[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126877-en":3,"doc-seo-126877-105":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},126877,1099523885336,"Violet","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning based Post Event Analysis for Cybersecurity of Cyber-Physical System - paper","As ICT equipment becomes integrated into power systems, cybersecurity risks increase, especially with the shift from traditional hardwired substations to digital substations and SCADA communications. This work introduces a machine-learning-based post event analysis framework to distinguish power system faults from cyber-attacks. An artificial neural network and other ML models are trained using transient fault measurements and cyber-attack data collected from substation scenarios. The approach identifies ten fault types and the event location, while supporting evaluation under N-1 contingency conditions.","Machine Learning based Post Event Analysis for Cybersecurity of Cyber-Physical System  \nKuchan Park, Junho Hong, Wencong Su  \nDepartment of Electrical and Computer Engineering University of Michigan-Dearborn  \nDearborn, USA  \n[kuchan@umich.edu](kuchan@umich.edu), [jhwr@umich.edu](jhwr@umich.edu), [wencong@umich.edu](wencong@umich.edu)  \nHyoJong Lee  \nNew Technology DTE Energy Detroit, MI, USA [hyojong.lee@dteenergy.com](hyojong.lee@dteenergy.com)  \narXiv :2311 . 13488v2 [ ee ss . SY] 7 Mar 2024  \nAbstract—As Information and Communication Technology (ICT) equipment continues to be integrated into power systems, issues related to cybersecurity are increasingly emerging. Particularly noteworthy is the transition to digital substations, which is shifting operations from traditional hardwired-based systems to communication-based Supervisory Control and Data Acquisition (SCADA) system operations. These changes in the power system have increased the vulnerability of the system to cyber-attacks and emphasized its importance. This paper proposes a machine learning (ML) based post event analysis of the power system in order to respond to these cybersecurity issues. An artificial neural network (ANN) and other ML models are trained using transient fault measurements and cyber-attack data on substations. The trained models can successfully distinguish between power system faults and cyber-attacks. Furthermore, the results of the proposed ML-based methods can also identify 10 different fault types and the location where the event occurred.  \nIndex Terms—Post event analysis, Deep-learning based cyberphysical faults detection, Transmission system, Cyber-attack  \nI. INTRODUCTION  \nIn the power system architecture, the transmission network plays a pivotal role in efficient electricity delivery with minimized losses. Protecting this transmission infrastructure is thus crucial for maintaining the overall stability and reliability of the power system [1] . Faults in the power system can arise from various factors, such as heavy snowfall, lightning, earthquakes, or animal interference. Inadequate or delayed responses to these incidents can lead to extended power outages, irreversible equipment damage, and significant economic repercussions. The implications of such damage extend beyond the transmission system, impacting both power generation and distribution sectors. With the evolution of the power system towards a more distributed framework as opposed to the traditional centralized model, the system dynamics have become increasingly complex. This complexity introduces heightened vulnerabilities and necessitates rapid response mechanisms during emergencies. The deployment of AI-based technologies for fault and cyber-attack detection, enabled by recent advancements in big data storage and processing capabilities, is essential to address these challenges effectively.  \nThere are several recent related works about this field. The works of [2] developed artificial intelligence based intrusion detection system. Sampled value (SV) message of IEC61850  \ncommunication protocol and penetration of renewable energy were considered. A cyber-attack detection technology for Transmission Protective Relays based on deep learning techniques has been proposed by [3] . The authors of [4] presents a method that involves preprocessing power system data to convert it into image-like formats, enabling the use of Convolutional Neural Networks (CNN) to detect faults and cyber attacks. This innovative approach leverages the powerful image processing capabilities of CNNs to analyze and interpret complex power system data. However, such studies have faced challenges in accurately detecting the types of faults and determining their locations within power systems. Additionally, being primarily focused on relays, these research efforts are limited in scope. As a result, applying these methods to the broader context of the entire power system presents difficulties, highlighting ","cbCaimrOZ4TrbvIY","https://ap.wps.com/l/cbCaimrOZ4TrbvIY","pdf",671905,1,5,"English","en",105,"# Abstract\n# Introduction\n## Motivation and problem context\n## Related work and limitations\n# Proposed ML-based post event analysis","[{\"question\":\"What problem does the paper address in cyber-physical power systems?\",\"answer\":\"It addresses how to respond to growing cybersecurity risks that arise when power systems adopt digital substations and SCADA communication, which increase exposure to cyber-attacks.\"},{\"question\":\"How does the proposed method distinguish between faults and cyber-attacks?\",\"answer\":\"It trains an artificial neural network and other ML models using transient fault measurements and cyber-attack data, enabling the models to differentiate power system faults from cyber-attacks.\"},{\"question\":\"What results can the trained models provide after an event?\",\"answer\":\"The method can identify ten different fault types and determine the location along the line, and it also distinguishes cyber-attacks from conventional faults even under N-1 contingency conditions.\"}]","Machine Learning based Post Event Analysis for Cybersecurity of Cyber-Physical System - paper | PDF",1785935355,13,{"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},"machine-learning-based-post-event-analysis-for-cybersecurity-of-cyber-physical-system-paper","",{"@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/machine-learning-based-post-event-analysis-for-cybersecurity-of-cyber-physical-system-paper/126877/",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","2026-08-05",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 paper address in cyber-physical power systems?","Question",{"text":75,"@type":76},"It addresses how to respond to growing cybersecurity risks that arise when power systems adopt digital substations and SCADA communication, which increase exposure to cyber-attacks.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method distinguish between faults and cyber-attacks?",{"text":80,"@type":76},"It trains an artificial neural network and other ML models using transient fault measurements and cyber-attack data, enabling the models to differentiate power system faults from cyber-attacks.",{"name":82,"@type":73,"acceptedAnswer":83},"What results can the trained models provide after an event?",{"text":84,"@type":76},"The method can identify ten different fault types and determine the location along the line, and it also distinguishes cyber-attacks from conventional faults even under N-1 contingency conditions.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":103,"slug":104},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"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":21,"slug":137},19,"General","general"]