Do Classical Methods Still Win? Revisiting Forecasting Strategies for Curtailment Mitigation in Brazil

Do Classical Methods Still Win? Revisiting Forecasting Strategies for Curtailment Mitigation in Brazil | 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 Do Classical Methods Still Win? Revisiting Forecasting Strategies for Curtailment Mitigation in Brazil Ricardo Accorsi Casonatto, Eugênia Cornils Monteiro da Silva, and 3 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8263871/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 Background: The increase in curtailment in Brazil highlights structural limitations in the electrical system and reinforces the need for more accurate demand forecasts to support dispatch, storage, and expansion decisions. Although deep learning and hybrid models have advanced rapidly, classical statistical methods remain widely used. This study compares statistical, machine-learning, and hybrid forecasting models using monthly Brazilian electricity consumption data (2004–2023) to assess which techniques offer the best accuracy and efficiency for curtailment-oriented planning. Results: Six models were evaluated: SARIMAX, Holt–Winters, LSTM, XGBoost, ES-RNN, and N-BEATS. Performance was assessed using sMAPE and computational metrics. Holt–Winters achieved the lowest error (2.03 ± 0.06%) with the fastest inference and smallest storage. ES-RNN provided the second-best accuracy (2.18 ± 0.06%) but required significantly more computation. SARIMAX also performed well (2.3 ± 0.1%) with fast inference but high storage demand. LSTM and N-BEATS showed moderate accuracy, with LSTM having the highest computational cost. XGBoost was the least accurate (6.4 ± 0.2%) despite low latency. Conclusions: Classical methods, particularly Holt–Winters, outperformed more complex AI-based models for this dataset, highlighting that methodological sophistication does not always guarantee superior results. Accurate, low-cost forecasting can aid curtailment mitigation and support more reliable renewable integration. Energy Consumption Demand Forecasting Curtailment Sustainability Statistical Models Artificial Intelligence Time Series 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-8263871","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":555725232,"identity":"32c1cb53-ee3b-4d49-8217-e0f1b510ac2d","order_by":0,"name":"Ricardo Accorsi Casonatto","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA10lEQVRIiWNgGAWjYDACZjiLsfEBkOThI0VLswFICxspFrJJgElCyszbmR8w/KixkzPvP9xW+TXHToaNgfnhoxt4tMgcZjNg7DmWbCxzI7Httuy2ZKDD2IyNc/BokWDmYWDgbTiQOEOCse225DZmoBYeNmlCWhj/grTwH2wrltxWT5wWZrAtDIltjB+3HSZGC5vBYRmgXyQkEpulGbcd52FjJuQX/sMPH74BhpgE//GHH39uq7bnZ29++BifFhA4AGOAggI5cokAjD9IUT0KRsEoGAUjBgAA8Ms73WvsTTcAAAAASUVORK5CYII=","orcid":"","institution":"University of Brasilia (UnB)","correspondingAuthor":true,"prefix":"","firstName":"Ricardo","middleName":"Accorsi","lastName":"Casonatto","suffix":""},{"id":555725233,"identity":"7b374a76-07b3-489c-b8cd-d1ddab3ab9ff","order_by":1,"name":"Eugênia Cornils Monteiro da Silva","email":"","orcid":"","institution":"Federal University of Goias","correspondingAuthor":false,"prefix":"","firstName":"Eugênia","middleName":"Cornils Monteiro da","lastName":"Silva","suffix":""},{"id":555725234,"identity":"86c436b9-4bd3-4181-9bf0-082524565d5c","order_by":2,"name":"Sanderson César Macedo Barbalho","email":"","orcid":"","institution":"University of Brasilia (UnB)","correspondingAuthor":false,"prefix":"","firstName":"Sanderson","middleName":"César Macedo","lastName":"Barbalho","suffix":""},{"id":555725235,"identity":"f582b7ca-4034-4923-bfbc-f7c184eabef9","order_by":3,"name":"Marcelo Carneiro Gonçalves","email":"","orcid":"","institution":"University of Brasilia (UnB)","correspondingAuthor":false,"prefix":"","firstName":"Marcelo","middleName":"Carneiro","lastName":"Gonçalves","suffix":""},{"id":555725236,"identity":"e485c57f-945c-496c-8999-1abdb3fff03b","order_by":4,"name":"Maria Gabriela Mendonça Peixoto","email":"","orcid":"","institution":"University of Brasilia (UnB)","correspondingAuthor":false,"prefix":"","firstName":"Maria","middleName":"Gabriela Mendonça","lastName":"Peixoto","suffix":""}],"badges":[],"createdAt":"2025-12-02 20:08:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8263871/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8263871/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":97900594,"identity":"b508b9f9-a71d-4b2f-963e-9e87b224ce48","added_by":"auto","created_at":"2025-12-10 15:45:39","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7390,"visible":true,"origin":"","legend":"","description":"","filename":"04cb318193544f9c9b8a93b5956b51ae.json","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/3fd2d769f5bf76348a997fe2.json"},{"id":97898068,"identity":"d97a27d7-2ae7-4fe6-8a0a-2e6a02babfa4","added_by":"auto","created_at":"2025-12-10 15:38:39","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93496,"visible":true,"origin":"","legend":"","description":"","filename":"04cb318193544f9c9b8a93b5956b51ae1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/252d86026333779974096e8e.xml"},{"id":97900174,"identity":"5f27f1b5-f9e9-4555-8893-d47df3b0f84d","added_by":"auto","created_at":"2025-12-10 15:45:17","extension":"pdf","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106729,"visible":true,"origin":"","legend":"","description":"","filename":"CoverletterEnergySustainabilityandSociety.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/c8f6dfebebe0a1b9cabcb0d5.pdf"},{"id":97858113,"identity":"55391c8e-01f3-410c-9337-5dd001323242","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":578558,"visible":true,"origin":"","legend":"","description":"","filename":"decomp6.png","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/074c0d0a06fd0ec51871b532.png"},{"id":97900093,"identity":"fb02ff11-967b-4b8f-bd44-f5eec6c11548","added_by":"auto","created_at":"2025-12-10 15:45:13","extension":"eps","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2890,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/c5862d805329fc8461133021.eps"},{"id":97900194,"identity":"b1d2d413-1f32-4ec7-b5ea-18b36180ae7d","added_by":"auto","created_at":"2025-12-10 15:45:17","extension":"eps","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":91593,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/f7adb73cc0ffbab17d74916b.eps"},{"id":97900530,"identity":"12e1af96-1780-4eb1-9d14-476d3de921c4","added_by":"auto","created_at":"2025-12-10 15:45:36","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95398,"visible":true,"origin":"","legend":"","description":"","filename":"lstmoverview.png","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/4e81bca72862a865de7b2853.png"},{"id":97899885,"identity":"704649a7-9c41-4bdb-b20b-492359464a4d","added_by":"auto","created_at":"2025-12-10 15:45:02","extension":"pdf","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1797406,"visible":true,"origin":"","legend":"","description":"","filename":"papercurtailment3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/cb82046e16f66e21053c7ef0.pdf"},{"id":97900170,"identity":"ab03ea60-b3bc-4f6a-902d-57051789b559","added_by":"auto","created_at":"2025-12-10 15:45:17","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":506314,"visible":true,"origin":"","legend":"","description":"","filename":"preds.png","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/3280da73bbe280c50b75a869.png"},{"id":97858112,"identity":"dc279ced-6951-4fa8-9074-0e722be981bc","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"bst","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":146013,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/452885143ff1f4ac7fa2d158.bst"},{"id":97900156,"identity":"4888c974-a837-47cc-8f52-e6093f563dc0","added_by":"auto","created_at":"2025-12-10 15:45:16","extension":"bst","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":29828,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/89661bd402fba963d1561d05.bst"},{"id":97899046,"identity":"18055da6-fa21-49ae-a663-073d2cc4bf9f","added_by":"auto","created_at":"2025-12-10 15:40:56","extension":"pdf","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":421391,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/a83687b74c181f97260fa56a.pdf"},{"id":97858095,"identity":"d1cc4002-1188-4fe8-93be-566d8ee92995","added_by":"auto","created_at":"2025-12-10 08:15:34","extension":"bst","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35515,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/5fc66d38aabe83eb1cf50921.bst"},{"id":97897905,"identity":"35490b54-2914-45c0-b332-1cbeef5aca74","added_by":"auto","created_at":"2025-12-10 15:38:26","extension":"bst","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33968,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/c728ea71ad0bfb0950540076.bst"},{"id":97900173,"identity":"1eae3b23-553f-4236-92e7-f93c173b74c6","added_by":"auto","created_at":"2025-12-10 15:45:17","extension":"cls","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":55857,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/7324b7ef892ea8d6b83a2a31.cls"},{"id":97858116,"identity":"beec0aa8-7829-42b2-a0a7-e508e9da41e8","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"bst","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64023,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/e1a4c6602926dcc0792fda97.bst"},{"id":97899716,"identity":"ec5fd44b-8163-4112-9a71-0c40bf038741","added_by":"auto","created_at":"2025-12-10 15:44:51","extension":"bst","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":64166,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/fa30e78f239933be9cee5a94.bst"},{"id":97858118,"identity":"75f8e115-b1fc-444f-91d0-d033e924f549","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"bst","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/e16ab4128c2521176d07c75f.bst"},{"id":97858107,"identity":"ec10f45c-2097-4fdb-aa76-d66e79e4ff06","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"bst","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39951,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/a222378a714b1fe976eb6363.bst"},{"id":97900209,"identity":"8b147214-792b-4430-92d5-f4d2d415116d","added_by":"auto","created_at":"2025-12-10 15:45:18","extension":"bst","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":40758,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/a63608cc8af36dd21d545623.bst"},{"id":97899446,"identity":"3c8d233b-1565-427e-ae04-ad54d504838b","added_by":"auto","created_at":"2025-12-10 15:44:31","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217768,"visible":true,"origin":"","legend":"","description":"","filename":"ts5.png","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/4f93e6faf3495475a27d687b.png"},{"id":97858117,"identity":"b3ccbb9e-bfcc-40e2-9d73-d9f59a6824e5","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"pdf","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/ef6061020937f55086d34e9b.pdf"},{"id":97858115,"identity":"c4964622-8222-4a73-80b5-3321397a1325","added_by":"auto","created_at":"2025-12-10 08:15:35","extension":"xml","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":103211,"visible":true,"origin":"","legend":"","description":"","filename":"04cb318193544f9c9b8a93b5956b51ae1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/332cf8f721d500717d7c014e.xml"},{"id":97897666,"identity":"5834ad5f-621b-42d3-aea9-3c1f1b51d3e7","added_by":"auto","created_at":"2025-12-10 15:38:05","extension":"html","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":108197,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1/bbe896b53abb9b98383eb8fa.html"},{"id":99383326,"identity":"c93a96a5-2c3b-4f91-bc0f-3ae780a621e8","added_by":"auto","created_at":"2026-01-02 10:55:13","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2187773,"visible":true,"origin":"","legend":"","description":"","filename":"papercurtailment3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8263871/v1_covered_6c6b10c2-cf0a-4e72-97b3-e4d8106e141e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Do Classical Methods Still Win? Revisiting Forecasting Strategies for Curtailment Mitigation in Brazil","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":"Energy Consumption, Demand Forecasting, Curtailment, Sustainability, Statistical Models, Artificial Intelligence, Time Series","lastPublishedDoi":"10.21203/rs.3.rs-8263871/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8263871/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eBackground: The increase in curtailment in Brazil highlights structural limitations in the electrical system and reinforces the need for more accurate demand forecasts to support dispatch, storage, and expansion decisions. Although deep learning and hybrid models have advanced rapidly, classical statistical methods remain widely used. This study compares statistical, machine-learning, and hybrid forecasting models using monthly Brazilian electricity consumption data (2004\u0026ndash;2023) to assess which techniques offer the best accuracy and efficiency for curtailment-oriented planning. Results: Six models were evaluated: SARIMAX, Holt\u0026ndash;Winters, LSTM, XGBoost, ES-RNN, and N-BEATS. Performance was assessed using sMAPE and computational metrics. Holt\u0026ndash;Winters achieved the lowest error (2.03 \u0026plusmn; 0.06%) with the fastest inference and smallest storage. ES-RNN provided the second-best accuracy (2.18 \u0026plusmn; 0.06%) but required significantly more computation. SARIMAX also performed well (2.3 \u0026plusmn; 0.1%) with fast inference but high storage demand. LSTM and N-BEATS showed moderate accuracy, with LSTM having the highest computational cost. XGBoost was the least accurate (6.4 \u0026plusmn; 0.2%) despite low latency. Conclusions: Classical methods, particularly Holt\u0026ndash;Winters, outperformed more complex AI-based models for this dataset, highlighting that methodological sophistication does not always guarantee superior results. Accurate, low-cost forecasting can aid curtailment mitigation and support more reliable renewable integration.\u003c/p\u003e","manuscriptTitle":"Do Classical Methods Still Win? Revisiting Forecasting Strategies for Curtailment Mitigation in Brazil","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-10 08:15:29","doi":"10.21203/rs.3.rs-8263871/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":"0c48b5cb-8c13-45f2-9b1b-edff9b55f7ec","owner":[],"postedDate":"December 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-02T10:54:38+00:00","versionOfRecord":[],"versionCreatedAt":"2025-12-10 08:15:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8263871","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8263871","identity":"rs-8263871","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}