Deep reinforcement learning for the management of the wall regeneration cycle in wall-bounded turbulent flows

Deep reinforcement learning for the management of the wall regeneration cycle in wall-bounded turbulent flows | 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 Deep reinforcement learning for the management of the wall regeneration cycle in wall-bounded turbulent flows Giorgio Maria Cavallazzi, Luca Guastoni, Ricardo Vinuesa, Alfredo Pinelli This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4901523/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 15 Nov, 2024 Read the published version in Flow, Turbulence and Combustion → Version 1 posted 9 You are reading this latest preprint version Abstract The wall cycle in wall-bounded turbulent flows is a complex turbulence regeneration mechanism that remains not fully understood. This study explores the potential of deep reinforcement learning (DRL) for managing the wall regeneration cycle to achieve desired flow dynamics. We integrate the StableBaselines3 DRL libraries with the open-source DNS solver CaNS to create a robust platform for dynamic flow control. The DRL agent interacts with the DNS environment, learning policies that modify wall boundary conditions to optimize objectives such as the reduction of the skin-friction coefficient or the enhancement of certain coherent structures features. Initial experiments demonstrate the capability of DRL to achieve drag-reduction rates comparable with those achieved via traditional methods, though limited to short time periods. We also propose a strategy to enhance the coherence of velocity streaks, assuming that maintaining straight streaks can inhibit instability and further reduce skin friction. The implementation makes use of the message-passing-interface (MPI) wrappers for efficient communication between the Python-based DRL agent and the DNS solver, ensuring scalability on high-performance computing architectures. Our results highlight the promise of DRL in flow control applications and underscore the need for more advanced control laws and objective functions. Future work will focus on optimizing actuation periods and exploring new computational architectures to extend the applicability and the efficiency of DRL in turbulent flow management. flow control drag reduction Direct Numerical Simulation Deep Reinforcement Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 15 Nov, 2024 Read the published version in Flow, Turbulence and Combustion → Version 1 posted Editorial decision: Revision requested 15 Sep, 2024 Reviews received at journal 15 Sep, 2024 Reviews received at journal 12 Sep, 2024 Reviewers agreed at journal 06 Sep, 2024 Reviewers agreed at journal 19 Aug, 2024 Reviewers invited by journal 19 Aug, 2024 Editor assigned by journal 14 Aug, 2024 Submission checks completed at journal 13 Aug, 2024 First submitted to journal 12 Aug, 2024 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-4901523","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":350508227,"identity":"3413131c-61f3-4775-b3ea-47cffac8565a","order_by":0,"name":"Giorgio Maria Cavallazzi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABJ0lEQVRIie2RMUvEMBTHUx5kytE1BWm+QkoXxeKNfo13FOricKMgnEKHW4RbBb+EIDhXAr2lH6Budwg3t+DQwcGXcouaq6tgf0NI/smPl8djbGTkLwJ20fvDZm4TKBjuA+/2NwXtBjgyxAHlC73CBK0DijqHsn2fJ8xfVlGD+myqlqJttp2hpODB/U8lMjx9ONIZk9VlLFGn4OWTJ4loKEEePDqUXMQgtaF2MiQFOMDkmVmF1YwHmyHF36Ud6hvBQex6RR1QFIjYa6wi05KqGClA8F7RVnF8jH6SAtOZkPVbeYx6rSVwaiq7EFE1y08c7auVMV73kYT+apbXzdX1lJJt2yWnYbg2L693jioFzU7QLL5f5OLQIBWlXue4WLhej4yMjPxPPgH2DVpL3su9ZgAAAABJRU5ErkJggg==","orcid":"","institution":"City, University of London","correspondingAuthor":true,"prefix":"","firstName":"Giorgio","middleName":"Maria","lastName":"Cavallazzi","suffix":""},{"id":350508228,"identity":"ebb520d9-8ba4-44f7-9482-8ab512535fdc","order_by":1,"name":"Luca Guastoni","email":"","orcid":"","institution":"Technical University of Munich","correspondingAuthor":false,"prefix":"","firstName":"Luca","middleName":"","lastName":"Guastoni","suffix":""},{"id":350508229,"identity":"2b5e2edb-4c9a-4a06-b73d-dd6a34d87f11","order_by":2,"name":"Ricardo Vinuesa","email":"","orcid":"","institution":"KTH Royal Institute of Technology","correspondingAuthor":false,"prefix":"","firstName":"Ricardo","middleName":"","lastName":"Vinuesa","suffix":""},{"id":350508230,"identity":"a7bf19d1-736f-4c6d-9d0e-e1bb54339475","order_by":3,"name":"Alfredo Pinelli","email":"","orcid":"","institution":"City, University of London","correspondingAuthor":false,"prefix":"","firstName":"Alfredo","middleName":"","lastName":"Pinelli","suffix":""}],"badges":[],"createdAt":"2024-08-12 15:10:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4901523/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4901523/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s10494-024-00609-4","type":"published","date":"2024-11-15T15:57:52+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":69286189,"identity":"53b5a940-0d45-449b-b9e7-bf6e379c39b2","added_by":"auto","created_at":"2024-11-18 19:30:18","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":785911,"visible":true,"origin":"","legend":"","description":"","filename":"FTaCsubCavallazzi2.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4901523/v1_covered_0a9ddbef-2d9e-48ee-ba44-5e9dd976241c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Deep reinforcement learning for the management of the wall regeneration cycle in wall-bounded turbulent flows","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"flow-turbulence-and-combustion","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"appl","sideBox":"Learn more about [Flow, Turbulence and Combustion](http://link.springer.com/journal/10494)","snPcode":"10494","submissionUrl":"https://submission.nature.com/new-submission/10494/3","title":"Flow, Turbulence and Combustion","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"flow control, drag reduction, Direct Numerical Simulation, Deep Reinforcement Learning","lastPublishedDoi":"10.21203/rs.3.rs-4901523/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4901523/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The wall cycle in wall-bounded turbulent flows is a complex turbulence regeneration mechanism that remains not fully understood. This study explores the potential of deep reinforcement learning (DRL) for managing the wall regeneration cycle to achieve desired flow dynamics. We integrate the StableBaselines3 DRL libraries with the open-source DNS solver CaNS to create a robust platform for dynamic flow control. The DRL agent interacts with the DNS environment, learning policies that modify wall boundary conditions to optimize objectives such as the reduction of the skin-friction coefficient or the enhancement of certain coherent structures features. Initial experiments demonstrate the capability of DRL to achieve drag-reduction rates comparable with those achieved via traditional methods, though limited to short time periods. We also propose a strategy to enhance the coherence of velocity streaks, assuming that maintaining straight streaks can inhibit instability and further reduce skin friction. The implementation makes use of the message-passing-interface (MPI) wrappers for efficient communication between the Python-based DRL agent and the DNS solver, ensuring scalability on high-performance computing architectures. Our results highlight the promise of DRL in flow control applications and underscore the need for more advanced control laws and objective functions. Future work will focus on optimizing actuation periods and exploring new computational architectures to extend the applicability and the efficiency of DRL in turbulent flow management.","manuscriptTitle":"Deep reinforcement learning for the management of the wall regeneration cycle in wall-bounded turbulent flows","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-09 19:25:03","doi":"10.21203/rs.3.rs-4901523/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-09-15T20:51:28+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-15T14:43:46+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-12T14:04:08+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"234632895147216788720851879007969538158","date":"2024-09-06T11:42:06+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"224468139664485485106004745892742456602","date":"2024-08-19T09:05:02+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-19T08:47:46+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-14T08:28:46+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-13T04:34:02+00:00","index":"","fulltext":""},{"type":"submitted","content":"Flow, Turbulence and Combustion","date":"2024-08-12T15:09:01+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"flow-turbulence-and-combustion","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"appl","sideBox":"Learn more about [Flow, Turbulence and Combustion](http://link.springer.com/journal/10494)","snPcode":"10494","submissionUrl":"https://submission.nature.com/new-submission/10494/3","title":"Flow, Turbulence and Combustion","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"45f45981-f5a4-4e83-bed5-63dcd1c584cc","owner":[],"postedDate":"September 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"published-in-journal","subjectAreas":[],"tags":[],"updatedAt":"2024-11-18T19:27:43+00:00","versionOfRecord":{"articleIdentity":"rs-4901523","link":"https://doi.org/10.1007/s10494-024-00609-4","journal":{"identity":"flow-turbulence-and-combustion","isVorOnly":false,"title":"Flow, Turbulence and Combustion"},"publishedOn":"2024-11-15 15:57:52","publishedOnDateReadable":"November 15th, 2024"},"versionCreatedAt":"2024-09-09 19:25:03","video":"","vorDoi":"10.1007/s10494-024-00609-4","vorDoiUrl":"https://doi.org/10.1007/s10494-024-00609-4","workflowStages":[]},"version":"v1","identity":"rs-4901523","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4901523","identity":"rs-4901523","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}