Proposing A Robust Deep Learning Framework for Short-Term Solar Power Forecasting Using Sky Images

Proposing A Robust Deep Learning Framework for Short-Term Solar Power Forecasting Using Sky Images | 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 Proposing A Robust Deep Learning Framework for Short-Term Solar Power Forecasting Using Sky Images Shahinur Rahman, Md. Ali Akber, Md. Aminul Islam, Sharif Miah, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9619678/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 Intermittent solar energy must be correctly predicted on short-term time scales to maintain the stability and efficiency of the power grid it interacts with. This work presents a deep learning framework that is effective in predicting solar irradiance, a direct proxy for energy generation from the input data, which consists of time-ordered sky images. We establish an end-to-end pipeline to process and synchronize high-resolution sky image data from a fisheye camera with colocated direct normal irradiance measurements from pyranometers. The essential part of our model is a Convolutional Neural Network (CNN) that extracts important spatiotemporal identifiers from the images and translates them into predicted values for future irradiance. Our model shows a significant predictive power trained and assessed on a real-world dataset, specifically showing a Sunny Days Mean Absolute Error (MAE) of 0.353, a Root Mean Squared Error (RMSE) of 0.463, a Cloudy Days Mean Absolute Error (MAE) of 0.964, and a Root Mean Squared Error (RMSE) of 2.029, noticed within the held-out test set. The amount of variance in irradiance explained by the model based on visual sky conditions also represents a large jump from baseline, suggesting that this model captures almost 50% of variability in irradiance. Model stability and generalizability are confirmed by the evaluation of training progress. The proposed work lays the groundwork for a highly effective and reproducible deep learning framework for short-term solar forecasting, which serves as a robust paradigm suitable for future incorporation into smart grid management systems to improve solar power generation reliability. Deep learning Solar irradiance forecasting Solar power forecasting Short-Term Forecasting Renewable energy integration 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-9619678","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":635673408,"identity":"2609df30-57f5-46b6-a268-4a13e10a51d0","order_by":0,"name":"Shahinur Rahman","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABKklEQVRIiWNgGAWjYDACCQY2hgQgzcbA3MDAcAAsxvgASPDwEdbCCNfCbADSwoZPCwQgtLBJgEkcOuRnNz978HDH4Xw+/oONn26csUmc3977rPJrjp0M0KkPH93A1GJw55i5QeKZw5ZtEonN0jk30hI3nDludlt2WzLQYWzGxjlYtEgkmEkkth02YJNgbJDO+XA4d4NEGtttyW3MQC08bNJYtMjPSP8G0cJ/sPk3SMv8+c/YiiW31ePUwnAjB2oLQ2Ib0GGHcxtusLExftx2GKcWgxs5ZUAt6UCHJbZZ55xJq99wJo1ZmnHbcR42Zux+ATpsm+TPNmsD+f7Dh2/nHLMxlm8/xvjx57Zqe3725oePsTkMK2DmAZPEKgcBxh+kqB4Fo2AUjILhDgB04WSJWOPc0AAAAABJRU5ErkJggg==","orcid":"","institution":"City University","correspondingAuthor":true,"prefix":"","firstName":"Shahinur","middleName":"","lastName":"Rahman","suffix":""},{"id":635673409,"identity":"4a5eecef-edb4-4c09-8746-bf05d3e69a89","order_by":1,"name":"Md. Ali Akber","email":"","orcid":"","institution":"City University","correspondingAuthor":false,"prefix":"","firstName":"Md.","middleName":"Ali","lastName":"Akber","suffix":""},{"id":635673410,"identity":"82427086-0a11-459a-8d0d-2dfd17c9c694","order_by":2,"name":"Md. Aminul Islam","email":"","orcid":"","institution":"City University","correspondingAuthor":false,"prefix":"","firstName":"Md.","middleName":"Aminul","lastName":"Islam","suffix":""},{"id":635673411,"identity":"d9cccdf9-fa73-4f8e-b835-eff2a2e52828","order_by":3,"name":"Sharif Miah","email":"","orcid":"","institution":"City University","correspondingAuthor":false,"prefix":"","firstName":"Sharif","middleName":"","lastName":"Miah","suffix":""},{"id":635673412,"identity":"87683cde-d393-4a24-9d33-86d7e3ff7ee2","order_by":4,"name":"Md. Sadikul Islam","email":"","orcid":"","institution":"City University","correspondingAuthor":false,"prefix":"","firstName":"Md.","middleName":"Sadikul","lastName":"Islam","suffix":""}],"badges":[],"createdAt":"2026-05-05 14:10:12","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-9619678/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9619678/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108747060,"identity":"1bba8fa9-91ac-4fd5-8a6c-2bf6a7276903","added_by":"auto","created_at":"2026-05-08 02:26:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":773732,"visible":true,"origin":"","legend":"","description":"","filename":"RobustDLFrameworkSolarForecasting.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9619678/v1_covered_0b109403-9c52-4ba7-b74b-493243089b36.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"Proposing A Robust Deep Learning Framework for Short-Term Solar Power Forecasting Using Sky Images","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","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":"Deep learning, Solar irradiance forecasting, Solar power forecasting, Short-Term Forecasting, Renewable energy integration","lastPublishedDoi":"10.21203/rs.3.rs-9619678/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9619678/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Intermittent solar energy must be correctly predicted on short-term time scales to maintain the stability and efficiency of the power grid it interacts with. This work presents a deep learning framework that is effective in predicting solar irradiance, a direct proxy for energy generation from the input data, which consists of time-ordered sky images. We establish an end-to-end pipeline to process and synchronize high-resolution sky image data from a fisheye camera with colocated direct normal irradiance measurements from pyranometers. The essential part of our model is a Convolutional Neural Network (CNN) that extracts important spatiotemporal identifiers from the images and translates them into predicted values for future irradiance. Our model shows a significant predictive power trained and assessed on a real-world dataset, specifically showing a Sunny Days Mean Absolute Error (MAE) of 0.353, a Root Mean Squared Error (RMSE) of 0.463, a Cloudy Days Mean Absolute Error (MAE) of 0.964, and a Root Mean Squared Error (RMSE) of 2.029, noticed within the held-out test set. The amount of variance in irradiance explained by the model based on visual sky conditions also represents a large jump from baseline, suggesting that this model captures almost 50% of variability in irradiance. Model stability and generalizability are confirmed by the evaluation of training progress. The proposed work lays the groundwork for a highly effective and reproducible deep learning framework for short-term solar forecasting, which serves as a robust paradigm suitable for future incorporation into smart grid management systems to improve solar power generation reliability.","manuscriptTitle":"Proposing A Robust Deep Learning Framework for Short-Term Solar Power Forecasting Using Sky Images","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-05-08 02:26:16","doi":"10.21203/rs.3.rs-9619678/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":"0c9ef7cd-7fcf-4bc6-80c2-e52e92f43c6c","owner":[],"postedDate":"May 8th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":{"display":true,"email":"[email protected]","identity":"journal-of-control-automation-and-electrical-systems","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"jcae","sideBox":"Learn more about [Journal of Control, Automation and Electrical Systems](https://link.springer.com/journal/40313)","snPcode":"40313","submissionUrl":"https://submission.springernature.com/new-submission/40313/3","title":"Journal of Control, Automation and Electrical Systems","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-05-08T02:26:16+00:00","versionOfRecord":[],"versionCreatedAt":"2026-05-08 02:26:16","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9619678","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9619678","identity":"rs-9619678","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}