[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119107-en":3,"doc-seo-119107-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},119107,2336464648322,"Aria","https://ap-avatar.wpscdn.com/avatar/2200025388227c56fec?_k=1778556882303663488",8,"Research & Report","Power Failure Cascade Prediction using Machine Learning - Thesis","Predicting power failure cascades triggered by branch failures enables earlier assessment of grid risk and system behavior. The thesis introduces multiple flow-free machine learning models, including support vector machines, naive Bayes classifiers, and logistic regression, to forecast generation-level grid states from an initial contingency. It also proposes a graph neural network model that predicts cascades using initial contingencies and power injection values. Models are trained on simulated cascade sequence data, evaluated with metrics for failure size, final grid state, and failure timing, and benchmarked against literature influence models. Results show consistent accuracy gains and near two-orders-of-magnitude computational speedup.","Power Failure Cascade Prediction using Machine  \nLearning  \nby  \nSathwik P. Chadaga  \nDual Degree (B.Tech. and M.Tech.), Electrical Engineering, Indian Institute of Technology Madras, 2020  \nSubmitted to the Department of Aeronautics and Astronautics in partial fulfillment of the requirements for the degree of  \nMasters of Science in Aeronautics and Astronautics  \nat the  \nMASSACHUSETTS INSTITUTE OF TECHNOLOGY  \nSeptember 2023  \n© 2023 Sathwik P. Chadaga. All rights reserved.  \nThe author hereby grants to MIT a nonexclusive, worldwide, irrevocable, royalty-free license to exercise any and all rights under copyright, including to reproduce, preserve, distribute and publicly display copies of the thesis, or release the thesis under an open-access license.  \nAuthored by: Sathwik P. Chadaga  \nDepartment of Aeronautics and Astronautics  \nAugust 8, 2023  \nCertified by: Eytan H. Modiano  \nR.C. Maclaurin Professor of Aeronautics and Astronautics Thesis Supervisor  \nAccepted by: Jonathan P. How  \nR. C. Maclaurin Professor of Aeronautics and Astronautics Chair, Graduate Program Committee  \n2  \nPower Failure Cascade Prediction using Machine Learning  \nby  \nSathwik P. Chadaga  \nSubmitted to the Department of Aeronautics and Astronautics on August 8, 2023, in partial fulfillment of the requirements for the degree of  \nMasters of Science in Aeronautics and Astronautics  \nAbstract  \nWe consider the problem of predicting power failure cascades due to branch failures. We propose several flow-free models using machine learning techniques like support vector machines, naive Bayes classifiers, and logistic regression. These models predict the grid states at every generation of a cascade process given the initial contingency. Further, we also propose a model based on graph neural networks (GNNs) that predicts cascades from the initial contingency and power injection values. We train the proposed models using a cascade sequence data pool generated from simulations. We then evaluate our models at various levels of granularity. We present several error metrics that gauge the models’ ability to predict the failure size, the final grid state, and the failure time steps of each branch within the cascade. We benchmark the proposed models against the influence model proposed in the literature. We show that the proposed machine learning models outperform the influence models under every metric. We also show that the graph neural network model, in addition to being generic over randomly scaled power injection values, outperforms multiple influence models that are built specifically for their corresponding loading profiles. Finally, we show that the proposed models reduce the computational time by almost two orders of magnitude.  \nThesis Supervisor: Eytan H. Modiano  \nTitle: R.C. Maclaurin Professor of Aeronautics and Astronautics  \n4  \nAcknowledgments  \nI want to thank my advisor Prof. Eytan Modiano for his guidance and constant support. His insights and intuitions have been crucial in the formulation and development of this work. I also want to thank my colleagues Xinyu Wu and Dr. Dan Wu. Their works on the influence model and their implementation of the cascading failure simulator, with which I generate the data required to train my models, have been vital to my thesis. I am also grateful to my undergraduate advisors Prof. David Koilpillai and Prof. Nambi Seshadri who inspired me to be a researcher.  \nThis work was supported by NSF grants CNS-1735463 and CNS-2106268, and by a research award from the C3 .ai Digital Transformation Institute.  \nI would like to thank my colleagues at the Communications and Networking Research Group-Bai Liu, Vishrant Tripathi, Chirag Rao, Nick Jones, Jerrod Wigmore, Quang Nguyen, Vallabh Ramakanth, and Xinzhe Fu-for creating such a supportive and friendly atmosphere in the lab. I also want to thank my friends Akshay Subramanian and Avik Pal for the useful discussions on graph neural networks that initially encouraged me to exp","cbCaidgvubWIefBS","https://ap.wps.com/l/cbCaidgvubWIefBS","pdf",811328,1,70,"English","en",105,"# Contents\n## 1 Introduction\n## 1.1 Motivation\n## 1.2 Related Work\n## 1.3 Problem Formulation\n## 1.4 Contributions\n## 1.5 Outline\n## 2 Machine Learning Techniques for Failure Cascade Prediction","[{\"question\":\"What problem does the thesis address?\",\"answer\":\"The thesis addresses predicting power failure cascades caused by branch failures and estimating how the grid evolves during a cascade.\"},{\"question\":\"Which machine learning methods are proposed?\",\"answer\":\"It proposes flow-free models using support vector machines, naive Bayes classifiers, and logistic regression, and it introduces an additional graph neural network model based on power injection and initial contingency.\"},{\"question\":\"How are the models evaluated and how do they compare to prior work?\",\"answer\":\"The models are trained on simulation-generated cascade sequence data and evaluated using error metrics for failure size, final grid state, and branch failure timing. They outperform influence models across every metric and the GNN model remains strong under randomly scaled power injection values.\"}]","Power Failure Cascade Prediction using Machine Learning - Thesis | PDF",1785722425,176,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"power-failure-cascade-prediction-using-machine-learning-thesis","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/power-failure-cascade-prediction-using-machine-learning-thesis/119107/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the thesis address?","Question",{"text":75,"@type":76},"The thesis addresses predicting power failure cascades caused by branch failures and estimating how the grid evolves during a cascade.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning methods are proposed?",{"text":80,"@type":76},"It proposes flow-free models using support vector machines, naive Bayes classifiers, and logistic regression, and it introduces an additional graph neural network model based on power injection and initial contingency.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the models evaluated and how do they compare to prior work?",{"text":84,"@type":76},"The models are trained on simulation-generated cascade sequence data and evaluated using error metrics for failure size, final grid state, and branch failure timing. They outperform influence models across every metric and the GNN model remains strong under randomly scaled power injection values.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":21,"slug":103},"Exam","exam",{"id":105,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":105,"slug":137},19,"General","general"]