New Paper: Two papers will appear in USENIX International Conference on Automonic Computing (ICAC) 2014!
New Paper: One paper will appear in special track on Self-Aware Cyber-Physical Systems of USENIX International Conference on Automonic Computing (ICAC) 2014!
Article “How Can Supercomputers Survive a Drought?” appears at
GreenBiz covered my research: “5 reasons the thirst for water technology will grow in 2014”
New Paper: “Thermal-Aware Scheduling of Batch Jobs in Geographically Distributed Data Centers”
accepted by IEEE Transactions on Cloud Computing. Earlier version appeared at ICDCS 2012.
It is well known that data centers are so important for our digital economy that we cannot possibly live without them.
Making large data centers efficient (e.g., cost effective, sustainable, etc.) has been an undeniably hot topic for years. Meanwhile, integrating
large data centers with the smart grid (e.g., for demand response, regulation services, etc.) is also becoming a trending research topic.
There've been tens of thousands of papers on making data centers efficient, and some of our own papers
fall into this category. Expectedly, there'll be more papers coming from various research groups worldwide.
Our group is trying to find out: What are data centers and are we really looking at data centers?
As of now, our answer is “Yes, but perhaps not the whole picture!”
We'll show our findings very
soon (after some necessary internal review).
California declared drought emergency on January 17, 2014 (link)
As California is experiencing the record drought, Gov. Jerry Brown urges a 20% cut in water consumption; mandatory conservation measure could also be coming
NBC: California governor declares drought emergency, asks for conservation
Sacramento and Folsom have issued mandatory water usage restrictions (source)
Parts of 11 states, including Arkansas, California, Colorado, Hawaii, Idaho, Kansas, New Mexico, Nevada, Oklahoma, Texas and Utah, are designed as drought disaster areas (source)
Our data centers are thirsty!
While it has been well known that data centers are huge energy hogs, data centers also leave an astonishing water footprint!
Why should we care about data centers’ water footprints? Here're some simple facts.
See LBNL's “Guideline for Water and Energy Considerations During Federal Data Center Consolidations”, prepared for the U.S. DoE Federal Energy Management Program
See California's drought emergency
Green certifications: The 2013 survey by Uptime Institute shows that a vast majority of the 1,000 data centers surveyed are actively seeking green certifications (e.g., LEED by U.S.
Green Building Council), which often carry tax credits as well as other benefits. For these green certifications, energy efficiency is just ONE component;
water conservation is another key factor and often a prerequisite!
Facebook open sourced its dashboard code for monitoring data center water usage (and PUE), in the hope that more data centers
will pay attention to water efficiency. (Link)
AT&T's cooling towers in large (data center) facilities consume 1 billion gallons of water in 2012, about 30% of the
entire company's water consumption. (Link)
S. Ren, “Optimizing Water Efficiency in Distributed Data Centers,” International Conference on Cloud and Green Computing (CGC, acceptance
ratio: 19/80=24%), 2013. [PDF]
Note: This paper preliminarily demonstrates the feasibility of scheduling delay-sensitive workloads among different data centers for optimizing water usage effectiveness, defined
as the water consumption per unit IT energy (like power usage effectiness factor). This paper does not minimize or cap the actual water consumption.
M. A. Islam, K. Ahmed, S. Ren, and G. Quan, “Making Data Center Less ‘Thirsty' via Online Batch Job Scheduling,”
Tech. Report, 2013. [PDF]
Note: This technical report explores time diversity of water usage effectiveness to dyanamically “backfill” delay-tolerant batch jobs
in a single data center to minimize the combined cost, incorporating electricity cost, water consumption and carbon emission.
Shaolei Ren received the B.E. degree in Electronic Engineering from Tsinghua University in
July 2006, the M.Phil. degree in Eletronic and Computer Engineering from Hong Kong
University of Science and Technology in August 2008, and the Ph.D. degree in
Electrical Engineering from University of California, Los Angeles, in June 2012.
Since August 2012, he has been with Florida International University,
where he currently holds a joint appointment of Assistant Professor in the School of Computing and Information Sciences and the Department of Electrical and Computer Engineering.
Dr. Ren directs the Sustainable Computing Group at FIU. His research centers around cloud computing and data center resource management,
with an emphasis on sustainability. He received the Best Paper Award at
the 8th International Workshop on Feedback Computing, the Best Paper Award at
IEEE International Conference on Communications in 2009, and was selected by
IBM T. J. Watson Research as one of the 10 Emerging Leaders in Multimedia and Signal Processing in 2010.