[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126371-en":3,"doc-seo-126371-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126371,962085564549,"Genevieve","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Probabilistic and Explainable Machine Learning for Tabular Power Grid Data","Modeling power grid frequency stability is increasingly difficult with the growing penetration of renewable energy sources. The work compares deterministic machine learning models and introduces a probabilistic extension that captures uncertainty instead of returning only point estimates. Using TabNet and TabNetProba, the study evaluates performance against XGBoost and NGBoost and applies explainable AI to reveal which operational factors drive stability and where uncertainty originates across Continental Europe and the Nordic region. Results show TabNetProba matches state-of-the-art performance while providing reliable uncertainty estimates.","Probabilistic and Explainable Machine Learning for Tabular  \nPower Grid Data  \nAlexandra Nikoltchovska  \nKarlsruhe Institute of Technology Eggenstein-Leopoldshafen, Germany [alexandra.nikoltchovska@kit.edu](alexandra.nikoltchovska@kit.edu)  \nSebastian Pütz  \nKarlsruhe Institute of Technology Eggenstein-Leopoldshafen, Germany [sebastian.puetz@kit.edu](sebastian.puetz@kit.edu)  \nXiao Li  \nKarlsruhe Institute of Technology Eggenstein-Leopoldshafen, Germany [xiao.li@kit.edu](xiao.li@kit.edu)  \nVeit Hagenmeyer  \nKarlsruhe Institute of Technology Eggenstein-Leopoldshafen, Germany [veit.hagenmeyer@kit.edu](veit.hagenmeyer@kit.edu)  \nAbstract  \nModeling power grid frequency stability is becoming increasingly challenging due to the integration of renewable energy sources. Machine learning approaches, such as gradient-boosted trees, have shown promise in analyzing the complex characteristics of power systems. However, these models are inherently deterministic, providing only point estimates. Meanwhile, the task of capturing the underlying uncertainty, particularly through (deep) probabilistic models, is still underexplored, despite its potential to better account for the stochastic nature of power grid dynamics. In this paper, we first compare the performance of TabNet, a deep learning architecture designed for tabular data, to XGBoost for modeling power grid frequency stability. We then present TabNetProba: a probabilistic extension of TabNet, that enables uncertainty-aware estimates comparable to NGBoost. Using these (trained) models, we leverage explainable artificial intelligence (XAI) to analyze the drivers influencing grid stability and identify sources of uncertainty in two major European synchronous areas: Continental Europe and the Nordic region. Our results demonstrate that TabNetProba achieves competitive performance with state-of-the-art methods while providing reliable uncertainty estimates. We find that load and conventional generation ramps, as well as forecast errors, are the key quantities for modeling and explaining mean stability indicators in both synchronous areas. In Continental Europe, renewable generation emerges as a key factor in explaining model uncertainty, while in the Nordic region, load and generation features dominate uncertainty estimation, allowing for more reliable and interpretable stability estimates for modern power systems.  \nCCS Concepts  \n• Computing methodologies → Artificial intelligence; Machine learning; • Applied computing → Engineering.  \nThis work is licensed under a Creative Commons Attribution 4 .0 International License.  \nE-ENERGY’25, Rotterdam, Netherlands  \n© 2025 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-1125-1/25/06  \n[https://doi.org/10.1145/3679240.3734623](https://doi.org/10.1145/3679240.3734623)  \nBenjamin Schäfer  \nKarlsruhe Institute of Technology Eggenstein-Leopoldshafen, Germany [benjamin.schaefer@kit.edu](benjamin.schaefer@kit.edu)  \nKeywords  \npower grid frequency stability, probabilistic machine learning, explainable artificial intelligence, tabular data, deep learning, TabNetProba  \nACM Reference Format:  \nAlexandra Nikoltchovska, Sebastian Pütz, Xiao Li, Veit Hagenmeyer, and Benjamin Schäfer. 2025. Probabilistic and Explainable Machine Learning for Tabular Power Grid Data. In The 16th ACM International Conference on Future and Sustainable Energy Systems (E-ENERGY’25), June 17–20, 2025, Rotterdam, Netherlands. ACM, New York, NY, USA, 19 pages.  \n[https://doi.org/10.1145/3679240.3734623](https://doi.org/10.1145/3679240.3734623)  \n1 Introduction  \nThe power grid is fundamental to modern society, enabling the reliable delivery of electrical energy to homes, industries, and critical infrastructures. A key challenge in operating this complex system is maintaining stability-keeping the system within operational limits and ensuring it returns to a steady state after disturbances. While stability encompasses many aspects, including voltage levels and phase an","cbCaicyrRl0D6oZK","https://ap.wps.com/l/cbCaicyrRl0D6oZK","pdf",1963661,4,1,19,"English","en",105,"# Introduction\n## Power grid stability and frequency as key indicators\n## Tabular data and limitations of traditional modeling\n## Machine learning for tabular stability analysis\n## Probabilistic and explainable modeling approach","[{\"question\":\"Why is probabilistic modeling important for power grid frequency stability?\",\"answer\":\"Frequency stability changes with renewable integration, and stochastic dynamics make uncertainty crucial. Probabilistic models provide uncertainty-aware estimates rather than only point predictions.\"},{\"question\":\"How does TabNetProba relate to TabNet and NGBoost?\",\"answer\":\"TabNetProba is a probabilistic extension of TabNet, enabling uncertainty-aware estimates comparable to NGBoost by modeling distribution parameters.\"},{\"question\":\"Which factors are most influential for mean stability indicators in the studied regions?\",\"answer\":\"Load and conventional generation ramps, together with forecast errors, are key for modeling mean stability indicators in both synchronous areas. Renewable generation is a main source of model uncertainty in Continental Europe, while load and generation features dominate uncertainty estimation in the Nordic region.\"}]","Probabilistic and Explainable Machine Learning for Tabular Power Grid Data | PDF",1785904711,48,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"probabilistic-and-explainable-machine-learning-for-tabular-power-grid-data","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,52],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":51},"https://docshare.wps.com/document/research-report/",3,{"item":53,"name":13,"@type":44,"position":20},"https://docshare.wps.com/document/probabilistic-and-explainable-machine-learning-for-tabular-power-grid-data/126371/",{"url":53,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-24","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is probabilistic modeling important for power grid frequency stability?","Question",{"text":76,"@type":77},"Frequency stability changes with renewable integration, and stochastic dynamics make uncertainty crucial. Probabilistic models provide uncertainty-aware estimates rather than only point predictions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does TabNetProba relate to TabNet and NGBoost?",{"text":81,"@type":77},"TabNetProba is a probabilistic extension of TabNet, enabling uncertainty-aware estimates comparable to NGBoost by modeling distribution parameters.",{"name":83,"@type":74,"acceptedAnswer":84},"Which factors are most influential for mean stability indicators in the studied regions?",{"text":85,"@type":77},"Load and conventional generation ramps, together with forecast errors, are key for modeling mean stability indicators in both synchronous areas. Renewable generation is a main source of model uncertainty in Continental Europe, while load and generation features dominate uncertainty estimation in the Nordic region.","https://schema.org",{"og:url":53,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":53},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},"General","general"]