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:20210402T160546Z
LOCATION:Track 9
DTSTART;TZID=America/New_York:20201113T171000
DTEND;TZID=America/New_York:20201113T174000
UID:submissions.supercomputing.org_SC20_sess231_ws_mlcs106@linklings.com
SUMMARY:Scheduling in Data Centers Running on Renewable Energy with Deep R
 einforcement Learning
DESCRIPTION:Workshop\n\nScheduling in Data Centers Running on Renewable En
 ergy with Deep Reinforcement Learning\n\nVenkataswamy, Grimshaw\n\nMost da
 tacenters operate on electricity generated using non-renewable sources. El
 ectricity cost is a significant part of the operational expense in datacen
 ters. Higher electricity costs translate to endusers paying higher prices 
 for cloud services or service providers seeing reduced profits. To reduce 
 the cost to endusers and make higher profits, cloud service providers need
  to reduce operational expenses. Renewable energies are increasingly becom
 ing a viable electricity source that dramatically lower electrical power c
 osts and achieve dramatic reductions in climate impact. The green datacent
 ers are colocated at the sources and powered by renewable energy. The gree
 n datacenters are not restricted to using a single source of renewable ene
 rgy; instead, they utilize multiple energy sources. \n\nUsing renewable en
 ergy sources to power the datacenters has challenges. For instance, wind f
 low is not continuous and not uniform across regions, time of day, or seas
 ons. The datacenters running on renewable energy sources need smart system
 -software that adapt to the power variability to ensure that cloud service
 s are available even when there is transient power unavailability in these
  datacenters. Three issues that need addressing are 1) Meeting Service Lev
 el Objectives, 2) Resource Pool Management, and 3) Adapting to power varia
 bility.  \n\nHand-engineering domain-specific heuristics-based schedulers 
 to meet specific objective functions is time-consuming and expensive, and 
 requires extensive tuning in this dynamic environment. We applied deep rei
 nforcement learning (DRL) to automatically learn effective job scheduling 
 policies while continuously adapting to the complex dynamic environment. T
 he DRL-based scheduler's objective function is to maximize the total value
  from jobs.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR