{"paper_id":"16decda4-3ef1-431a-a5c4-58b894ef07b6","body_text":"MKAN-iTransformer: Interpretable Multi-Scale Temporal Modeling with Attention Mechanisms for Photovoltaic Power Prediction | 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 MKAN-iTransformer: Interpretable Multi-Scale Temporal Modeling with Attention Mechanisms for Photovoltaic Power Prediction Linjie Liu, Min Liu, Zhuangchou Han, HaiQiang Zhao This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7268148/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 24 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted 30 You are reading this latest preprint version Abstract Accurate photovoltaic (PV) power forecasting is vital for integrating renewable energy into power grids, yet remains challenging due to complex, multi-scale dependencies and seasonal variability. We propose MKAN-iTransformer, a novel hybrid model combining the Multi-Scale Kolmogorov-Arnold Network (MKAN) for interpretable, multi-scale temporal feature extraction with the iTransformer module for variable-wise attention and inter-variable dependency modeling.Extensive experiments on seasonal photovoltaic datasets from the Chinese State Grid Renewable Energy Generation Forecasting Competition demonstrate that MKAN-iTransformer consistently outperforms state-of-the-art baselines, including LSTM, GRU, BiLSTM, Transformer, xLSTM, and iTransformer. Specifically, it reduces Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) by up to 18.7%, 9.8%, and 16.7% in spring; 8.5% (MSE) and 10.5% (MAE) in summer; 31.2%, 12.1%, and 25.4% in autumn; and 78.5%, 53.6%, and 71.4% in winter.Compared to advanced KAN/MKAN-based models, improvements reach up to 85.5% across error metrics, with increases in the Coefficient of Determination ($R^2$) of up to 12.7%.These results demonstrate MKAN-iTransformer’s superior accuracy, robustness, and interpretability across all seasons, making it highly suitable for practical multivariate time series forecasting in energy management. Physical sciences/Energy science and technology Physical sciences/Engineering Physical sciences/Mathematics and computing Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 24 Feb, 2026 Read the published version in Scientific Reports → Version 1 posted Editorial decision: Revision requested 16 Jan, 2026 Reviewers agreed at journal 15 Jan, 2026 Reviews received at journal 15 Jan, 2026 Reviewers agreed at journal 15 Jan, 2026 Reviewers agreed at journal 15 Jan, 2026 Reviewers agreed at journal 15 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviewers agreed at journal 14 Jan, 2026 Reviews received at journal 14 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviewers agreed at journal 13 Jan, 2026 Reviews received at journal 28 Sep, 2025 Reviewers agreed at journal 21 Sep, 2025 Reviewers agreed at journal 24 Aug, 2025 Reviewers invited by journal 08 Aug, 2025 Editor invited by journal 08 Aug, 2025 Editor assigned by journal 04 Aug, 2025 Submission checks completed at journal 02 Aug, 2025 First submitted to journal 01 Aug, 2025 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-7268148\",\"acceptedTermsAndConditions\":true,\"allowDirectSubmit\":false,\"archivedVersions\":[],\"articleType\":\"Article\",\"associatedPublications\":[],\"authors\":[{\"id\":497801799,\"identity\":\"99ff2098-17fa-4ce4-a6d5-a7bc8a5ca5e4\",\"order_by\":0,\"name\":\"Linjie Liu\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Guizhou University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Linjie\",\"middleName\":\"\",\"lastName\":\"Liu\",\"suffix\":\"\"},{\"id\":497801800,\"identity\":\"cfe7ca66-45fe-4bec-ad72-97a0a7e1cbd1\",\"order_by\":1,\"name\":\"Min Liu\",\"email\":\"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA0ElEQVRIiWNgGAWjYLCCBwYMchAWG7FaEgwYjEnVwsCQ2EC0Fn72BtYNCQWH0+f7nzFg+FB2mIF/dgN+LZI9B9huJBgczt144IwB44xzhxkk7hzAr8XgRgJUS2OPATNv22EGA4kE/Frs7z8Aa0k3bOYxYP5LjBYDCQawlgR5NqAWRmK0SJxJbANqSTfcwMNWcLDnXDqPxA0CWvjbDx+78eGPtbx8/+GND36UWcvxzyCghYGBsQHiwgMMDEDEwENIPQLINxCvdhSMglEwCkYYAAD2OEJ0bYyPXwAAAABJRU5ErkJggg==\",\"orcid\":\"\",\"institution\":\"Guizhou University\",\"correspondingAuthor\":true,\"prefix\":\"\",\"firstName\":\"Min\",\"middleName\":\"\",\"lastName\":\"Liu\",\"suffix\":\"\"},{\"id\":497801801,\"identity\":\"f9c8bcea-a873-4a5c-b3bc-40e620cd8883\",\"order_by\":2,\"name\":\"Zhuangchou Han\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Guizhou University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"Zhuangchou\",\"middleName\":\"\",\"lastName\":\"Han\",\"suffix\":\"\"},{\"id\":497801802,\"identity\":\"b02cdb25-5a05-4d28-8f63-2425705f00e7\",\"order_by\":3,\"name\":\"HaiQiang Zhao\",\"email\":\"\",\"orcid\":\"\",\"institution\":\"Guizhou University\",\"correspondingAuthor\":false,\"prefix\":\"\",\"firstName\":\"HaiQiang\",\"middleName\":\"\",\"lastName\":\"Zhao\",\"suffix\":\"\"}],\"badges\":[],\"createdAt\":\"2025-08-01 06:53:22\",\"currentVersionCode\":1,\"declarations\":\"\",\"doi\":\"10.21203/rs.3.rs-7268148/v1\",\"doiUrl\":\"https://doi.org/10.21203/rs.3.rs-7268148/v1\",\"draftVersion\":[],\"editorialEvents\":[{\"content\":\"https://doi.org/10.1038/s41598-026-39797-6\",\"type\":\"published\",\"date\":\"2026-02-24T15:58:42+00:00\"}],\"editorialNote\":\"\",\"failedWorkflow\":false,\"files\":[{\"id\":103765852,\"identity\":\"ff249c78-f417-428b-a66a-3c597bd9006b\",\"added_by\":\"auto\",\"created_at\":\"2026-03-02 16:10:21\",\"extension\":\"pdf\",\"order_by\":1,\"title\":\"\",\"display\":\"\",\"copyAsset\":false,\"role\":\"manuscript-pdf\",\"size\":5269349,\"visible\":true,\"origin\":\"\",\"legend\":\"\",\"description\":\"\",\"filename\":\"MKANiTransformer2.pdf\",\"url\":\"https://assets-eu.researchsquare.com/files/rs-7268148/v1_covered_0168dc50-4b29-4d94-bc7b-0a0613ab2158.pdf\"}],\"financialInterests\":\"No competing interests reported.\",\"formattedTitle\":\"MKAN-iTransformer: Interpretable Multi-Scale Temporal Modeling with Attention Mechanisms for Photovoltaic Power Prediction\",\"fulltext\":[],\"fulltextSource\":\"\",\"fullText\":\"\",\"funders\":[],\"hasAdminPriorityOnWorkflow\":false,\"hasManuscriptDocX\":false,\"hasOptedInToPreprint\":true,\"hasPassedJournalQc\":\"\",\"hasAnyPriority\":false,\"hideJournal\":false,\"highlight\":\"\",\"institution\":\"\",\"isAcceptedByJournal\":true,\"isAuthorSuppliedPdf\":true,\"isDeskRejected\":\"\",\"isHiddenFromSearch\":false,\"isInQc\":false,\"isInWorkflow\":false,\"isPdf\":true,\"isPdfUpToDate\":true,\"isWithdrawnOrRetracted\":false,\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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-7268148/v1\",\"lastPublishedDoiUrl\":\"https://doi.org/10.21203/rs.3.rs-7268148/v1\",\"license\":{\"name\":\"CC BY 4.0\",\"url\":\"https://creativecommons.org/licenses/by/4.0/\"},\"manuscriptAbstract\":\"Accurate photovoltaic (PV) power forecasting is vital for integrating renewable energy into power grids, yet remains challenging due to complex, multi-scale dependencies and seasonal variability. We propose MKAN-iTransformer, a novel hybrid model combining the Multi-Scale Kolmogorov-Arnold Network (MKAN) for interpretable, multi-scale temporal feature extraction with the iTransformer module for variable-wise attention and inter-variable dependency modeling.Extensive experiments on seasonal photovoltaic datasets from the Chinese State Grid Renewable Energy Generation Forecasting Competition demonstrate that MKAN-iTransformer consistently outperforms state-of-the-art baselines, including LSTM, GRU, BiLSTM, Transformer, xLSTM, and iTransformer. Specifically, it reduces Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE) by up to 18.7\\\\%, 9.8\\\\%, and 16.7\\\\% in spring; 8.5\\\\% (MSE) and 10.5\\\\% (MAE) in summer; 31.2\\\\%, 12.1\\\\%, and 25.4\\\\% in autumn; and 78.5\\\\%, 53.6\\\\%, and 71.4\\\\% in winter.Compared to advanced KAN/MKAN-based models, improvements reach up to 85.5\\\\% across error metrics, with increases in the Coefficient of Determination ($R^2$) of up to 12.7\\\\%.These results demonstrate MKAN-iTransformer’s superior accuracy, robustness, and interpretability across all seasons, making it highly suitable for practical multivariate time series forecasting in energy management.\",\"manuscriptTitle\":\"MKAN-iTransformer: Interpretable Multi-Scale Temporal Modeling with Attention Mechanisms for Photovoltaic Power Prediction\",\"msid\":\"\",\"msnumber\":\"\",\"nonDraftVersions\":[{\"code\":1,\"date\":\"2025-08-14 06:11:08\",\"doi\":\"10.21203/rs.3.rs-7268148/v1\",\"editorialEvents\":[{\"type\":\"communityComments\",\"content\":0},{\"type\":\"decision\",\"content\":\"Revision requested\",\"date\":\"2026-01-16T05:49:20+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"87017739111727978664980150267421740477\",\"date\":\"2026-01-16T01:24:51+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2026-01-15T15:17:07+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"338474972024091741820489007566455401180\",\"date\":\"2026-01-15T13:34:37+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"158840135008633299504182814509901682557\",\"date\":\"2026-01-15T12:47:25+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"133984581996990902533002859430011530991\",\"date\":\"2026-01-15T12:07:52+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"284396958491265842795933421914818657036\",\"date\":\"2026-01-14T15:20:15+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"94792747556551962444426519399847581990\",\"date\":\"2026-01-14T06:20:08+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"103808893147305370212875850374861486202\",\"date\":\"2026-01-14T06:17:35+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2026-01-14T06:08:13+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"328365417316281450216125788661921061527\",\"date\":\"2026-01-14T03:35:56+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"134820069151838384813572551291765577887\",\"date\":\"2026-01-14T02:25:21+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"95170590690555251654486491504196794375\",\"date\":\"2026-01-14T01:26:37+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"124105618955421969705141697487402496606\",\"date\":\"2026-01-13T17:50:34+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"181748097982280572687903636971984316976\",\"date\":\"2026-01-13T14:31:57+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"67963484661079085953231703475972566543\",\"date\":\"2026-01-13T13:27:13+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"293358923822642612222561680316305945089\",\"date\":\"2026-01-13T13:18:20+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"23124361178583891535296124232740021505\",\"date\":\"2026-01-13T13:07:36+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"220325809314288983254279126036807792075\",\"date\":\"2026-01-13T12:53:41+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"84545218241147709838594067826258733836\",\"date\":\"2026-01-13T12:51:55+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"183139811334887684181144647131125236867\",\"date\":\"2026-01-13T12:00:50+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"174597274528919306622797544360945060327\",\"date\":\"2026-01-13T12:00:29+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"editorInvitedReview\",\"content\":\"\",\"date\":\"2025-09-28T12:52:30+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"111944990905743574074464915406540895961\",\"date\":\"2025-09-22T00:10:34+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewerAgreed\",\"content\":\"248785623494620159808911509772904308649\",\"date\":\"2025-08-24T14:12:25+00:00\",\"index\":\"hide\",\"fulltext\":\"\"},{\"type\":\"reviewersInvited\",\"content\":\"\",\"date\":\"2025-08-08T15:49:08+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorInvited\",\"content\":\"\",\"date\":\"2025-08-08T05:41:38+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"editorAssigned\",\"content\":\"\",\"date\":\"2025-08-04T06:47:20+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"checksComplete\",\"content\":\"\",\"date\":\"2025-08-02T09:44:38+00:00\",\"index\":\"\",\"fulltext\":\"\"},{\"type\":\"submitted\",\"content\":\"Scientific Reports\",\"date\":\"2025-08-01T06:42:23+00:00\",\"index\":\"\",\"fulltext\":\"\"}],\"status\":\"published\",\"journal\":{\"display\":true,\"email\":\"info@researchsquare.com\",\"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\":\"727b127e-eb9a-480f-8720-ebe78ad29d55\",\"owner\":[],\"postedDate\":\"August 14th, 2025\",\"published\":true,\"recentEditorialEvents\":[],\"rejectedJournal\":[],\"revision\":\"\",\"amendment\":\"\",\"status\":\"published-in-journal\",\"subjectAreas\":[{\"id\":52883882,\"name\":\"Physical sciences/Energy science and technology\"},{\"id\":52883883,\"name\":\"Physical sciences/Engineering\"},{\"id\":52883884,\"name\":\"Physical sciences/Mathematics and computing\"}],\"tags\":[],\"updatedAt\":\"2026-03-02T16:06:30+00:00\",\"versionOfRecord\":{\"articleIdentity\":\"rs-7268148\",\"link\":\"https://doi.org/10.1038/s41598-026-39797-6\",\"journal\":{\"identity\":\"scientific-reports\",\"isVorOnly\":false,\"title\":\"Scientific Reports\"},\"publishedOn\":\"2026-02-24 15:58:42\",\"publishedOnDateReadable\":\"February 24th, 2026\"},\"versionCreatedAt\":\"2025-08-14 06:11:08\",\"video\":\"\",\"vorDoi\":\"10.1038/s41598-026-39797-6\",\"vorDoiUrl\":\"https://doi.org/10.1038/s41598-026-39797-6\",\"workflowStages\":[]},\"version\":\"v1\",\"identity\":\"rs-7268148\",\"journalConfig\":\"researchsquare\"},\"__N_SSP\":true},\"page\":\"/article/[identity]/[[...version]]\",\"query\":{\"redirect\":\"/article/rs-7268148\",\"identity\":\"rs-7268148\",\"version\":[\"v1\"]},\"buildId\":\"8U1c8b4HqxoKbykW_rLl7\",\"isFallback\":false,\"isExperimentalCompile\":false,\"dynamicIds\":[84888],\"gssp\":true,\"scriptLoader\":[]}","source_license":"CC-BY-4.0","license_restricted":false}