A Photovoltaic Power Forecasting Method Integrating Physical Mechanisms and Deep Learning

A Photovoltaic Power Forecasting Method Integrating Physical Mechanisms and Deep Learning | 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 A Photovoltaic Power Forecasting Method Integrating Physical Mechanisms and Deep Learning Hongyu Gao, Yuan Lu, Lizhong Tang, Jinrui Cai, Fei Han This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8576566/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 With the rapid expansion of distributed photovoltaic installations, the intermittent and fluctuating nature of their output power poses challenges to grid dispatch and operational stability. Physical models offer good interpretability but suffer from limited accuracy under complex meteorological conditions. Pure data-driven methods lack sufficient generalization under extreme operating conditions, and existing hybrid approaches often employ static weights that struggle to adapt to environmental changes. To address these issues, this paper proposes a photovoltaic power forecasting method that integrates physical mechanisms with multi-scale deep learning. The key innovations of this method include: (1) A non-uniform error compensation strategy based on irradiance interval segmentation to enhance the accuracy of the physical branch across different light intensity ranges; (2) Construction of a 37-dimensional physically enhanced feature system incorporating meteorological, temporal, physically derived, and statistical interaction features, utilizing a parallel Multi-scale CNN (kernel lengths 3/7/15) combined with BiLSTM architecture to extract multi-scale temporal characteristics; (3) A dynamic weighted fusion mechanism based on four-dimensional confidence levels (irradiance, temperature, time, and weather stability) to achieve complementary environmental perception between physical and data-driven models. Validation using 15-minute resolution annual measurement data from a prefecture-level city photovoltaic power station demonstrates significant improvements over pure physical and pure neural network approaches in metrics including MAE, RMSE, and R$^2$ (example results: MAE = 3.571 kW, RMSE = 6.384 kW, R$^2$= 0.9781). Ablation analysis further validated the effectiveness of each module. By balancing physical consistency with data-driven expressiveness, this approach provides practical value for enhancing the accuracy of photovoltaic power forecasting and improving engineering applicability. Photovoltaic power forecasting Feature engineering Adaptive fusion Multi-scale feature extraction Dynamic weight allocation Full Text Additional Declarations No competing interests reported. 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-8576566","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":574375813,"identity":"eb058ea7-2246-4ec5-bedb-2cf84fb5f0a5","order_by":0,"name":"Hongyu Gao","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Hongyu","middleName":"","lastName":"Gao","suffix":""},{"id":574375814,"identity":"dab983bb-f1ab-471c-8c57-bea2f24165ed","order_by":1,"name":"Yuan Lu","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Yuan","middleName":"","lastName":"Lu","suffix":""},{"id":574375815,"identity":"9b10554d-7280-4f92-ba5e-bbb6345caf77","order_by":2,"name":"Lizhong Tang","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Lizhong","middleName":"","lastName":"Tang","suffix":""},{"id":574375816,"identity":"74fd0391-cdc8-475a-b59f-09d9d91363c6","order_by":3,"name":"Jinrui Cai","email":"","orcid":"","institution":"Northeast Petroleum University","correspondingAuthor":false,"prefix":"","firstName":"Jinrui","middleName":"","lastName":"Cai","suffix":""},{"id":574375817,"identity":"386bc921-2d4f-45e0-bb0c-7a4058e1f422","order_by":4,"name":"Fei Han","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3UlEQVRIiWNgGAWjYBACNvnDBx98+CHBw8/e//BBQkUNYS18EmzJhjN7bOQke84wGzw4c4ywFjkJHjVhHrY0Y4MZOWySD1uYiXCYdA8b4wyew4kbGHKPVSQ2sDHwt3cn4Ncic/bYgw8WhxO3M5xLu5G4Q4ZB4szZDfi1MOSlG4Js2dnYYHYj8Qwbg4FELiEtOWbSPGxAhx1mMCtIbGMmQosEWAvQ+8d4zBiI08JzDBbIbMkSCWeO8RD0i3x7MzQq5R8f/PijokaOv70XvxYMwEOa8lEwCkbBKBgFWAEAvgVMkx2pLfYAAAAASUVORK5CYII=","orcid":"","institution":"State Key Laboratory of Continental Shale Oil (SKL-CSO)","correspondingAuthor":true,"prefix":"","firstName":"Fei","middleName":"","lastName":"Han","suffix":""}],"badges":[],"createdAt":"2026-01-12 02:38:12","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8576566/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8576566/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108240440,"identity":"c50a0504-ebd9-47fd-9a2b-804549f8df74","added_by":"auto","created_at":"2026-04-30 20:24:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3587106,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8576566/v1_covered_24c442ee-1001-4930-93a9-781c71318276.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Photovoltaic Power Forecasting Method Integrating Physical Mechanisms and Deep Learning","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Photovoltaic power forecasting, Feature engineering, Adaptive fusion, Multi-scale feature extraction, Dynamic weight allocation","lastPublishedDoi":"10.21203/rs.3.rs-8576566/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8576566/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"With the rapid expansion of distributed photovoltaic installations, the intermittent and fluctuating nature of their output power poses challenges to grid dispatch and operational stability. Physical models offer good interpretability but suffer from limited accuracy under complex meteorological conditions. Pure data-driven methods lack sufficient generalization under extreme operating conditions, and existing hybrid approaches often employ static weights that struggle to adapt to environmental changes. To address these issues, this paper proposes a photovoltaic power forecasting method that integrates physical mechanisms with multi-scale deep learning. The key innovations of this method include: (1) A non-uniform error compensation strategy based on irradiance interval segmentation to enhance the accuracy of the physical branch across different light intensity ranges; (2) Construction of a 37-dimensional physically enhanced feature system incorporating meteorological, temporal, physically derived, and statistical interaction features, utilizing a parallel Multi-scale CNN (kernel lengths 3/7/15) combined with BiLSTM architecture to extract multi-scale temporal characteristics; (3) A dynamic weighted fusion mechanism based on four-dimensional confidence levels (irradiance, temperature, time, and weather stability) to achieve complementary environmental perception between physical and data-driven models. Validation using 15-minute resolution annual measurement data from a prefecture-level city photovoltaic power station demonstrates significant improvements over pure physical and pure neural network approaches in metrics including MAE, RMSE, and R$^2$ (example results: MAE = 3.571 kW, RMSE = 6.384 kW, R$^2$= 0.9781). Ablation analysis further validated the effectiveness of each module. By balancing physical consistency with data-driven expressiveness, this approach provides practical value for enhancing the accuracy of photovoltaic power forecasting and improving engineering applicability.","manuscriptTitle":"A Photovoltaic Power Forecasting Method Integrating Physical Mechanisms and Deep Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-17 17:16:40","doi":"10.21203/rs.3.rs-8576566/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":"fdc80269-e843-40f1-9fdf-af8b167ba3e5","owner":[],"postedDate":"April 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-04-30T20:23:36+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-17 17:16:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8576566","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8576566","identity":"rs-8576566","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}