi-agent Reinforcement Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-06-13 14:34:38","doi":"10.21203/rs.3.rs-4505335/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":"c32e01c7-e51b-42fc-86a8-b4b4c179b784","owner":[],"postedDate":"June 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-11-13T08:24:08+00:00","versionOfRecord":[],"versionCreatedAt":"2024-06-13 14:34:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4505335","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4505335","identity":"rs-4505335","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}