Enhancing Microservices Performance with AI-Based Load Balancing: A Deep Learning Perspective

Enhancing Microservices Performance with AI-Based Load Balancing: A Deep Learning Perspective | 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 Microservices Performance with AI-Based Load Balancing: A Deep Learning Perspective GOPICHAND BANDARUPALLI This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6396660/v3 This work is licensed under a CC BY 4.0 License Status: Posted Version 3 posted You are reading this latest preprint version Show more versions Abstract Microservices architectures have become a cornerstone of modern software engineering, enabling scalability and flexibility in distributed systems. However, efficient load balancing under variable traffic remains a challenge. This study proposes a deep learning-based approach to enhance load balancing in microservices, leveraging Long Short-Term Memory (LSTM) networks to predict traffic patterns and optimize resource distribution. The proposed model is evaluated against traditional load balancing algorithms such as round-robin and least connections, using a unique dataset of synthetic and real-world traffic traces from Kubernetes clusters. Performance metrics, including latency, throughput, and resource utilization, demonstrate the superiority of the AI-driven approach, achieving up to 25% lower latency and 30% higher throughput compared to baselines. Bar graphs, line graphs, and tables illustrate comparative analysis, highlighting the model’s effectiveness in dynamic environments. Artificial Intelligence and Machine Learning Deep Learning Load Balancing LSTM Microservices Performance Optimization Full Text Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 3 posted You are reading this latest preprint version Show more versions 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-6396660","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":452193677,"identity":"e25a4a1d-3683-4643-8dd8-ddc7fc8b0579","order_by":0,"name":"GOPICHAND BANDARUPALLI","email":"data:image/png;base64,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","orcid":"","institution":"campbellsville university","correspondingAuthor":true,"prefix":"","firstName":"GOPICHAND","middleName":"","lastName":"BANDARUPALLI","suffix":""}],"badges":[],"createdAt":"2025-04-07 18:02:29","currentVersionCode":3,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6396660/v3","doiUrl":"https://doi.org/10.21203/rs.3.rs-6396660/v3","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Enhancing Microservices Performance with AI-Based Load Balancing: A Deep Learning Perspective","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Campbellsville University","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"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":"Deep Learning, Load Balancing, LSTM, Microservices, Performance Optimization","lastPublishedDoi":"10.21203/rs.3.rs-6396660/v3","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6396660/v3","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eMicroservices architectures have become a cornerstone of modern software engineering, enabling scalability and flexibility in distributed systems. However, efficient load balancing under variable traffic remains a challenge. This study proposes a deep learning-based approach to enhance load balancing in microservices, leveraging Long Short-Term Memory (LSTM) networks to predict traffic patterns and optimize resource distribution. The proposed model is evaluated against traditional load balancing algorithms such as round-robin and least connections, using a unique dataset of synthetic and real-world traffic traces from Kubernetes clusters. Performance metrics, including latency, throughput, and resource utilization, demonstrate the superiority of the AI-driven approach, achieving up to 25% lower latency and 30% higher throughput compared to baselines. Bar graphs, line graphs, and tables illustrate comparative analysis, highlighting the model\u0026rsquo;s effectiveness in dynamic environments.\u003c/p\u003e","manuscriptTitle":"Enhancing Microservices Performance with AI-Based Load Balancing: A Deep Learning Perspective","msid":"","msnumber":"","nonDraftVersions":[{"code":3,"date":"2025-05-08 14:41:21","doi":"10.21203/rs.3.rs-6396660/v3","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}},{"code":2,"date":"2025-05-05 15:57:40","doi":"10.21203/rs.3.rs-6396660/v2","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}},{"code":1,"date":"2025-04-09 05:43:12","doi":"10.21203/rs.3.rs-6396660/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":"5da960ac-304e-4795-a1a2-b25e467d33c1","owner":[],"postedDate":"May 8th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48090915,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-04-09T05:43:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-08 14:41:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v3","identity":"rs-6396660","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6396660","identity":"rs-6396660","version":["v3"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}