Although the industry already has some reference indicators, the data center managers can be compared with their own data centers. But, Washburn, it is a reminder that these indicators are more suitable for large companies, and often only large companies can benefit from them.
In a way, the larger the data center, the more power it uses to conserve electricity. "For a large number of small companies, the electricity bill has little impact on it, it will focus on other more important places." ”
However, many small companies often do not have the data needed for energy assessment, so there is often no way to compare them with other companies, and it is difficult to know how efficient their data centers are.
"If you're a small company, you have the means to get the assessment data you need, and you can look for a comparison with a company of your own size," Washburn said. "To ensure comparability, data centers should be roughly the same size, and servers, storage devices and network devices are as similar as possible." ”
Microsoft's chief energy and refrigeration architect, Microsoft's representative in the green grid http://www.aliyun.com/zixun/aggregation/16434.html ">christian Belady also believes that the approach described earlier has limitations, Especially when used by smaller companies. However, he believes that even small companies can still use small scale to achieve energy efficiency.
Once the CIO decides to use the data Center for electricity, Belady says, it should also consider computing methods such as PUE, which will ensure that the company is on the right path to energy efficiency, "the industry is growing fast and we can't wait until all the data and metrics are in place." ”
Washburn also agrees with this statement. Whether these metrics and methods are from suppliers or industry organizations, Washburn says, they are a good starting point for energy assessment.
10 conclusions about data center Energy saving
1.90% of companies with large data centers face increased demand for electricity and refrigeration over the next two years.
2. A McKinsey survey of 458 servers for production-oriented data centers showed that 32% (146) of servers were less utilized than the average utilization of 3%. These are the main considerations for energy conservation.
3. By applying virtualization technology, you can reduce the number of servers by up to 65%, but the specifics vary by enterprise.
4. The setting temperature of the air conditioner in the data Center can save energy 4%~5% every 1 degrees.
5. Carbon dioxide emissions in the data center account for about 0.6% of the world's total carbon dioxide emissions. (In comparison, the aviation industry's carbon dioxide emissions are about 0.9%, and the steel industry is about 1%.) )
6. The findings of the relevant institutions show that the use of DC power supply in the data center can increase the power efficiency of 20% and be more reliable than the current AC power supply system, and the energy efficiency will be better in the long run.
7. In 2006, the EPA calculated that the PUE value of the data center was usually higher than 2. Through a series of energy efficiency improvement measures, this value is expected to reach 1.9 by 2011. The EPA also predicts that some of the leading data centers will have a minimum of 1.2 pue value by adopting a variety of advanced it technologies and refrigeration technologies (such as water-cooled and thermoelectric conversion technologies).
8. Google has reported that its 6 self-built data centers have a value of 1.21 pue.
9. The United States can save up to 960 million dollars over the next 6 years by adopting a variety of green energy-saving technologies such as virtualization, server consolidation, and dynamic intelligent refrigeration.
In 2007, Google filed a patent application for a maritime data center, which builds 3 to 7 miles off the coast and uses tidal power to generate electricity.
The content source of this page is from Internet, which doesn't represent Alibaba Cloud's opinion;
products and services mentioned on that page don't have any relationship with Alibaba Cloud. If the
content of the page makes you feel confusing, please write us an email, we will handle the problem
within 5 days after receiving your email.
If you find any instances of plagiarism from the community, please send an email to:
info-contact@alibabacloud.com
and provide relevant evidence. A staff member will contact you within 5 working days.