Google posts it's latest PUE achievement of 1.14.
Measuring to improve: comprehensive, real-world data center efficiency numbers
March 26, 2012 at 9:00 AMTo paraphrase Lord Kelvin, if you don’t measure you can’t improve. Our data center operations team lives by this credo, and we take every opportunity to measure the performance of our facilities. In the same way that you might examine your electricity bill and then tweak the thermostat, we constantly track our energy consumption and use that data to make improvements to our infrastructure. As a result, our data centers use 50 percent less energy than the typical data center.......
Google's Joe Kava uses the Lord Kelvin principle of "if you don't measure you can't improve." But, I think a more apt explanation for the complexity of greening a data center is situation awareness.
Situation awareness
From Wikipedia, the free encyclopediaSituation awareness is the perception of environmental elements with respect to time and/or space, the comprehension of their meaning, and the
projection of their status after some variable has changed, such as time. It is also a field of study concerned with perception of the environment
critical to decision-makers in complex, dynamic areas from aviation, air traffic control, power plant operations, military command and control, and
emergency services such as fire fighting and policing; to more ordinary but nevertheless complex tasks
such as driving an automobile or bicycle.
Situation awareness involves being aware of what is happening in the vicinity to understand how information, events, and one's own actions will
impact goals and objectives, both immediately and in the near future. Lacking or inadequate situation awareness has been identified as one of
the primary factors in accidents attributed to human error.[1] Thus, situation awareness is especially important in work domains where the information
flow can be quite high and poor decisions may lead to serious consequences (e.g., piloting an airplane, functioning as a soldier, or treating critically
ill or injured patients).
Having complete, accurate and up-to-the-minute SA is essential where technological and situational complexity on the human decision-maker are
a concern. Situation awareness has been recognized as a critical, yet often elusive, foundation for successful decision-making across a broad
range of complex and dynamic systems, including aviation and air traffic control,[2] emergency response and military command and controloperations,[3]
and offshore oil and nuclear power plant management.[4]
Situation awareness vs. Lord Kelvin's principle has you thinking in the bigger picture. Thinking about knowledge. Am I doing the right thing? How did I get here and can I repeat it?
Situation assessment
Endsley (1995b, p. 36) argues that "it is important to distinguish the term situation awareness, as a state of knowledge, from the processes used to achieve that state. These processes, which may vary widely among individuals and contexts, will be referred to as situation assessment or the process of achieving, acquiring, or maintaining SA." Thus, in brief, situation awareness is viewed as "a state of knowledge," andsituation assessment as "the processes" used to achieve that knowledge. Note that SA is not only produced by the processes of situation assessment, it also drives those same processes in a recurrent fashion. For example, one's current awareness can determine what one pays attention to next and how one interprets the information perceived (Endsley, 2000).
Google has shared the high level concepts of achieving a lower PUE.
1. Measure PUE
You can't manage what you don’t measure, so characterize your data center's efficiency performance by measuring energy use. We use a ratio called PUE - Power Usage Effectiveness - to help us reduce energy used for non-computing, like cooling and power distribution. To effectively use PUE it's important to measure often - we sample at least once per second. It’s even more important to capture energy data over the entire year - seasonal weather variations have a notable affect on PUE.
2. Manage airflow
Good air flow management is fundamental to efficient data center operation. Start with minimizing hot and cold air mixing by using well-designed containment. Eliminate hot spots and be sure to use blanking plates for any unpopulated slots in your rack. We've found a little analysis can pay big dividends. For example, thermal modeling using computational fluid dynamics (CFD) can help you quickly characterize and optimize air flow for your facility without many disruptive reorganizations of your computing room. Also be sure to size your cooling load to your expected IT equipment, and if you are building extra capacity, be sure your cooling approach is energy proportional
…...
What does Google do to determine where it should spend its resources? At some point there is a marginal return or a negative return. It will cost more than what can be saved. On the other hand at Google's scale what may be small for most can be huge for them.
Our 2011 numbers and more are available for closer examination on our data center site. We’ve learned a lot through building and operating our data centers, so we’ve also shared our best practices. These include steps like raising the temperature on the server floor and using the natural environment to cool the data center, whether it’s outside air or recycled water.
The really interesting thing to know is what has Google tried and found not to work. As any good engineer knows many times you learn more from failures than success.
See Inside
How You Learn More from Success Than Failure
The brain may not learn from its mistakes after all
| November 4, 2009 | 15
Have you ever bowled a string of strikes that seems like it came out of nowhere? There might be more to such streaks than pure luck, according to a study that offers new clues as to how the brain learns from positive and negative experiences.
I think good engineers have learned to rewire their brain vs. others.
“Success has a much greater influence on the brain than failure,” says Massachusetts Institute of Technology neuroscientist Earl Miller, who led the research. He believes the findings apply to many aspects of daily life in which failures are left unpunished but achievements are rewarded in one way or another—such as when your teammates cheer your strikes at the bowling lane. The pleasurable feeling that comes with the successes is brought about by a surge in the neurotransmitter dopamine. By telling brain cells when they have struck gold, the chemical apparently signals them to keep doing whatever they did that led to success. As for failures, Miller says, we might do well to pay more attention to them, consciously encouraging our brain to learn a little more from failure than it would by default.
