Comparative Analysis of Hybrid ML Models for Solar Power Forecasting in Bangladesh

Comparative Analysis of Hybrid ML Models for Solar Power Forecasting in Bangladesh | 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 Comparative Analysis of Hybrid ML Models for Solar Power Forecasting in Bangladesh Mushfiq Us Salehin This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6143766/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 The study deals with the evaluation of the hybrid machine learning model KNN-SVM for forecasting solar power in Bangladesh. Furthermore, the results are compared with that achieved from the individual models: K-Nearest Neighbor, Support Vector Machine, and Long Short-Term Memory. In this regard, the hybrid mode performed better, obtaining the minimum RMSE of 0.0066 both for HTGSR and HTPEG. While LSTM had the edge for sequence prediction, nonlinear patterns were handled by the KNN-SVM hybrid, where instance-based learning is balanced against margin optimization. This hybrid approach fits well with solar energy forecasting for improved energy management and integration of renewable energy into the national grid in Bangladesh for the purpose of sustainable energy planning. Artificial Intelligence and Machine Learning Solar Power Forecasting Machine Learning Models K-Nearest Neighbors (KNN) Support Vector Machine (SVM) Long Short-Term Memory (LSTM) Renewable En- ergy Prediction Climate Variability Root Mean Square Error (RMSE) 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-6143766","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":423188758,"identity":"07c3e948-6cb1-45e0-9a8e-5f53f9f99d5e","order_by":0,"name":"Mushfiq Us Salehin","email":"data:image/png;base64,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","orcid":"","institution":"BRAC University","correspondingAuthor":true,"prefix":"","firstName":"Mushfiq","middleName":"Us","lastName":"Salehin","suffix":""}],"badges":[],"createdAt":"2025-03-03 07:44:08","currentVersionCode":1,"declarations":{"humanSubjects":true,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":true,"humanSubjectConsent":true,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-6143766/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6143766/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":77691840,"identity":"70131af3-abfb-4aaf-9e3e-8b7bf89a8298","added_by":"auto","created_at":"2025-03-04 09:48:32","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1022797,"visible":true,"origin":"","legend":"","description":"","filename":"mechinelearning1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6143766/v1_covered_7617b0a4-dd30-4c84-84be-ce50795d51d0.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eComparative Analysis of Hybrid ML Models for Solar Power Forecasting in Bangladesh\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"BRAC University","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":"Solar Power Forecasting, Machine Learning Models, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Long Short-Term Memory (LSTM), Renewable En- ergy Prediction, Climate Variability, Root Mean Square Error (RMSE)","lastPublishedDoi":"10.21203/rs.3.rs-6143766/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6143766/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe study deals with the evaluation of the hybrid machine learning model KNN-SVM for forecasting solar power in Bangladesh. Furthermore, the results are compared with that achieved from the individual models: K-Nearest Neighbor, Support Vector Machine, and Long Short-Term Memory. In this regard, the hybrid mode performed better, obtaining the minimum RMSE of 0.0066 both for HTGSR and HTPEG. While LSTM had the edge for sequence prediction, nonlinear patterns were handled by the KNN-SVM hybrid, where instance-based learning is balanced against margin optimization. This hybrid approach fits well with solar energy forecasting for improved energy management and integration of renewable energy into the national grid in Bangladesh for the purpose of sustainable energy planning.\u003c/p\u003e","manuscriptTitle":"Comparative Analysis of Hybrid ML Models for Solar Power Forecasting in Bangladesh","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-04 09:16:22","doi":"10.21203/rs.3.rs-6143766/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":"d6f274f7-e1ea-4793-a09d-69ca0d3ad56f","owner":[],"postedDate":"March 4th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":45166241,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-03-04T09:16:22+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-04 09:16:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6143766","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6143766","identity":"rs-6143766","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}