Ensemble learning with anomaly detection for accurate day-ahead electricity price forecasting

Ensemble learning with anomaly detection for accurate day-ahead electricity price forecasting | 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 Article Ensemble learning with anomaly detection for accurate day-ahead electricity price forecasting Faheem Jan, Musaad S. Aldhabani, Izatmand Haleemzai, Ahmed M. Zidan, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9130354/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 Timely and accurate electricity price forecasting is essential for the efficient operation of competitive electricity markets. However, predicting day-ahead electricity prices remains challenging due to market volatility, anomalous price observations, and complex nonlinear relationships in electricity price dynamics. This study proposes a novel ensemble forecasting framework for predicting day-ahead electricity prices in the German electricity market. The framework integrates classical time-series models, machine-learning approaches, and hybrid models as base learners, and combines their forecasts using three weighting strategies based on validation performance, model diversity, and error minimization. To enhance forecasting robustness, six years of hourly electricity market data were preprocessed to detect and normalize anomalous observations. Experimental results demonstrate that the proposed ensemble framework consistently outperforms individual classical time-series models, standalone machine-learning models, and hybrid approaches. Among the benchmark models, hybrid models show better predictive performance than classical time-series methods but remain inferior to the proposed ensemble strategies. The findings highlight the importance of anomaly treatment and intelligent model combination for improving electricity price forecasting accuracy. The proposed framework provides valuable insights and practical forecasting tools for energy traders, grid operators, and policymakers involved in electricity market decision-making. Physical sciences/Energy science and technology Physical sciences/Engineering Physical sciences/Mathematics and computing Electricity Price Forecasting Anomaly Detection Ensemble Learning Machine Learning STL Decomposition.vector autoregressive autoregressive moving average autoregressive neural network k-nearest Neighbors 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-9130354","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":626116925,"identity":"c023838c-709c-4fe6-a35c-ddb720b2d767","order_by":0,"name":"Faheem Jan","email":"","orcid":"","institution":"Bacha Khan University","correspondingAuthor":false,"prefix":"","firstName":"Faheem","middleName":"","lastName":"Jan","suffix":""},{"id":626116926,"identity":"aa6e492a-d642-4af0-a5c0-cca78cae92e2","order_by":1,"name":"Musaad S. Aldhabani","email":"","orcid":"","institution":"University of Tabuk","correspondingAuthor":false,"prefix":"","firstName":"Musaad","middleName":"S.","lastName":"Aldhabani","suffix":""},{"id":626116935,"identity":"44212b22-3819-4ebd-a990-e716cc61be28","order_by":2,"name":"Izatmand Haleemzai","email":"data:image/png;base64,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","orcid":"","institution":"Polytechnical University of Kabul","correspondingAuthor":true,"prefix":"","firstName":"Izatmand","middleName":"","lastName":"Haleemzai","suffix":""},{"id":626116938,"identity":"43e85dfc-5270-4d3b-8b3d-e96ae7094c3f","order_by":3,"name":"Ahmed M. Zidan","email":"","orcid":"","institution":"King Khalid University","correspondingAuthor":false,"prefix":"","firstName":"Ahmed","middleName":"M.","lastName":"Zidan","suffix":""},{"id":626116942,"identity":"bbf1665a-518d-40ba-8306-ee693a20c9e4","order_by":4,"name":"Mehwish Tahir","email":"","orcid":"","institution":"Shaheed Benazir Bhutto Women University","correspondingAuthor":false,"prefix":"","firstName":"Mehwish","middleName":"","lastName":"Tahir","suffix":""}],"badges":[],"createdAt":"2026-03-15 17:38:45","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9130354/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9130354/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":108095336,"identity":"6ef90132-e877-4039-a1fe-f62d0a9d8f6d","added_by":"auto","created_at":"2026-04-29 09:56:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1323809,"visible":true,"origin":"","legend":"","description":"","filename":"paper7Bigdata.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9130354/v1_covered_a6da5dce-0f9f-442c-be35-87a615a9bc1d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Ensemble learning with anomaly detection for accurate day-ahead electricity price forecasting","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":"Electricity Price Forecasting, Anomaly Detection, Ensemble Learning, Machine Learning, STL Decomposition.vector autoregressive, autoregressive moving average, autoregressive neural network, k-nearest Neighbors ","lastPublishedDoi":"10.21203/rs.3.rs-9130354/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9130354/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTimely and accurate electricity price forecasting is essential for the efficient operation of competitive electricity markets. However, predicting day-ahead electricity prices remains challenging due to market volatility, anomalous price observations, and complex nonlinear relationships in electricity price dynamics. This study proposes a novel ensemble forecasting framework for predicting day-ahead electricity prices in the German electricity market. The framework integrates classical time-series models, machine-learning approaches, and hybrid models as base learners, and combines their forecasts using three weighting strategies based on validation performance, model diversity, and error minimization. To enhance forecasting robustness, six years of hourly electricity market data were preprocessed to detect and normalize anomalous observations. Experimental results demonstrate that the proposed ensemble framework consistently outperforms individual classical time-series models, standalone machine-learning models, and hybrid approaches. Among the benchmark models, hybrid models show better predictive performance than classical time-series methods but remain inferior to the proposed ensemble strategies. The findings highlight the importance of anomaly treatment and intelligent model combination for improving electricity price forecasting accuracy. The proposed framework provides valuable insights and practical forecasting tools for energy traders, grid operators, and policymakers involved in electricity market decision-making.\u003c/p\u003e","manuscriptTitle":"Ensemble learning with anomaly detection for accurate day-ahead electricity price forecasting","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-21 10:48:22","doi":"10.21203/rs.3.rs-9130354/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":"fa95e1fb-420e-475a-b6aa-7063e2580f86","owner":[],"postedDate":"April 21st, 2026","published":true,"recentEditorialEvents":[{"type":"decision","content":"Withdrawn","date":"2026-04-29T09:42:33+00:00","index":"","fulltext":""}],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":66633618,"name":"Physical sciences/Energy science and technology"},{"id":66633619,"name":"Physical sciences/Engineering"},{"id":66633620,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-04-29T09:55:08+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-21 10:48:22","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9130354","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9130354","identity":"rs-9130354","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}