MoSAIC-PPO: Mobility-aware Service Allocation with Integrated Constraints using Proximal Policy Optimization for Vehicular Edge Computing

MoSAIC-PPO: Mobility-aware Service Allocation with Integrated Constraints using Proximal Policy Optimization for Vehicular Edge Computing | 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 MoSAIC-PPO: Mobility-aware Service Allocation with Integrated Constraints using Proximal Policy Optimization for Vehicular Edge Computing Surayya. A., Md Muzakkir Hussain This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8799236/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 Vehicular Edge Computing (VEC) enables latency critical vehicular applications by offloading computation from vehicles to nearby edge service providers (ESPs). However, high vehicle mobility, bursty service demand, limited edge resources, and inter-service dependencies make static or re active orchestration strategies ineffective. This paper presents MoSAIC-PPO, a hybrid orchestration framework that jointly optimizes microservice placement, replica scaling, and migration in dynamic VEC environments. MoSAIC-PPO integrates domain specific heuristics with Proximal Policy Optimization (PPO) to balance short-term responsiveness and long-term performance optimization. The heuristic layer incorporates EWMA-based de mand forecasting, safety-stock replica provisioning, dependency aware service placement, and hysteresis-controlled migration to ensure feasibility and stability under fluctuating workloads. The PPO agent refines orchestration decisions over time by optimizing a multi-objective reward function that captures end to-end service latency, migration overhead, cloud offloading ratio, edge resource utilization, and inter-service dependency delay. The framework is evaluated using realistic SUMO-generated vehicular mobility traces from Luxembourg city. Extensive trace driven experiments demonstrate that MoSAIC-PPO consistently outperforms Random, Greedy, heuristics, and DRL baselines in terms of average and P95 latency, SLA violations, cloud offloading, and edge resource utilization across varying ESP densities and vehicular loads. Computer Architecture and Engineering Computational Mathematics Intelligent transportation system Vehicular Edge Computing Microservice Placement Reinforcement Learning Proximal Policy Optimization Service chaining 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-8799236","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":586481903,"identity":"1d272a12-720e-429b-ae90-30a026ae5c76","order_by":0,"name":"Surayya. A.","email":"","orcid":"","institution":"SRM University, AP","correspondingAuthor":false,"prefix":"","firstName":"Surayya.","middleName":"","lastName":"A.","suffix":""},{"id":586481904,"identity":"4563339a-8a26-4ff4-8d9c-64f5c1f8c246","order_by":1,"name":"Md Muzakkir Hussain","email":"data:image/png;base64,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","orcid":"https://orcid.org/0000-0002-6371-2545","institution":"SRM University, AP","correspondingAuthor":true,"prefix":"","firstName":"Md","middleName":"Muzakkir","lastName":"Hussain","suffix":""}],"badges":[],"createdAt":"2026-02-05 16:13:35","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-8799236/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8799236/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102295496,"identity":"eb9e914a-81b2-41de-97c9-b2fe21e2a575","added_by":"auto","created_at":"2026-02-10 10:11:46","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":6664681,"visible":true,"origin":"","legend":"","description":"","filename":"MoSAICTITS.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8799236/v1_covered_5dbea203-6b19-4210-ace4-9bfe11bd511e.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eMoSAIC-PPO: Mobility-aware Service Allocation with Integrated Constraints using Proximal Policy Optimization for Vehicular Edge Computing\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"SRM University, Ap, India","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":"Intelligent transportation system, Vehicular Edge Computing, Microservice Placement, Reinforcement Learning, Proximal Policy Optimization, Service chaining","lastPublishedDoi":"10.21203/rs.3.rs-8799236/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8799236/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eVehicular Edge Computing (VEC) enables latency critical vehicular applications by offloading computation from vehicles to nearby edge service providers (ESPs). However, high vehicle mobility, bursty service demand, limited edge resources, and inter-service dependencies make static or re active orchestration strategies ineffective. This paper presents MoSAIC-PPO, a hybrid orchestration framework that jointly optimizes microservice placement, replica scaling, and migration in dynamic VEC environments. MoSAIC-PPO integrates domain specific heuristics with Proximal Policy Optimization (PPO) to balance short-term responsiveness and long-term performance optimization. The heuristic layer incorporates EWMA-based de mand forecasting, safety-stock replica provisioning, dependency aware service placement, and hysteresis-controlled migration to ensure feasibility and stability under fluctuating workloads. The PPO agent refines orchestration decisions over time by optimizing a multi-objective reward function that captures end to-end service latency, migration overhead, cloud offloading ratio, edge resource utilization, and inter-service dependency delay. The framework is evaluated using realistic SUMO-generated vehicular mobility traces from Luxembourg city. Extensive trace driven experiments demonstrate that MoSAIC-PPO consistently outperforms Random, Greedy, heuristics, and DRL baselines in terms of average and P95 latency, SLA violations, cloud offloading, and edge resource utilization across varying ESP densities and vehicular loads.\u003c/p\u003e","manuscriptTitle":"MoSAIC-PPO: Mobility-aware Service Allocation with Integrated Constraints using Proximal Policy Optimization for Vehicular Edge Computing","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-06 08:58:38","doi":"10.21203/rs.3.rs-8799236/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":"6899bf55-ada7-4976-9aee-2c948943986c","owner":[],"postedDate":"February 6th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":62438930,"name":"Computer Architecture and Engineering"},{"id":62438931,"name":"Computational Mathematics"}],"tags":[],"updatedAt":"2026-02-06T08:58:38+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-06 08:58:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8799236","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8799236","identity":"rs-8799236","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}