BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Taipei
BEGIN:STANDARD
DTSTART:19790930T230000
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260616T032601Z
UID:FEB15390-CAE4-4F90-A12B-4EBC9C4D7EE7
DTSTART;TZID=Asia/Taipei:20260615T132000
DTEND;TZID=Asia/Taipei:20260615T155000
DESCRIPTION:IEEE Taipei Chapter PELS Chapter - Power Seminar\n\nSpeaker: Pr
 of. Hao Zhu\, University of Texas Austin\n\nTitle: The Dual Frontier betwe
 en AI and the Power Grid\n\nAbstract: AI/ML technologies are rapidly resha
 ping the paradigm of operating electric power grids. Meanwhile\, the hyper
 scale and dynamic energy demands of AI datacenters pose significant challe
 nges to grid reliability. In this talk\, I will explore the dual frontier 
 between AI and the power system\, with a focus on grid dynamic modeling an
 d analysis. First\, to effectively apply AI tools to grid dynamics\, it is
  crucial to consider not only computational/memory efficiency but also the
  unique characteristics of dynamic systems. To address this\, we introduce
  TRASE-NODEs—Trajectory Sensitivity-aware Neural ODEs—which leverage t
 he classical dynamic sensitivity concept to significantly improve data eff
 iciency and control performance in neural dynamic models. Second\, we exam
 ine the impact of large-scale AI datacenters on wide-area power system osc
 illations. By developing a stochastic model to represent sustained\, perio
 dic power fluctuations\, our numerical studies reveal that factors such as
  datacenter sizing and geographic distribution can influence oscillation l
 evels. This quantitative analysis highlights the need for developing mitig
 ation strategies at both the grid and hardware levels to support the conti
 nued growth of AI-driven energy demand.\n\nSpeaker(s): Hao Zhu\n\nRoom: 10
 6\, Bldg: Electrical Engineering 2\, National Taiwan University\, Taipei\,
  T'ai-pei\, Taiwan
LOCATION:Room: 106\, Bldg: Electrical Engineering 2\, National Taiwan Unive
 rsity\, Taipei\, T'ai-pei\, Taiwan
ORGANIZER:kakim@ntu.edu.tw
SEQUENCE:13
SUMMARY:Power Seminar on AI and the Power Grid
URL;VALUE=URI:https://events.vtools.ieee.org/m/563391
X-ALT-DESC:Description: <br /><p>IEEE Taipei Chapter PELS Chapter - Power S
 eminar</p>\n<p>Speaker: Prof. Hao Zhu\, University of Texas Austin</p>\n<p
  class="x_x_MsoNormal">Title: The Dual Frontier between AI and the Power G
 rid</p>\n<p class="x_x_MsoNormal">Abstract: AI/ML technologies are rapidly
  reshaping the paradigm of operating electric power grids. Meanwhile\, the
  hyperscale and dynamic energy demands of AI datacenters pose significant 
 challenges to grid reliability. In this talk\, I will explore the dual fro
 ntier between AI and the power system\, with a focus on grid dynamic model
 ing and analysis. First\, to effectively apply AI tools to grid dynamics\,
  it is crucial to consider not only computational/memory efficiency but al
 so the unique characteristics of dynamic systems. To address this\, we int
 roduce TRASE-NODEs&mdash\;<u>Tra</u>jectory&nbsp\;<u>Se</u>nsitivity-aware
  Neural ODEs&mdash\;which leverage the classical dynamic sensitivity conce
 pt to significantly improve data efficiency and control performance in neu
 ral dynamic models. Second\, we examine the impact of large-scale AI datac
 enters on wide-area power system oscillations. By developing a stochastic 
 model to represent sustained\, periodic power fluctuations\, our numerical
  studies reveal that factors such as datacenter sizing and geographic dist
 ribution can influence oscillation levels. This quantitative analysis high
 lights the need for developing mitigation strategies at both the grid and 
 hardware levels to support the continued growth of AI-driven energy demand
 .</p>\n<p class="x_x_MsoNormal">&nbsp\;</p>\n<p class="x_x_MsoNormal">&nbs
 p\;</p>
END:VEVENT
END:VCALENDAR