BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20230124T170804Z
LOCATION:C1-2-3
DTSTART;TZID=America/Chicago:20221116T083000
DTEND;TZID=America/Chicago:20221116T170000
UID:submissions.supercomputing.org_SC22_sess274_rpost131@linklings.com
SUMMARY:A Light-Weight and Unsupervised Method for Near Real-time Anomaly 
 Detection Using Operational Data Measurement
DESCRIPTION:Posters, Research Posters\n\nA Light-Weight and Unsupervised M
 ethod for Near Real-time Anomaly Detection Using Operational Data Measurem
 ent\n\nVargis, Ghiasvand\n\nMonitoring the status of large computing syste
 ms is essential to identify unexpected behavior and improve their performa
 nce and up-time. However, due to the large-scale and distributed design of
  such computing systems as well as a large number of monitoring parameters
 , automated monitoring methods should be applied. Such automatic monitorin
 g methods should also have the ability to adapt themselves to the continuo
 us changes in the computing system. In addition, they should be able to id
 entify behavioral anomalies in useful time, in order to perform appropriat
 e reactions. This work proposes a general light-weight and unsupervised me
 thod for near real-time anomaly detection using operational data measureme
 nt on large computing systems. The proposed model requires as low as 4 hou
 rs of data and 50 epochs for each training process to accurately resemble 
 the behavioral pattern of computing systems.\n\nRegistration Category: Tec
 h Program Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR