BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Efficient cloud operations via job-migration and pricing - Ishai M
 enache\, Microsoft Research New England
DTSTART:20110323T100000Z
DTEND:20110323T110000Z
UID:TALK30274@talks.cam.ac.uk
CONTACT:Microsoft Research Cambridge Talks Admins
DESCRIPTION:Cloud computing technology offers on-demand network access to 
 shared pools of configurable computing resources\, such as virtual servers
 \, applications and software services. This paradigm delivers the economy 
 of scale to users via large datacenters\, fast and flexible provisioning o
 f resources\, and the freedom from long-term investments in equipment. Des
 pite the potential advantages\, a new set of challenges must be overcome b
 efore cloud providers can see a return on their investments\; namely\, dea
 ling with the uncertainty involved in operating cloud systems\, both in te
 rms of supply (time-varying energy prices and availability) and demand for
  computing resources.\n\nOne way to reduce operation costs is by exploitin
 g the spatiotemporal variation of electricity prices. I start by showing h
 ow techniques from online algorithms can be employed to develop algorithms
  that move computation to datacenters in which energy is available at a ch
 eaper price. The algorithm we design performs remarkably well on empirical
  electricity-prices and job-demand data. In the second part of the talk\, 
 I develop a general queuing-based model for the study of cloud computing e
 conomics\, incorporating stochastic demands and diversity in the applicati
 on types and user preferences. Despite the high level of heterogeneity\, I
  show that a simple per-unit price (currently employed by most cloud platf
 orms) suffices to induce social efficiency. I will conclude with a discuss
 ion of ongoing work on combining energy-aware scheduling and mechanism des
 ign for optimizing profits.
LOCATION:Small lecture theatre\, Microsoft Research Ltd\, 7 J J Thomson Av
 enue (Off Madingley Road)\, Cambridge
END:VEVENT
END:VCALENDAR
