An Innovative Deep Learning Approach for Simultaneous Load and Price Prediction in Smart Power Grids

An Innovative Deep Learning Approach for Simultaneous Load and Price Prediction in Smart Power Grids | 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 An Innovative Deep Learning Approach for Simultaneous Load and Price Prediction in Smart Power Grids S-Mozhgan Rahmatinia, Seyed-Amin Hosseini seno This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4287067/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 Predicting time series data in the electricity domain serves as a fundamental basis for implementing Demand Response (DR) techniques in smart grid networks, a topic widely addressed in the literature. In this paper, we propose a flexible deep learning approach based on the encoder-decoder architecture for simultaneous prediction of both load and electricity price. The ability of the model to capture long-term dependencies and extract meaningful patterns from the data is crucial for its effectiveness. To enhance this capability, we incorporate a scaled attention mechanism into the model to attend over the hidden encoder outputs, enabling better capture of relevant information. Additionally, we introduce a preprocessing step using the Fast Fourier Transform (FFT) to extract frequency-domain features from the input data. By applying FFT at the beginning of the proposed model in the encoder section, we aim to better capture the underlying patterns in the data and facilitate the learning process. It is worth noting that while FFT is utilized for preprocessing, the decoder section of the model operates directly on the original data without employing inverse FFT, ensuring data integrity and preventing information leakage. The proposed model is trained and evaluated on [ 38 ] data and compared with several deep learning approaches, demonstrating improved prediction accuracy in all cases. This work contributes to the field by presenting a novel approach that effectively leverages both attention mechanisms and Fourier domain preprocessing for enhanced time series prediction in the electricity domain. Multivariate Time Series Forecasting Deep Learning Model Encoder-Attention-Decoder Architecture Fast Fourier Transform (FFT) Temporal Patterns 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-4287067","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":296747229,"identity":"ae461b28-4f80-4671-9f78-69f07ee03de7","order_by":0,"name":"S-Mozhgan Rahmatinia","email":"","orcid":"","institution":"Ferdowsi University of Mashhad","correspondingAuthor":false,"prefix":"","firstName":"S-Mozhgan","middleName":"","lastName":"Rahmatinia","suffix":""},{"id":296747230,"identity":"977706ba-e1a0-4410-9645-a7f8f77dd704","order_by":1,"name":"Seyed-Amin Hosseini seno","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAt0lEQVRIiWNgGAWjYBACAyjJww8V4CFei2QDaVpAjAPEOsycvf3xhw8Fd2SMb2QnMPyoYZAxbyCgxbLnjJnkDINnPGY3cjcw9hxj4JEhZJ3BjRw2Zh6Dw2AtDLwNDDwShBxmcCP98ec/QC3GM4C2/CVOS4KBNANQi4FE7gZm4mw5A/RLD1CLxJm3Gw7LHJMgQstxYIj9+HPYnr89d+PDNzU29gS1oIADDAykaRgFo2AUjIJRgAMAAK0yOnKUmoIZAAAAAElFTkSuQmCC","orcid":"","institution":"Ferdowsi University of Mashhad","correspondingAuthor":true,"prefix":"","firstName":"Seyed-Amin","middleName":"Hosseini","lastName":"seno","suffix":""}],"badges":[],"createdAt":"2024-04-18 10:27:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4287067/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4287067/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":62786633,"identity":"c27d8878-a8b3-406c-b662-5e355c535ebd","added_by":"auto","created_at":"2024-08-19 13:22:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":721612,"visible":true,"origin":"","legend":"","description":"","filename":"RahmatiniaFinalSGFFT.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4287067/v1_covered_b6e45cd4-abaf-470b-a8d3-1a66f244f6f3.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Innovative Deep Learning Approach for Simultaneous Load and Price Prediction in Smart Power Grids","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":"Multivariate Time Series Forecasting, Deep Learning Model, Encoder-Attention-Decoder Architecture, Fast Fourier Transform (FFT), Temporal Patterns","lastPublishedDoi":"10.21203/rs.3.rs-4287067/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4287067/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003ePredicting time series data in the electricity domain serves as a fundamental basis for implementing Demand Response (DR) techniques in smart grid networks, a topic widely addressed in the literature. In this paper, we propose a flexible deep learning approach based on the encoder-decoder architecture for simultaneous prediction of both load and electricity price. The ability of the model to capture long-term dependencies and extract meaningful patterns from the data is crucial for its effectiveness. To enhance this capability, we incorporate a scaled attention mechanism into the model to attend over the hidden encoder outputs, enabling better capture of relevant information. Additionally, we introduce a preprocessing step using the Fast Fourier Transform (FFT) to extract frequency-domain features from the input data. By applying FFT at the beginning of the proposed model in the encoder section, we aim to better capture the underlying patterns in the data and facilitate the learning process. It is worth noting that while FFT is utilized for preprocessing, the decoder section of the model operates directly on the original data without employing inverse FFT, ensuring data integrity and preventing information leakage. The proposed model is trained and evaluated on [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e] data and compared with several deep learning approaches, demonstrating improved prediction accuracy in all cases. This work contributes to the field by presenting a novel approach that effectively leverages both attention mechanisms and Fourier domain preprocessing for enhanced time series prediction in the electricity domain.\u003c/p\u003e","manuscriptTitle":"An Innovative Deep Learning Approach for Simultaneous Load and Price Prediction in Smart Power Grids","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-03 11:03:59","doi":"10.21203/rs.3.rs-4287067/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":"18f96bc5-bea5-41d2-8dfc-82a1dc8702bc","owner":[],"postedDate":"May 3rd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-08-19T13:14:31+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-03 11:03:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4287067","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4287067","identity":"rs-4287067","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}