BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160551Z
LOCATION:Track 8
DTSTART;TZID=America/New_York:20201111T154500
DTEND;TZID=America/New_York:20201111T155000
UID:submissions.supercomputing.org_SC20_sess198_ws_whpc104@linklings.com
SUMMARY:Smart-PGSim: Using Neural Network to Accelerate AC-OPFPower Grid S
 imulation
DESCRIPTION:Workshop\n\nSmart-PGSim: Using Neural Network to Accelerate AC
 -OPFPower Grid Simulation\n\nDong, Kestor, Li\n\nIn this work, we address 
 the problem of accelerating complex power-grid simulation through machine 
 learning (ML). Specifically, we develop a framework, Smart-PGsim, which ge
 nerates multitask-learning (MTL) neural network (NN) models to predict the
  initial values of variables critical to the problem convergence.  MTL mod
 els allow information sharing when predicting multiple dependent variables
  while including customized layers to predict individual variables.\n\nWe 
 show that, to achieve the required accuracy, it is paramount to embed doma
 in-specific constraints derived from the specific power-grid components in
  the MTL model.  Smart-PGsim then employs the predicted initial values as 
 a high-quality initial condition for the power-grid numerical solver (warm
  start), resulting in both higher performance compared to state-of-the-art
  solutions while maintaining the required accuracy. Smart-PGsim brings 2.6
 0x speedup on average (up to 3.28x) computed over 10,000 problems, without
  losing solution optimality.\n\nTag: Education, Training and Outreach, Pro
 fessional Development, Workforce Development\n\nRegistration Category: Wor
 kshop Reg Pass
END:VEVENT
END:VCALENDAR