Participant-Level Anomaly Detection for Generation and Load Data Using Dual-Side LSTMs

Participant-Level Anomaly Detection for Generation and Load Data Using Dual-Side LSTMs | 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 Participant-Level Anomaly Detection for Generation and Load Data Using Dual-Side LSTMs Qianya He, Qi Liu, Xueliang Gong, Jiaxun Liu, Liming Yao, Tianze Yu, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9206232/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 14 You are reading this latest preprint version Abstract Reliable anomaly detection for generation and load metering data is essential to market settlement. In practice, anomalies are diverse and sparse, and the load side contains a large and time-varying number of participants, which makes fine-grained participant-level localization difficult. Conventional statistical thresholding and generic outlier detectors (e.g., LOF) are often sensitive to nonstationarity and cannot effectively exploit temporal dependency across intra-day time slots, resulting in coarse alarms and high false positives. To address these issues, this paper proposes a dual-side LSTM-based participant-level anomaly detection method. Multimodal features are constructed from 24 intra-day measurements, a daily total, FFT-derived frequency components, and calendar context. A zero-padding and masking mechanism is introduced to handle daily changes in the number of load participants without contaminating model training. A dual-layer LSTM with a 16-d participant embedding learns participant-specific temporal patterns, and a rule combining relative-error screening with confidence verification produces participant-level anomaly positioning and abnormal time-slot identification. Experiments on one-month desensitized provincial-grid data (242 generators and 78k--85k loads) achieve 98.3% F1-score (96.7% recall, 100.0% precision), with 97.2% positioning accuracy and 96.8% time-slot recognition accuracy, substantially outperforming statistical and LOF baselines. Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 16 Apr, 2026 Reviews received at journal 14 Apr, 2026 Reviews received at journal 13 Apr, 2026 Reviews received at journal 10 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers agreed at journal 04 Apr, 2026 Reviews received at journal 03 Apr, 2026 Reviewers agreed at journal 03 Apr, 2026 Reviewers agreed at journal 02 Apr, 2026 Reviewers invited by journal 02 Apr, 2026 Editor assigned by journal 02 Apr, 2026 Editor invited by journal 31 Mar, 2026 Submission checks completed at journal 30 Mar, 2026 First submitted to journal 30 Mar, 2026 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-9206232","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":617969046,"identity":"1b0a743b-bd3e-4ec9-888a-a4c1272c9dae","order_by":0,"name":"Qianya He","email":"","orcid":"","institution":"Guangdong Power Exchange Center Co.","correspondingAuthor":false,"prefix":"","firstName":"Qianya","middleName":"","lastName":"He","suffix":""},{"id":617969047,"identity":"c2f0bbcf-7980-4d80-b17b-9ce8123dbee3","order_by":1,"name":"Qi Liu","email":"","orcid":"","institution":"Guangdong Power Exchange Center Co.","correspondingAuthor":false,"prefix":"","firstName":"Qi","middleName":"","lastName":"Liu","suffix":""},{"id":617969048,"identity":"08cd5e56-e086-46fb-b644-b9871e8d5b11","order_by":2,"name":"Xueliang Gong","email":"","orcid":"","institution":"Guangdong Power Exchange Center Co.","correspondingAuthor":false,"prefix":"","firstName":"Xueliang","middleName":"","lastName":"Gong","suffix":""},{"id":617969049,"identity":"6488e06e-0ae6-4e8f-a054-f43467bf5def","order_by":3,"name":"Jiaxun Liu","email":"","orcid":"","institution":"Guangdong Power Exchange Center Co.","correspondingAuthor":false,"prefix":"","firstName":"Jiaxun","middleName":"","lastName":"Liu","suffix":""},{"id":617969050,"identity":"e88a93b5-a517-4e97-af62-08440a4a2c84","order_by":4,"name":"Liming Yao","email":"","orcid":"","institution":"Guangdong Power Exchange Center Co.","correspondingAuthor":false,"prefix":"","firstName":"Liming","middleName":"","lastName":"Yao","suffix":""},{"id":617969051,"identity":"7e928498-fd0a-41d2-9ec2-799f809c4393","order_by":5,"name":"Tianze Yu","email":"","orcid":"","institution":"Beijing Tsintergy Technology Co.","correspondingAuthor":false,"prefix":"","firstName":"Tianze","middleName":"","lastName":"Yu","suffix":""},{"id":617969052,"identity":"ce9336ee-c7cb-41bd-bdcd-fcdf8b34a477","order_by":6,"name":"Tong Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAzklEQVRIiWNgGAWjYBACxvkP2z98MJBg5mdvIFILc0NyG+OMCgt2yZ4DRGphb0hvY+Y4U8FvcCOBSC28DQfbHjO2SUgz3Hy88QZDjU00QS2SjY3txoVtEsaMs9OKLRiOpeU2ENJi2MzYID2zTSKZWTrHTIKx4TBhLfbHgFp42yTq2yTPEKmFsYexTZrnjAQzjwQPsVpmMDYbzqiQYJbgAfolgRi/MM5gf/jgg0Eds/3xwxtvfKixIawFGRhIJJCiHKKFVB2jYBSMglEwMgAAqyY+RJ7GngkAAAAASUVORK5CYII=","orcid":"","institution":"Beijing Tsintergy Technology Co.","correspondingAuthor":true,"prefix":"","firstName":"Tong","middleName":"","lastName":"Zhao","suffix":""}],"badges":[],"createdAt":"2026-03-24 03:38:28","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9206232/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9206232/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106725924,"identity":"53b87238-e898-4b89-86cb-4b877c8e0a70","added_by":"auto","created_at":"2026-04-12 18:34:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":319877,"visible":true,"origin":"","legend":"","description":"","filename":"20260330ParticipantLevelAnomalyDetectionforGenerationandLoadDataUsingDualSideLSTMsScientificReports.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9206232/v1_covered_b51f8f6b-a741-4af1-aa2d-97fb36df6b5c.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Participant-Level Anomaly Detection for Generation and Load Data Using Dual-Side LSTMs","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-9206232/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9206232/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Reliable anomaly detection for generation and load metering data is essential to market settlement. In practice, anomalies are diverse and sparse, and the load side contains a large and time-varying number of participants, which makes fine-grained participant-level localization difficult. Conventional statistical thresholding and generic outlier detectors (e.g., LOF) are often sensitive to nonstationarity and cannot effectively exploit temporal dependency across intra-day time slots, resulting in coarse alarms and high false positives. To address these issues, this paper proposes a dual-side LSTM-based participant-level anomaly detection method. Multimodal features are constructed from 24 intra-day measurements, a daily total, FFT-derived frequency components, and calendar context. A zero-padding and masking mechanism is introduced to handle daily changes in the number of load participants without contaminating model training. A dual-layer LSTM with a 16-d participant embedding learns participant-specific temporal patterns, and a rule combining relative-error screening with confidence verification produces participant-level anomaly positioning and abnormal time-slot identification. Experiments on one-month desensitized provincial-grid data (242 generators and 78k--85k loads) achieve 98.3\\% F1-score (96.7\\% recall, 100.0\\% precision), with 97.2\\% positioning accuracy and 96.8\\% time-slot recognition accuracy, substantially outperforming statistical and LOF baselines.","manuscriptTitle":"Participant-Level Anomaly Detection for Generation and Load Data Using Dual-Side LSTMs","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-08 22:32:15","doi":"10.21203/rs.3.rs-9206232/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-16T14:13:06+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-14T06:31:56+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-13T16:29:42+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-10T09:37:21+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"32864285258035218809939157492349379681","date":"2026-04-08T04:35:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"109836332158652213130611520273538750679","date":"2026-04-04T09:29:08+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-03T06:50:51+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"301432673410688760767219208794257330131","date":"2026-04-03T04:26:40+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"79749619107150706679801402409102896002","date":"2026-04-03T03:06:41+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-04-03T03:01:30+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-04-03T02:59:00+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2026-03-31T13:07:25+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-30T09:32:34+00:00","index":"","fulltext":""},{"type":"submitted","content":"Scientific Reports","date":"2026-03-30T09:23:39+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"scientific-reports","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"scirep","sideBox":"Learn more about [Scientific Reports](http://www.nature.com/srep/)","snPcode":"","submissionUrl":"","title":"Scientific Reports","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Scientific Reports","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"70ebe211-2704-45fc-a81d-86d69cae5093","owner":[],"postedDate":"April 8th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[{"id":65759774,"name":"Physical sciences/Engineering"},{"id":65759775,"name":"Physical sciences/Mathematics and computing"}],"tags":[],"updatedAt":"2026-05-18T10:09:07+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-08 22:32:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9206232","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9206232","identity":"rs-9206232","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}