marina zapater marina@die upm es n.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Marina Zapater – marina@die.upm.es PowerPoint Presentation
Download Presentation
Marina Zapater – marina@die.upm.es

Loading in 2 Seconds...

play fullscreen
1 / 2

Marina Zapater – marina@die.upm.es - PowerPoint PPT Presentation


  • 163 Views
  • Uploaded on

c a m p u s. Thermal-aware optimization techniques for energy minimization in Data Centers. MONCLOA. ArTeCS , Universidad Complutense Madrid LSI Group , Universidad Politécnica de Madrid. GLOBAL CHANGE AND NEW ENERGIES CLUSTER. Proactive and reactive thermal-aware optimization techniques

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Marina Zapater – marina@die.upm.es' - dennis


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
marina zapater marina@die upm es

c a m p u s

Thermal-aware optimization techniques for energy minimization in Data Centers

MONCLOA

ArTeCS, Universidad Complutense Madrid

LSI Group, Universidad Politécnica de Madrid

GLOBAL CHANGE AND NEW ENERGIES CLUSTER

  • Proactive and reactive thermal-awareoptimization techniques
  • Currently at the resource manager level
  • Holistic approach: computing and cooling resources
  • Application-awarereness, workload profiling and heterogeneity

Marina Zapater – marina@die.upm.es

r esearch overview and current issues
Researchoverview and currentissues
  • Analysis of the computational and cooling resources: acquire knowledge of the data center.
    • Wireless sensor network (temperature, energy, air pressure…)
    • Servers internal sensors
    • Application-profiling information
  • Decision-making in a reactive and proactive way:
    • Allocate both computing and cooling resources
    • Anomaly detection (hotspot detection)
    • Reliability enhancement
  • Until now: task profiling, heterogeneous servers, MILP optimization algorithms for RM (Slurm)
    • GA, SA… even SMT solvers?
  • Current issues: lack of real scenarios – Data centers
    • Thermal/Power model creation and validation issues.