Operational wind speed forecasts for Chile’s electric grid using multi-layer perceptrons and graph neural networks

Operational wind speed forecasts for Chile’s electric grid using multi-layer perceptrons and graph neural networks | 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 Operational wind speed forecasts for Chile’s electric grid using multi-layer perceptrons and graph neural networks Dhruv Suri, Praneet Dutta, Flora Xue, Anela Arifi, Ravi Jain This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5627108/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 As Chile's electric power sector advances toward a future powered by renewable energy, accurate forecasting of renewable generation is essential for managing grid operations. The integration of renewable energy sources is particularly challenging due to the operational difficulties of managing their power generation, which is highly variable compared to fossil fuel sources. To mitigate this, we quantify the impact of increasing intermittent generation from wind and solar on thermal power plants in Chile and introduce a hybrid wind speed forecasting methodology which combines two custom machine learning models for Chile. The first model is based on TiDE, a multi-layer perceptron machine learning model for short-term forecasts up to 2 days, and the second is based on a graph neural network, GraphCast, for medium-term forecasts up to 10 days. Our hybrid approach outperforms the most accurate operational deterministic systems by 4-21% for short-term forecasts and 5-23% for medium-term forecasts and can directly lower the impact of wind generation on thermal ramping, curtailment, and system-level emissions in Chile. Physical sciences/Energy science and technology/Renewable energy/Wind energy Earth and environmental sciences/Climate sciences/Atmospheric science/Atmospheric dynamics Full Text Additional Declarations There is NO Competing Interest. Supplementary Files ChileSI1.pdf Supplementary Information 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-5627108","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":417566365,"identity":"76392afc-8225-4736-96fc-6450a87e5eec","order_by":0,"name":"Dhruv Suri","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzElEQVRIiWNgGAWjYJCCAzwVIIrxAQMDG4hLlJYzDBIMDMwGxGth4G0jRYv8jNyHB97Oq6vjn93M+LiijEGO70YCfi0GN9INDs7ddlhC4s5hZsMz5xiMJQlqkUhjOMy77YAEw438Y5KNbQyJGwhpkZ8B0jKnTkL+RjIbSEs9QS0MN0BaGpglDKBaEgwIOuzMM4aDc44dltx4I5nZsOGchOHMMw8IOKw9jfnDm5o6frkbyYwPG8ps5PmOE3IYGpAgTfkoGAWjYBSMAuwAAAGqRbP5aeg4AAAAAElFTkSuQmCC","orcid":"","institution":"Stanford University","correspondingAuthor":true,"prefix":"","firstName":"Dhruv","middleName":"","lastName":"Suri","suffix":""},{"id":417566366,"identity":"c8c9b39c-d7c8-406a-a81e-28adcba932f7","order_by":1,"name":"Praneet Dutta","email":"","orcid":"","institution":"Google Deepmind","correspondingAuthor":false,"prefix":"","firstName":"Praneet","middleName":"","lastName":"Dutta","suffix":""},{"id":417566367,"identity":"a17c13ec-e35f-4181-a948-05bb7040cdfc","order_by":2,"name":"Flora Xue","email":"","orcid":"","institution":"Google Deepmind","correspondingAuthor":false,"prefix":"","firstName":"Flora","middleName":"","lastName":"Xue","suffix":""},{"id":417566368,"identity":"9d095a4c-d222-4fd8-9455-41af3be9146e","order_by":3,"name":"Anela Arifi","email":"","orcid":"","institution":"Stanford University","correspondingAuthor":false,"prefix":"","firstName":"Anela","middleName":"","lastName":"Arifi","suffix":""},{"id":417566369,"identity":"88fa80d7-f024-4c0e-a150-f22a67651542","order_by":4,"name":"Ravi Jain","email":"","orcid":"","institution":"X - The Moonshot Factory","correspondingAuthor":false,"prefix":"","firstName":"Ravi","middleName":"","lastName":"Jain","suffix":""}],"badges":[],"createdAt":"2024-12-11 22:25:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5627108/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5627108/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":78798450,"identity":"4502adc7-22b4-45c2-87ac-09d3c77c089e","added_by":"auto","created_at":"2025-03-19 06:01:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":564627,"visible":true,"origin":"","legend":"Article File","description":"","filename":"Chilemanuscript1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5627108/v1_covered_edcc6fec-5d4b-4a0f-92e8-1fd9df4d84ff.pdf"},{"id":78796608,"identity":"6a9489ed-4c00-4e9b-bf7b-0b1341da1125","added_by":"auto","created_at":"2025-03-19 05:29:01","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":5602080,"visible":true,"origin":"","legend":"Supplementary Information","description":"","filename":"ChileSI1.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5627108/v1/5c78c08a41ee51c7a43a6b70.pdf"}],"financialInterests":"There is \u003cb\u003eNO\u003c/b\u003e Competing Interest.","formattedTitle":"Operational wind speed forecasts for Chile’s electric grid using multi-layer perceptrons and graph neural networks","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":"","lastPublishedDoi":"10.21203/rs.3.rs-5627108/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5627108/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"As Chile's electric power sector advances toward a future powered by renewable energy, accurate forecasting of renewable generation is essential for managing grid operations. The integration of renewable energy sources is particularly challenging due to the operational difficulties of managing their power generation, which is highly variable compared to fossil fuel sources. To mitigate this, we quantify the impact of increasing intermittent generation from wind and solar on thermal power plants in Chile and introduce a hybrid wind speed forecasting methodology which combines two custom machine learning models for Chile. The first model is based on TiDE, a multi-layer perceptron machine learning model for short-term forecasts up to 2 days, and the second is based on a graph neural network, GraphCast, for medium-term forecasts up to 10 days. Our hybrid approach outperforms the most accurate operational deterministic systems by 4-21% for short-term forecasts and 5-23% for medium-term forecasts and can directly lower the impact of wind generation on thermal ramping, curtailment, and system-level emissions in Chile.","manuscriptTitle":"Operational wind speed forecasts for Chile’s electric grid using multi-layer perceptrons and graph neural networks","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-19 05:28:56","doi":"10.21203/rs.3.rs-5627108/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":"0ea0e770-80c7-4741-a6a9-3850ef4222d8","owner":[],"postedDate":"March 19th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":44519179,"name":"Physical sciences/Energy science and technology/Renewable energy/Wind energy"},{"id":44519180,"name":"Earth and environmental sciences/Climate sciences/Atmospheric science/Atmospheric dynamics"}],"tags":[],"updatedAt":"2025-03-19T05:28:58+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-19 05:28:56","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5627108","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5627108","identity":"rs-5627108","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}