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:20210402T160559Z
LOCATION:Track 11
DTSTART;TZID=America/New_York:20201113T112500
DTEND;TZID=America/New_York:20201113T115000
UID:submissions.supercomputing.org_SC20_sess229_ws_ai4s102@linklings.com
SUMMARY:Reinforcement Learning-Based Solution to Power Grid Planning and O
 peration Under Uncertainties
DESCRIPTION:Workshop\n\nReinforcement Learning-Based Solution to Power Gri
 d Planning and Operation Under Uncertainties\n\nShang, Ye, Zhang, Yang, Xu
 ...\n\nWith the ever-increasing stochastic and dynamic behavior observed i
 n today’s bulk power systems, securely and economically planning future op
 erational scenarios that meet all reliability standards under uncertaintie
 s becomes a challenging computational task, which typically involves searc
 hing feasible and suboptimal solutions in a highly dimensional space via m
 assive numerical simulations. This paper presents a novel approach to achi
 eving this goal by adopting the state-of-the-art reinforcement learning al
 gorithm, soft actor critic (SAC). First, the optimization problem of findi
 ng feasible solutions under uncertainties is formulated as Markov decision
  process. Second, a general and flexible framework is developed to train S
 AC agents by adjusting  generator active power outputs in searching feasib
 le operating conditions. A software prototype is developed that verifies t
 he effectiveness of the proposed approach via numerical studies conducted 
 on the future planning cases of the SGCC Zhejiang Electric Power Company.\
 n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR