BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Europe/Copenhagen
BEGIN:DAYLIGHT
DTSTART:20260329T030000
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=3
TZNAME:CEST
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20261025T020000
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
RRULE:FREQ=YEARLY;BYDAY=-1SU;BYMONTH=10
TZNAME:CET
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260526T140543Z
UID:C58DB999-9BF1-4840-BCFD-32BCD447BFC8
DTSTART;TZID=Europe/Copenhagen:20260526T094500
DTEND;TZID=Europe/Copenhagen:20260526T104500
DESCRIPTION:In connection with the PhD defense of Lisa Marie Dannappel\, DT
 U Wind and Energy Systems is pleased to have Assoc. Prof. Qianwen Xu from 
 KTH Royal Institute of Technology\, who will give a talk titled “AI-Driv
 en Stability and Control of Converter-Dominated Power Systems.”\n\nModer
 n power systems are rapidly evolving into converter-dominated energy syste
 ms\, driven by distributed energy resources\, electrified transport\, and 
 emerging large-scale loads such as data centers. This transformation funda
 mentally reshapes grid stability and operation: stability is no longer gov
 erned by physical inertia but by fast\, complex converter interactions\, w
 hile system operation must cope with increasing uncertainty and scale.\n\n
 This talk presents how artificial intelligence can enable reliable and sca
 lable operation of such systems across three layers. First\, transfer lear
 ning-based approaches are developed for fast\, online modeling of converte
 r-interfaced assets\, enabling accurate system representation without deta
 iled device-level knowledge. Second\, AI-driven stability assessment frame
 works are introduced for real-time evaluation of converter–grid interact
 ions. Third\, safe deep reinforcement learning methods are presented for l
 arge-scale grid operation\, ensuring guaranteed safety while optimizing pe
 rformance. Together\, these advances point toward a new paradigm of autono
 mous\, AI-enabled energy systems\, where learning-based methods are tightl
 y integrated with physical constraints to ensure stability\, efficiency\, 
 and resilience.\n\nCo-sponsored by: DTU Wind and Energy Systems\n\nSpeaker
 (s): Qianwen Xu \n\nAgenda: \n- Welcome by Senior Researcher Shi You\n- Ta
 lk by Associate Prof. Qianwen Xu from KTH "AI-Driven Stability and Control
  of Converter-Dominated Power Systems"\n- Closure\n\nVirtual: https://even
 ts.vtools.ieee.org/m/560754
LOCATION:Virtual: https://events.vtools.ieee.org/m/560754
ORGANIZER:tweck@dtu.dk
SEQUENCE:17
SUMMARY:AI-Driven Stability and Control of Converter-Dominated Power System
 s – Assoc. Prof. Qianwen Xu
URL;VALUE=URI:https://events.vtools.ieee.org/m/560754
X-ALT-DESC:Description: <br /><p class="x_MsoNormal" data-olk-copy-source="
 MessageBody">In connection with the PhD defense of Lisa Marie Dannappel\, 
 DTU Wind and Energy Systems is pleased to have Assoc. Prof. Qianwen Xu fro
 m KTH Royal Institute of Technology\, who will give a talk titled <strong>
 &ldquo\;AI-Driven Stability and Control of Converter-Dominated Power Syste
 ms.&rdquo\;</strong>&nbsp\;</p>\n<p class="x_MsoNormal">Modern power syste
 ms are rapidly evolving into converter-dominated energy systems\, driven b
 y distributed energy resources\, electrified transport\, and emerging larg
 e-scale loads such as data centers. This transformation fundamentally resh
 apes grid stability and operation: stability is no longer governed by phys
 ical inertia but by fast\, complex converter interactions\, while system o
 peration must cope with increasing uncertainty and scale.</p>\n<p class="x
 _MsoNormal">This talk presents how artificial intelligence can enable reli
 able and scalable operation of such systems across three layers. First\, t
 ransfer learning-based approaches are developed for fast\, online modeling
  of converter-interfaced assets\, enabling accurate system representation 
 without detailed device-level knowledge. Second\, AI-driven stability asse
 ssment frameworks are introduced for real-time evaluation of converter&nda
 sh\;grid interactions. Third\, safe deep reinforcement learning methods ar
 e presented for large-scale grid operation\, ensuring guaranteed safety wh
 ile optimizing performance. Together\, these advances point toward a new p
 aradigm of autonomous\, AI-enabled energy systems\, where learning-based m
 ethods are tightly integrated with physical constraints to ensure stabilit
 y\, efficiency\, and resilience.</p><br /><br />Agenda: <br /><ul>\n<li>We
 lcome by Senior Researcher Shi You</li>\n<li>Talk by Associate Prof. Qianw
 en Xu from KTH "AI-Driven Stability and Control of Converter-Dominated Pow
 er Systems"</li>\n<li>Closure</li>\n</ul>
END:VEVENT
END:VCALENDAR