[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83976-en":3,"doc-seo-83976-105":29,"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":20,"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":13,"seo_description":14,"update_tm":27,"read_time":28},83976,7971461740886,"Theodore","https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2",8,"Research & Report","Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids","Transient stability control in smart grids depends on rapid post-fault damping of generator frequency and rotor-angle deviations to avoid cascading failures. The paper introduces FedPPO-PG, a federated multi-agent proximal policy optimization framework that converts transient stability control into cooperative reinforcement learning optimized directly for closed-loop stability objectives. Each generator runs a local actor using frequency deviations from the two most strongly coupled neighbors, with guided warm-start from a decentralized classical controller and a centralized critic under CTDE. On the IEEE 39-bus benchmark, FedPPO-PG stabilizes all trials, shortens mean stability time by 72.4%, and reduces control power by 7–14× versus a centralized baseline, while meeting real-time reporting latency constraints.","Federated Physics-Grounded Reinforcement Learning for Distributed Stability Control in Smart Grids  \nOmar Al-Refai, Ibrahim Shahbaz, Adam Ali Husseinat, Eman Hammad  \niSTAR Lab, Texas A&M University  \nCollege Station, TX, USA  \n{omaralrefai, i.shahbaz, adamali, [eman.hammad](eman.hammad}@tamu.edu)[}](eman.hammad}@tamu.edu)[@tamu.edu](eman.hammad}@tamu.edu)  \narXiv :2607 .05553v 1 [ cs .LG] 6 Jul 2026  \nAbstract—Transient stability control in smart grids requires rapid post-fault damping of generator frequency and rotor angle deviations to prevent cascading failures. This paper proposes FedPPO-PG, a Federated Multi-Agent Proximal Policy Optimization framework with Physics-Grounded neighborhoods, which reformulates transient stability control as a cooperative multiagent reinforcement learning problem optimized directly against closed-loop stability objectives. Each generator hosts an independent local actor augmented with the frequency deviations of its two most strongly coupled electrical neighbors, identified from the post-fault Kron-reduced susceptance matrix. A guided policy initialization phase warm-starts all actors from the classical decentralized controller, while a centralized critic guides advantage estimation under the centralized training–decentralized execution (CTDE) paradigm. Evaluated on a simulation of the IEEE 39-bus benchmark system across five training and three unseen fault contingencies, FedPPO-PG achieves 100% stabilization in all 24 trials, reduces mean stability time by 72.4%, and cuts the control power by 7-14 times compared to the centralized baseline. Each actor executes independently with no central coordinator at deployment, and the per-actor inference latency satisfies the IEEE/IEC 60255-118-1-2018 real-time reporting requirements.  \nIndex Terms—Transient stability control, multi-agent reinforcement learning, federated learning, proximal policy optimization, smart grids, decentralized control.  \nI. INTRODUCTION  \nModern smart grids (SGs) are increasingly modeled as cyberphysical systems that integrate sensing, communication, and control to improve dependability and resilience in the face of disruptions. Transient stability control remains a crucial challenge; following a severe fault, generator rotor angles and frequencies must be stabilized rapidly to prevent cascading failures and loss of synchronism.  \nRecent work has explored interpretable neural architectures for distributed transient stability control. In [1], the centralized training–decentralized execution (CTDE) paradigm was employed by training spline-based Kolmogorov–Arnold Networks (KANs) and Chebyshev-based KANs (ChebyKANs) to approximate centralized control actions using only local PMU measurements. Closed-loop simulations revealed a significant robustness gap: low root-mean-squared error (RMSE) in offline evaluation did not consistently translate into improved dynamic resilience under unseen fault contingencies. Specifically, in fully decentralized deployment, neither neural variant could stabilize the system unless control authority was concentrated on  \nhigh-inertia generators; in that case, ChebyKANs demonstrated better robustness.  \nSubsequently, a federated learning control (FLC) framework [2] was proposed to enhance distributed coordination. In this approach, ChebyKAN-based local controllers collaboratively learned a shared global policy via federated averaging, improving generalization at moderate penetration levels. However, performance degraded at higher levels of distributed control penetration, so full distributed control was not achieved, and neural network inference latency remained a practical concern for real-time deployment.  \nA key finding from these prior studies is that closed-loop stability objectives are not directly optimized by supervised imitation of centralized control. Function approximation accuracy alone is insufficient to guarantee robust transient performance under unseen disturbances, because offline re","cbCaisMLcjVHRbFI","https://ap.wps.com/l/cbCaisMLcjVHRbFI","pdf",6281280,1,7,"English","en",105,"# Introduction\n# System Model","[{\"question\":\"What problem does FedPPO-PG address in smart grids?\",\"answer\":\"It targets transient stability control after severe faults by damping generator frequency and rotor-angle deviations fast enough to prevent cascading failures and loss of synchronism.\"},{\"question\":\"How is the federated multi-agent training structured in FedPPO-PG?\",\"answer\":\"Each generator hosts an independent local actor, while periodic federated averaging coordinates actor weights; training uses a centralized critic to guide advantage estimation under CTDE, but execution remains decentralized.\"},{\"question\":\"What coupling information do actors use to improve coordination?\",\"answer\":\"Actors augment local inputs with frequency deviations from the two most strongly coupled electrical neighbors, identified from the post-fault Kron-reduced susceptance matrix.\"}]",1784191798,18,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"federated-physics-grounded-reinforcement-learning-for-distributed-stability-control-in-smart-grids","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/federated-physics-grounded-reinforcement-learning-for-distributed-stability-control-in-smart-grids/83976/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does FedPPO-PG address in smart grids?","Question",{"text":75,"@type":76},"It targets transient stability control after severe faults by damping generator frequency and rotor-angle deviations fast enough to prevent cascading failures and loss of synchronism.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the federated multi-agent training structured in FedPPO-PG?",{"text":80,"@type":76},"Each generator hosts an independent local actor, while periodic federated averaging coordinates actor weights; training uses a centralized critic to guide advantage estimation under CTDE, but execution remains decentralized.",{"name":82,"@type":73,"acceptedAnswer":83},"What coupling information do actors use to improve coordination?",{"text":84,"@type":76},"Actors augment local inputs with frequency deviations from the two most strongly coupled electrical neighbors, identified from the post-fault Kron-reduced susceptance matrix.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"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":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]