A Load Forecasting Method of New Power System Based on Personalized Federated Learning

A Load Forecasting Method of New Power System Based on Personalized Federated 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 Load Forecasting Method of New Power System Based on Personalized Federated Learning Yang Shen, Zewen Li, Fangming Deng, Bo Gao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4752697/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 The emerging distributed generation technology in new power systems encounters the challenges of unstable efficiency and high accuracy of prediction models. The generalization ability of prediction models is hindered by variations in users’ behavioral characteristics. Furthermore, inability to share power data across regions poses substantial impediments to generation arrangement and power dispatch. This paper proposes a load forecasting technology based on federated learning (FL), which can avoid uploading or sharing the users’ data to protect data privacy. A multi-task module was added to traditional FL to improve user accuracy (UA) rather than global model accuracy, where the client trains a separate personalized model by keeping the local Layer-Normalization (LN) private. Moreover, in order to fast model convergence, the local LSTM prediction algorithm was added with the Grey Wolf optimization (GWO) algorithm and the attention mechanism. The experimental results show that the overall model training time of the improved LSTM algorithm is shortened by 26%. The Mean absolute percentage error (MAPE) of the proposed multi-task FL is 9.79% lower than traditional FL, and the MAPE of clients with small data volume and large feature deviation is reduced by 18.07% at most. Personalized Federated Learning Multi-task Load Forecasting Deep Learning 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-4752697","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":332492441,"identity":"5b729adf-1fae-4942-9066-1dcc09281aeb","order_by":0,"name":"Yang Shen","email":"","orcid":"","institution":"Jiangxi Fangxing Technology Co., Ltd","correspondingAuthor":false,"prefix":"","firstName":"Yang","middleName":"","lastName":"Shen","suffix":""},{"id":332492442,"identity":"b0d5fbef-7d73-4336-b806-871609799d4c","order_by":1,"name":"Zewen Li","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Zewen","middleName":"","lastName":"Li","suffix":""},{"id":332492443,"identity":"3ec31b55-5f43-4b2d-8ca7-cf09b6b0e4ff","order_by":2,"name":"Fangming Deng","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYBACfobDBww+MDAwg3k8xGiRbDyWUDgDqIWHaC0Gh88ofOaBqSZKC8OxM4ybbSrs2O0lEhgfvG1jkDcnpIOx5+xh45wzycw8EgnMhnPbGAx3NhDQwixxLs04t+0ASAubNG8bQ4LBAQJa2OTfmP+2/AfWwv6bKC08DGcMjBkbILYwE6VFguFYgmHPMaBfzjxslpxzTsJwAyEt9geAUfmjxi6ZvT354Ic3ZTbyBG2BgWRg4DWAbSUa2BGvdBSMglEwCkYcAACAFzyzqDvL3QAAAABJRU5ErkJggg==","orcid":"","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Fangming","middleName":"","lastName":"Deng","suffix":""},{"id":332492444,"identity":"4862f154-002f-4577-9313-2094615bdff1","order_by":3,"name":"Bo Gao","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Bo","middleName":"","lastName":"Gao","suffix":""}],"badges":[],"createdAt":"2024-07-17 01:00:53","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4752697/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4752697/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":72786066,"identity":"04041e53-d4ce-4b5b-86ed-c14861c533df","added_by":"auto","created_at":"2025-01-02 06:54:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1731199,"visible":true,"origin":"","legend":"","description":"","filename":"ALoadForecastingMethodofNewPower.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4752697/v1_covered_b8d2eea1-2a1a-4b0c-bc2e-0e8333629f06.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"A Load Forecasting Method of New Power System Based on Personalized Federated 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":"Personalized Federated Learning, Multi-task, Load Forecasting, Deep Learning","lastPublishedDoi":"10.21203/rs.3.rs-4752697/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4752697/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"The emerging distributed generation technology in new power systems encounters the challenges of unstable efficiency and high accuracy of prediction models. The generalization ability of prediction models is hindered by variations in users’ behavioral characteristics. Furthermore, inability to share power data across regions poses substantial impediments to generation arrangement and power dispatch. This paper proposes a load forecasting technology based on federated learning (FL), which can avoid uploading or sharing the users’ data to protect data privacy. A multi-task module was added to traditional FL to improve user accuracy (UA) rather than global model accuracy, where the client trains a separate personalized model by keeping the local Layer-Normalization (LN) private. Moreover, in order to fast model convergence, the local LSTM prediction algorithm was added with the Grey Wolf optimization (GWO) algorithm and the attention mechanism. The experimental results show that the overall model training time of the improved LSTM algorithm is shortened by 26%. The Mean absolute percentage error (MAPE) of the proposed multi-task FL is 9.79% lower than traditional FL, and the MAPE of clients with small data volume and large feature deviation is reduced by 18.07% at most.","manuscriptTitle":"A Load Forecasting Method of New Power System Based on Personalized Federated Learning","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-08-13 06:50:38","doi":"10.21203/rs.3.rs-4752697/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":"1f548e2e-703e-4e38-9c94-8fd28dc1ff3d","owner":[],"postedDate":"August 13th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-01-02T06:54:04+00:00","versionOfRecord":[],"versionCreatedAt":"2024-08-13 06:50:38","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4752697","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4752697","identity":"rs-4752697","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}