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:20260504T094726Z
UID:59FB2EAD-5D9E-4C9F-813C-E5A3062976C9
DTSTART;TZID=Europe/Copenhagen:20260504T090000
DTEND;TZID=Europe/Copenhagen:20260504T100000
DESCRIPTION:Introduction: Energy systems modeling and optimization is essen
 tial for policy and grid operations\, yet traditional approaches often sac
 rifice physical accuracy for computational speed. By focusing primarily on
  electrical variables (power\, voltage\, energy)\, current common standard
  models neglect the vital thermal and electro-chemical dynamics of modern\
 , flexible assets\, leading to grid bottlenecks and economic inefficiencie
 s.\n\nTo bridge the gap between physical reality and system-level planning
 \, a rigorous bottom-up approach is proposed:\n\n- Multi-Physics Integrati
 on: Incorporating complex thermal and chemical behaviors into asset repres
 entation to prevent &quot;missed connections&quot; and grid delays.\n- Hybrid Method
 ology: Combining Artificial Intelligence (AI) with physics-based optimizat
 ion to ensure reliability without the typical computational burden.\n\nCon
 tent:\n\n- Multi-Physics Integration I: Thermal incorporation and control 
 for alkaline electrolyzers for system-level models\n- Multi-Physics Integr
 ation II: Aging-aware AC Optimal Power Flow of grid assets management (cab
 les and power transformers) to unlock grid capacity\n- Hybrid Methodology 
 I: Learning Active Constraints for Bilevel Optimization: Evaluating Classi
 fication Metrics on Real-World Distribution System Data\n- Hybrid Methodol
 ogy II: Surrogate Models in Power System Scheduling Problems: Learning Act
 ive Constraints via Graph Neural Networks\n\nCo-sponsored by: DTU Wind and
  Energy Systems\n\nSpeaker(s): Lingkang Jin\n\nAgenda: \n- Welcome by Assi
 stant Professor Haris Ziras\n- Lingkang Jin: AI‑Supported Multiphysics S
 ystem‑Level Energy System Modeling and Optimization\n- Closing of event\
 n\nVirtual: https://events.vtools.ieee.org/m/556668
LOCATION:Virtual: https://events.vtools.ieee.org/m/556668
ORGANIZER:chazi@dtu.dk
SEQUENCE:19
SUMMARY:AI‑Supported Multiphysics System‑Level Energy System Modeling a
 nd Optimization
URL;VALUE=URI:https://events.vtools.ieee.org/m/556668
X-ALT-DESC:Description: &lt;br /&gt;&lt;p class=&quot;x_MsoNormal&quot;&gt;&lt;strong&gt;&lt;span data-olk
 -copy-source=&quot;MessageBody&quot;&gt;Introduction&lt;/span&gt;&lt;/strong&gt;: Energy systems mo
 deling and optimization is essential for policy and grid operations\, yet 
 traditional approaches often sacrifice physical accuracy for computational
  speed. By focusing primarily on electrical variables (power\, voltage\, e
 nergy)\, current common standard models neglect the vital thermal and elec
 tro-chemical dynamics of modern\, flexible assets\, leading to grid bottle
 necks and economic inefficiencies.&lt;/p&gt;\n&lt;p class=&quot;x_MsoNormal&quot;&gt;To bridge t
 he gap between physical reality and system-level planning\, a rigorous bot
 tom-up approach is proposed:&lt;/p&gt;\n&lt;ul type=&quot;disc&quot;&gt;\n&lt;li class=&quot;x_MsoNormal
 &quot;&gt;&lt;strong&gt;Multi-Physics Integration:&lt;/strong&gt;&amp;nbsp\;Incorporating complex 
 thermal and chemical behaviors into asset representation to prevent &quot;misse
 d connections&quot; and grid delays.&lt;/li&gt;\n&lt;li class=&quot;x_MsoNormal&quot;&gt;&lt;strong&gt;Hybr
 id Methodology:&lt;/strong&gt;&amp;nbsp\;Combining&amp;nbsp\;&lt;strong&gt;Artificial Intellig
 ence (AI)&lt;/strong&gt;&amp;nbsp\;with&amp;nbsp\;&lt;strong&gt;physics-based optimization&lt;/st
 rong&gt; to ensure reliability without the typical computational burden.&lt;/li&gt;
 \n&lt;/ul&gt;\n&lt;p class=&quot;x_MsoNormal&quot;&gt;&lt;strong&gt;&lt;span data-olk-copy-source=&quot;Messag
 eBody&quot;&gt;Content:&lt;/span&gt;&lt;/strong&gt;&lt;/p&gt;\n&lt;ol start=&quot;1&quot; type=&quot;1&quot;&gt;\n&lt;li class=&quot;x
 _MsoListParagraph&quot;&gt;&lt;strong&gt;Multi-Physics Integration I:&amp;nbsp\;&lt;/strong&gt;The
 rmal incorporation and control for alkaline electrolyzers for system-level
  models&lt;/li&gt;\n&lt;li class=&quot;x_MsoListParagraph&quot;&gt;&lt;strong&gt;Multi-Physics Integra
 tion II:&amp;nbsp\;&lt;/strong&gt;Aging-aware AC Optimal Power Flow of grid assets m
 anagement (cables and power transformers) to unlock grid capacity&lt;/li&gt;\n&lt;l
 i class=&quot;x_MsoListParagraph&quot;&gt;&lt;strong&gt;Hybrid Methodology I:&amp;nbsp\;&lt;/strong&gt;
 Learning Active Constraints for Bilevel Optimization: Evaluating Classific
 ation Metrics on Real-World Distribution System Data&lt;/li&gt;\n&lt;li class=&quot;x_Ms
 oListParagraph&quot;&gt;&lt;strong&gt;Hybrid Methodology II:&amp;nbsp\;&lt;/strong&gt;Surrogate Mo
 dels in Power System Scheduling Problems: Learning Active Constraints via 
 Graph Neural Networks&lt;/li&gt;\n&lt;/ol&gt;&lt;br /&gt;&lt;br /&gt;Agenda: &lt;br /&gt;&lt;ul&gt;\n&lt;li&gt;Welco
 me by Assistant Professor Haris Ziras&lt;/li&gt;\n&lt;li&gt;&lt;span data-olk-copy-source
 =&quot;MessageBody&quot;&gt;Lingkang Jin: AI‑Supported Multiphysics System‑Level En
 ergy System Modeling and Optimization&lt;/span&gt;&lt;/li&gt;\n&lt;li&gt;&lt;span data-olk-copy
 -source=&quot;MessageBody&quot;&gt;Closing of event&lt;/span&gt;&lt;/li&gt;\n&lt;/ul&gt;
END:VEVENT
END:VCALENDAR