Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Domain Generalization

Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Domain Generalization | 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 Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Domain Generalization Andrea Rossi, Andrea Visentin, Diego Carraro, Steven Prestwich, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4934203/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 11 You are reading this latest preprint version Abstract Predicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing the provisioning cost. Modelling prediction uncertainty is also desirable to better inform the resource decision-making process, but research in this field is under-investigated. In this paper, we propose univariate and bivariate Bayesian deep learning models that provide predictions of future workload demand and its uncertainty. We run extensive experiments on Google and Alibaba clusters, where we first train our models with datasets from different cloud providers and compare them with LSTM-based baselines. Results show that modelling the uncertainty of predictions has a positive impact on performance, especially on service level metrics, because uncertainty quantification can be tailored to desired target service levels that are critical in cloud applications. Moreover, we investigate whether our models benefit transfer learning capabilities across different domains, i.e.\dataset distributions. Experiments on the same workload datasets reveal that acceptable transfer learning performance can be achieved within the same provider (because distributions are more similar). Also, domain knowledge does not transfer when the source and target domains are very different (e.g.\from different providers), but this performance degradation can be mitigated by increasing the training set size of the source domain. Bayesian Neural Networks Cloud Computing Workload Prediction Uncertainty Deep Learning Transfer Learning Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 22 Oct, 2024 Reviews received at journal 31 Aug, 2024 Reviews received at journal 30 Aug, 2024 Reviews received at journal 28 Aug, 2024 Reviewers agreed at journal 24 Aug, 2024 Reviewers agreed at journal 23 Aug, 2024 Reviewers agreed at journal 22 Aug, 2024 Reviewers invited by journal 22 Aug, 2024 Editor assigned by journal 20 Aug, 2024 Submission checks completed at journal 19 Aug, 2024 First submitted to journal 18 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-4934203","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":347831034,"identity":"ad3624ac-1fdc-4e23-ad25-140ad4990408","order_by":0,"name":"Andrea Rossi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYPACCTkYi4doLcYka2FIbCBaKX8D78OHP/5YpPf3H2CT+FHDIMNP0EUH2I2NedskcmfcSGCT7DnGwCNJ0L4DbGzSjA0SuRskGEAMBh6DAwR0yAO1SP74I5FuwH8AosWekBYDoBYJHjaJBAOGBKgthNxleJiNGeQXwxk3Epste45J8EgQskXueBsjMMTq5Pn7Dx+88aPGxp6/gZA1zHAWI0itBCH1o2AUjIJRMAqIAQAKMy+lFnxUNwAAAABJRU5ErkJggg==","orcid":"","institution":"University College Cork","correspondingAuthor":true,"prefix":"","firstName":"Andrea","middleName":"","lastName":"Rossi","suffix":""},{"id":347831038,"identity":"d5918fd3-f595-4fea-9cf8-b3610792dff2","order_by":1,"name":"Andrea Visentin","email":"","orcid":"","institution":"University College Cork","correspondingAuthor":false,"prefix":"","firstName":"Andrea","middleName":"","lastName":"Visentin","suffix":""},{"id":347831039,"identity":"9c04db1b-aae9-4699-9ded-80bd909e4b00","order_by":2,"name":"Diego Carraro","email":"","orcid":"","institution":"University College Cork","correspondingAuthor":false,"prefix":"","firstName":"Diego","middleName":"","lastName":"Carraro","suffix":""},{"id":347831041,"identity":"1a1507da-f4a0-4133-a563-13febc529cea","order_by":3,"name":"Steven Prestwich","email":"","orcid":"","institution":"University College Cork","correspondingAuthor":false,"prefix":"","firstName":"Steven","middleName":"","lastName":"Prestwich","suffix":""},{"id":347831042,"identity":"d5b574f7-9a7e-4694-82c7-b06b5dca4d7d","order_by":4,"name":"Kenneth N. Brown","email":"","orcid":"","institution":"University College Cork","correspondingAuthor":false,"prefix":"","firstName":"Kenneth","middleName":"N.","lastName":"Brown","suffix":""}],"badges":[],"createdAt":"2024-08-18 16:25:00","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4934203/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4934203/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":64581623,"identity":"46ae5243-b6ab-491c-ac99-ee9218881271","added_by":"auto","created_at":"2024-09-16 06:32:14","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":644675,"visible":true,"origin":"","legend":"","description":"","filename":"mtmnnbqbcqtbrzkwbbnqdqxrhkwssscn.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4934203/v1_covered_a6ca7b81-b7d7-45b3-89b8-785b5f1fbf07.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Domain Generalization","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":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Bayesian Neural Networks, Cloud Computing, Workload Prediction, Uncertainty, Deep Learning, Transfer Learning","lastPublishedDoi":"10.21203/rs.3.rs-4934203/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4934203/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePredicting future resource demand in Cloud Computing is essential for optimizing the trade-off between serving customers' requests efficiently and minimizing the provisioning cost. Modelling prediction uncertainty is also desirable to better inform the resource decision-making process, but research in this field is under-investigated. In this paper, we propose univariate and bivariate Bayesian deep learning models that provide predictions of future workload demand and its uncertainty. We run extensive experiments on Google and Alibaba clusters, where we first train our models with datasets from different cloud providers and compare them with LSTM-based baselines. Results show that modelling the uncertainty of predictions has a positive impact on performance, especially on service level metrics, because uncertainty quantification can be tailored to desired target service levels that are critical in cloud applications. Moreover, we investigate whether our models benefit transfer learning capabilities across different domains, i.e.\\dataset distributions. Experiments on the same workload datasets reveal that acceptable transfer learning performance can be achieved within the same provider (because distributions are more similar). Also, domain knowledge does not transfer when the source and target domains are very different (e.g.\\from different providers), but this performance degradation can be mitigated by increasing the training set size of the source domain.\u003c/p\u003e","manuscriptTitle":"Forecasting Workload in Cloud Computing: Towards Uncertainty-Aware Predictions and Domain Generalization","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-09-16 06:24:07","doi":"10.21203/rs.3.rs-4934203/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-10-22T23:26:29+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-09-01T02:35:01+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-30T06:20:18+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-08-29T03:02:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"304036598568913576996145655783066129663","date":"2024-08-24T12:33:12+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"311161738035114479202166666937853533420","date":"2024-08-23T14:10:31+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"321458308959952455596782029751782657222","date":"2024-08-22T14:26:47+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-08-22T11:53:03+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-08-20T06:05:30+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-08-19T13:05:14+00:00","index":"","fulltext":""},{"type":"submitted","content":"Cluster Computing","date":"2024-08-18T16:23:45+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"cluster-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [Cluster Computing](https://www.springer.com/journal/10586)","snPcode":"10586","submissionUrl":"https://submission.nature.com/new-submission/10586/3","title":"Cluster Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"d86f6fbf-307f-4beb-9e1b-133f0b20e3e0","owner":[],"postedDate":"September 16th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-11-17T21:08:04+00:00","versionOfRecord":[],"versionCreatedAt":"2024-09-16 06:24:07","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4934203","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4934203","identity":"rs-4934203","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}