[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84645-en":3,"doc-seo-84645-105":29,"detail-sidebar-cat-0-en-105":90},{"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":13,"seo_description":14,"update_tm":27,"read_time":28},84645,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Generative Autonomous Grid Control Integrating Decision Transformers with a Two-Stage Safety Stack","The paper addresses the inertia-driven shift in power-system frequency dynamics caused by inverter-based resources, making conventional automatic generation control too slow for fast deviations. It introduces an Autonomous Grid Generation Control framework that couples an offline-trained Decision Transformer with a two-stage symbolic safety stack for secondary frequency control. A sub-ten-millisecond constraint verification unit and a swing-equation-based digital twin certify stability, achieving over 99% ACE integral reduction and ~10 ms inference latency on the NPCC 140-bus system under low-inertia conditions.","Generative Autonomous Grid Control: Integrating Decision Transformers with a Two-Stage Safety  \nStack  \nMohamed Shamseldein, Senior Member, IEEE  \narXiv :2607 .02379v1 [ ee ss . SY] 2 Jul 2026  \nAbstract—The displacement of synchronous generation by inverter-based resources is accelerating power system frequency dynamics beyond the response capability of conventional automatic generation control. This paper presents Autonomous Grid Generation Control with Decision Transformers, a framework coupling an offline-trained Decision Transformer with a twostage symbolic safety stack for secondary frequency control. The Decision Transformer learns a conditional dispatch policy from offline supervisory control and data acquisition records via sequence modeling, eliminating online exploration risks. A Constraint Verification Unit provides sub-ten-millisecond algebraic screening using real-time power transfer distribution factors, while an aggregate digital twin performs swing-equation-based dynamic stability certification. Validated on the Northeast Power Coordinating Council 140-bus system under low-inertia conditions, the proposed controller reduces the area control error integral by over 99% relative to tuned automatic generation control, maintains a 59.4 Hz frequency nadir, and achieves inference latency of approximately 10 ms, well within real-time constraints. Comparative evaluation against a linear quadratic regulator baseline and structural analysis against conservative Q-learning demonstrate the advantages of the sequence-modeling formulation. Small-signal eigenvalue analysis characterizes the dominant 1.87 Hz electromechanical mode and confirms that the safety stack maintains stable operation across operating points. By falling back to tuned automatic generation control whenever proposals are rejected, the safety stack bounds worst-case performance to industry-standard levels in simulation.  \nIndex Terms—Decision transformer, offline reinforcement learning, digital twin, power system frequency control, safety verification, ANDES, NPCC system.  \nNOMENCLATURE  \nG , L, B Sets of generators, transmission lines, and buses [–] .  \nPg , Qg Active [MW] and reactive [Mvar] power generation of unit g.  \nVi ,θi Voltage magnitude [p.u.] and phase angle [rad] at bus i.  \nVt ,θt Vectors of all bus voltages [p.u.] and angles [rad] at time t.  \nfagg,t Aggregate system frequency at time t [Hz] .  \nPline,t Vector of active power flows on all lines at time t [MW] .  \nPgen,t Generation dispatch vector at time t [MW] . Pload,t Load demand vector at time t [MW] .  \n∆f System frequency deviation [Hz] .  \nM. Shamseldein is an Assistant Professor with the Department of Electrical Power and Machines, Faculty of Engineering, Ain Shams University, Cairo, Egypt.  \nACE Area Control Error [MW] .  \nD Offline dataset of trajectories [–] .  \nπβ , πθ Behavior (PID) policy and learned Decision Transformer policy [–] .  \nRt Return-to-go at time step t [–] .  \nK Context length for the Transformer window  \n[timesteps] .  \ndmodel Embedding dimension of the Transformer [–] . H Power Transfer Distribution Factor (PTDF) matrix  \n[–] .  \nM, D Aggregated inertia [s] and damping [p.u.] constants.  \nHsys System-wide inertia constant [s] .  \nfmin Predicted frequency nadir [Hz] .  \nfUFLS Under-Frequency Load-Shedding threshold [Hz] .∆at Normalized action delta [–] .  \n∆Pmax Maximum generator ramp per control step [MW] .θOU ,σOUOrnstein–Uhlenbeck noise parameters [–] . Cop Quadratic generation operating cost [$/h] .  \nαi ,βi ,γi Generator cost curve coefficients [$/MW2h,$/MWh, $/h] .  \nλf ,λace , ce,rd weighting coefficients [–] .  \nζ Damping ratio of electromechanical mode [–] . Ts Settling time [s] .  \nI. INTRODUCTION  \nTHE fundamental operational paradigm of power systems is  \nshifting. The displacement of synchronous generation by Inverter-Based Resources (IBRs) has precipitated a decline in system inertia, accelerating frequency dynamics from the order of seconds to hundr","cbCaimF0XsS6YExL","https://ap.wps.com/l/cbCaimF0XsS6YExL","pdf",1498161,1,11,"English","en",105,"# Abstract\n# Introduction\n## Related Work and Research Gaps","[{\"question\":\"Why is conventional automatic generation control insufficient for modern low-inertia grids?\",\"answer\":\"Inverter-based resources reduce system inertia, accelerating frequency dynamics from seconds to hundreds of milliseconds. This contraction outpaces the response capability of conventional automatic generation control and human operator limits.\"},{\"question\":\"How does the framework use a Decision Transformer in grid control?\",\"answer\":\"The Decision Transformer is trained offline via sequence modeling to learn a conditional dispatch policy from archived supervisory control and data acquisition records. It avoids online exploration risk by never learning through trial-and-error during deployment.\"},{\"question\":\"What does the two-stage safety stack do to ensure safe secondary frequency control?\",\"answer\":\"A constraint verification unit performs sub-10-millisecond algebraic screening using real-time PTDF-based checks, while an aggregate digital twin certifies dynamic stability using swing-equation-based analysis. If proposals are rejected, the system falls back to tuned automatic generation control to bound worst-case performance.\"}]",1784197441,28,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"generative-autonomous-grid-control-integrating-decision-transformers-with-a-two-stage-safety-stack","",{"@graph":35,"@context":84},[36,53,67],{"@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/generative-autonomous-grid-control-integrating-decision-transformers-with-a-two-stage-safety-stack/84645/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why is conventional automatic generation control insufficient for modern low-inertia grids?","Question",{"text":74,"@type":75},"Inverter-based resources reduce system inertia, accelerating frequency dynamics from seconds to hundreds of milliseconds. This contraction outpaces the response capability of conventional automatic generation control and human operator limits.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How does the framework use a Decision Transformer in grid control?",{"text":79,"@type":75},"The Decision Transformer is trained offline via sequence modeling to learn a conditional dispatch policy from archived supervisory control and data acquisition records. It avoids online exploration risk by never learning through trial-and-error during deployment.",{"name":81,"@type":72,"acceptedAnswer":82},"What does the two-stage safety stack do to ensure safe secondary frequency control?",{"text":83,"@type":75},"A constraint verification unit performs sub-10-millisecond algebraic screening using real-time PTDF-based checks, while an aggregate digital twin certifies dynamic stability using swing-equation-based analysis. If proposals are rejected, the system falls back to tuned automatic generation control to bound worst-case performance.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"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":105,"slug":137},19,"General","general"]