[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126706-en":3,"doc-seo-126706-105":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},126706,962084925636,"Olivia Brown","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","A Physics Informed Machine Learning Method for Power System Model Parameter Optimization","This paper presents a physics-informed, gradient-descent optimization framework for power system model parameter identification and control-oriented tuning. The method relies on automatic differentiation to compute gradients and applies neural-network-derived differentiation tools to dynamic power system simulations. It supports one-shot parameter identification of uncertain simulation parameters and can optimize model parameters to match desired system behavior. Using a single machine infinite busbar case, the work provides theoretical foundations and demonstrative use cases, indicating broad applicability to related optimization problems.","A Physics Informed Machine Learning Method for Power System Model Parameter Optimization  \nGeorg Kordowich  \nJohann Jaeger  \nInstitute of Electrical Energy Systems  \nFriedrich-Alexander-Universitt Erlangen-N¨urnberg  \nErlangen, Germany  \n[georg.kordowich@fau.de](georg.kordowich@fau.de)  \narXiv :2309 . 16579v1 [ ee ss . SY] 28 Sep 2023  \nAbstract—This paper proposes a gradient descent based optimization method that relies on automatic differentiation for the computation of gradients. The method uses tools and techniques originally developed in the field of artificial neural networks and applies them to power system simulations. It can be used as a one-shot physics informed machine learning approach for the identification of uncertain power system simulation parameters. Additionally, it can optimize parameters with respect to a desired system behavior. The paper focuses on presenting the theoretical background and showing exemplary use-cases for both parameter identification and optimization using a single machine infinite busbar system. The results imply a generic applicability for a wide range of problems.  \nIndex Terms—Automatic Differentiation, Backpropagation, Gradient Descent Optimization, Physics Informed Neural Networks, Power System Parameter Optimization  \nI. INTRODUCTION  \nA. Background  \nThe growth in distributed generation increases the complexity of the grid. More variability in generation and loadflow demands reinforcements for the power grid. As the construction of new powerlines and grid components can be prohibitively expensive, many recent approaches focus on maximizing the utilization of existing infrastructure. Consequently, a trend towards a smarter grid is notable, characterized by increased automation of grid operations and the installation of sensors and actors to enhance grid observability and controllability.  \nAccurate models of power systems and components are an essential foundation of the trend towards a smarter grid. The utilization of concepts like digital twins is becoming increasingly prevalent for grid control and supervision [1] . For concepts like model predictive control, an accurate mathematical description is a key prerequisite [2] . Additionally, a lot of recent research focuses on employing different optimization or machine learning techniques in order to improve grid stability and security. Examples are the optimization of protection schemes, energy management, demand response or operational control [3], [4] .  \nB. Challenge  \nWhile good models are a fundamental requirement for all aforementioned advancements, it is often time consuming and  \ndifficult to create accurate models. Even though the general structure of a model or digital twin may be known, the task of finding precise parameters that match real world behavior is often particularly difficult.  \nTherefore, parameter identification and optimization can be identified as a core challenge for enabling secure operation in future power systems. While often described as two different tasks, it is important to note that parameter identification and optimization are essentially the same problem from a mathematical point of view: Parameter identification is infact an optimization problem, aiming to minimize the error between model and real-world behavior.  \nC. Automatic Differentiation in Power Systems  \nTo address the challenge of parameter optimization and identification in power system simulations we propose a novel method that incorporates an automatic differentiation (AD) tool into a dynamic power system simulation. AD tools can be used to compute gradients of mathematical functions. In the context of our method, those gradients are utilized to optimize simulation parameters by minimizing a loss or error function using gradient descent.  \nThe idea of using AD tools in the context of power systems was previously employed for a range of applications. In the steady state domain, they were used to calculate the Jacobian matrix for pow","cbCaiv4FCyFUhWOe","https://ap.wps.com/l/cbCaiv4FCyFUhWOe","pdf",1291115,1,7,"English","en",105,"# Introduction\n## Background\n## Challenge\n## Automatic Differentiation in Power Systems","[{\"question\":\"What is the core idea of the proposed method?\",\"answer\":\"The method uses gradient descent with gradients computed via automatic differentiation inside dynamic power system simulations to optimize simulation parameters.\"},{\"question\":\"How does parameter identification relate to optimization in this work?\",\"answer\":\"Parameter identification is treated as an optimization problem that minimizes the mismatch between model behavior and real-world behavior.\"},{\"question\":\"Why does the approach emphasize interpretability and security?\",\"answer\":\"Unlike black-box neural networks and physics-informed neural networks, it eliminates neural networks and relies solely on physically meaningful equations, forming a white-box model.\"}]","A Physics Informed Machine Learning Method for Power System Model Parameter Optimization | PDF",1785934323,18,{"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},"a-physics-informed-machine-learning-method-for-power-system-model-parameter-optimization","",{"@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/a-physics-informed-machine-learning-method-for-power-system-model-parameter-optimization/126706/",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 is the core idea of the proposed method?","Question",{"text":75,"@type":76},"The method uses gradient descent with gradients computed via automatic differentiation inside dynamic power system simulations to optimize simulation parameters.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does parameter identification relate to optimization in this work?",{"text":80,"@type":76},"Parameter identification is treated as an optimization problem that minimizes the mismatch between model behavior and real-world behavior.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the approach emphasize interpretability and security?",{"text":84,"@type":76},"Unlike black-box neural networks and physics-informed neural networks, it eliminates neural networks and relies solely on physically meaningful equations, forming a white-box model.","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},[93,97,101,105,110,115,119,122,127,130,134],{"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":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},"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":106,"slug":137},19,"General","general"]