Research on scheduling rule extraction and model comparison based on autoencoder and self-attention mechanism

Research on scheduling rule extraction and model comparison based on autoencoder and self-attention mechanism | 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 Research on scheduling rule extraction and model comparison based on autoencoder and self-attention mechanism r pa, Pingan Ren, Hui Qin, Li Mo, Yongchuan Zhang, Zhiqiang Jiang, and 4 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-5345488/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 Reservoir operation rule function is a functional mapping method that reflects specific operational rules to guide reservoir operations. With the deepening of research, the scheduling function has changed from linear to nonlinear forms, from single-objective functions to integrated multi-objective functions, from ignoring uncertainty to incorporating uncertainty analysis, from using fixed parameters to parameters that dynamically change over time, and the system has been continuously refined. Different dispatching rule functions have different actual dispatching effects (flood control, power generation benefits, water resource utilization rate and reliability). Reservoir optimal dispatching aims to identify the best rule functions to achieve the specified objectives. Through advanced computing technologies, the complex relationships between dispatch-related factors and decision variables can be extracted from large amounts of historical reservoir operation data, thus facilitating the extraction of reservoir dispatch rules. With the construction of more and more reservoirs, the hydraulic connections between reservoir groups are complex, with mutual influences occurring across both spatial and temporal scales. These complex correlation factors need to be considered when extracting dispatch rule functions. Compared to conventional operation charts, the operation rule functions extracted through data mining methods offer greater convenience in reservoir group operations. This study adopts a machine learning model based on an autoencoder and self-attention mechanism, focusing on key reservoirs along the Yangtze River and its tributaries. A combined model of these techniques is proposed, and the natural gradient boosting scheduling comparison model is applied to optimize and compare the extracted scheduling rules. The applicability of the model is verified through analysis, and the results are further explained using SHAP (SHapley Additive exPlanations) theory, which provides interpretability for the model results. autoencoder self-attention Natural Gradient Boosting SHapley Additive exPlanations Scheduling rules Full Text 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-5345488","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":373274110,"identity":"43893fbf-7466-4269-b532-da78e93b0e93","order_by":0,"name":"r pa","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzUlEQVRIiWNgGAWjYBACxobDBx//qaip52dvIFILc+OxZAOeM8cSJHsOEKmFvfmMmQRvG3OCwYwEIrXwth0wNpA4w5ZnIPl44w2GGptoglqA7kl8YFAhU2wunVZswXAsLbeBkBbDGQcOGyScYWPcOTvHTAIYGIS12N9/2CZxsI2ZccPNM0RqASpik2xsY07ccIOHaC3HmI0ZzhwzluwB+iWBGL8wNpz/+JihokaOn/3wxhsfamwIa0EGBhIJpCiHaCFVxygYBaNgFIwMAAA0nkY4ykpiiwAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0000-0001-9935-6813","institution":"Huazhong University of Science and Technology - Main Campus: Huazhong University of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"r","middleName":"","lastName":"pa","suffix":""},{"id":373274111,"identity":"e8b82c43-0ed5-49af-8165-583e4ba8b992","order_by":1,"name":"Pingan Ren","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Pingan","middleName":"","lastName":"Ren","suffix":""},{"id":373274112,"identity":"786883bf-0a25-491f-9f22-48ea1c7297f1","order_by":2,"name":"Hui Qin","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Hui","middleName":"","lastName":"Qin","suffix":""},{"id":373274113,"identity":"f88bfb3d-f144-4ac4-99cf-8a308aa113f2","order_by":3,"name":"Li Mo","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Mo","suffix":""},{"id":373274114,"identity":"362d4966-9d22-4d9f-9217-f3777250fbf3","order_by":4,"name":"Yongchuan Zhang","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Yongchuan","middleName":"","lastName":"Zhang","suffix":""},{"id":373274115,"identity":"9a10e128-fc24-4841-9e73-be9b74bf8aba","order_by":5,"name":"Zhiqiang Jiang","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Zhiqiang","middleName":"","lastName":"Jiang","suffix":""},{"id":373274116,"identity":"68005998-16f4-4689-b233-e58c133405c3","order_by":6,"name":"Xinyu Chang","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Chang","suffix":""},{"id":373274117,"identity":"d6e343c4-b2ee-42af-b844-eebdd974ec1a","order_by":7,"name":"Jingwei Huang","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Jingwei","middleName":"","lastName":"Huang","suffix":""},{"id":373274118,"identity":"a79af42f-7ab5-467f-91da-e50998d73869","order_by":8,"name":"Shuai Liu","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Shuai","middleName":"","lastName":"Liu","suffix":""},{"id":373274119,"identity":"a91f4a8a-3402-4153-aaef-19cd7f8b0dad","order_by":9,"name":"Sipeng Zhu","email":"","orcid":"","institution":"Huazhong University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Sipeng","middleName":"","lastName":"Zhu","suffix":""}],"badges":[],"createdAt":"2024-10-28 08:48:06","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-5345488/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-5345488/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93242564,"identity":"9b19db3e-0191-48b6-bfd2-2dabdbe03e98","added_by":"auto","created_at":"2025-10-10 14:54:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1361954,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-5345488/v1_covered_40915548-5e11-4eb4-9369-00f4c6801c4c.pdf"}],"financialInterests":"","formattedTitle":"Research on scheduling rule extraction and model comparison based on autoencoder and self-attention mechanism","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":"autoencoder, self-attention, Natural Gradient Boosting, SHapley Additive exPlanations, Scheduling rules","lastPublishedDoi":"10.21203/rs.3.rs-5345488/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-5345488/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eReservoir operation rule function is a functional mapping method that reflects specific operational rules to guide reservoir operations. With the deepening of research, the scheduling function has changed from linear to nonlinear forms, from single-objective functions to integrated multi-objective functions, from ignoring uncertainty to incorporating uncertainty analysis, from using fixed parameters to parameters that dynamically change over time, and the system has been continuously refined. Different dispatching rule functions have different actual dispatching effects (flood control, power generation benefits, water resource utilization rate and reliability). Reservoir optimal dispatching aims to identify the best rule functions to achieve the specified objectives. Through advanced computing technologies, the complex relationships between dispatch-related factors and decision variables can be extracted from large amounts of historical reservoir operation data, thus facilitating the extraction of reservoir dispatch rules. With the construction of more and more reservoirs, the hydraulic connections between reservoir groups are complex, with mutual influences occurring across both spatial and temporal scales. These complex correlation factors need to be considered when extracting dispatch rule functions. Compared to conventional operation charts, the operation rule functions extracted through data mining methods offer greater convenience in reservoir group operations. This study adopts a machine learning model based on an autoencoder and self-attention mechanism, focusing on key reservoirs along the Yangtze River and its tributaries. A combined model of these techniques is proposed, and the natural gradient boosting scheduling comparison model is applied to optimize and compare the extracted scheduling rules. The applicability of the model is verified through analysis, and the results are further explained using SHAP (SHapley Additive exPlanations) theory, which provides interpretability for the model results.\u003c/p\u003e","manuscriptTitle":"Research on scheduling rule extraction and model comparison based on autoencoder and self-attention mechanism","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-11-14 15:54:03","doi":"10.21203/rs.3.rs-5345488/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":"60e33409-66a3-4e3b-a36e-1d3d32471b40","owner":[],"postedDate":"November 14th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-10T14:46:24+00:00","versionOfRecord":[],"versionCreatedAt":"2024-11-14 15:54:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-5345488","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-5345488","identity":"rs-5345488","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}