Making giant data centers more efficient is not as hard as it might seem. By doing so, you will increase operational efficiency and reduce your expenses. Here are a few pieces of advice that will help you make your data center work more efficiently.
It’s all about the power
The three most important characteristics of a data center are its capacity, performance, and reliability. Simultaneously, the smallest amount of attention is devoted to its efficiency, i.e., the quantity of energy it needs to operate correctly. This approach needs to be modified. It can easily lead to finite resources – namely space and energy – being exhausted, with a company that’s outgrown its data center.
According to both the U.S. Department of Energy and Gartner, the cost of electricity represents 25 percent to 40 percent of all operational expenditures in data centers. Gartner also notes that it can cost over $50,000 annually to power a single rack of servers.
Keep it cool
It is not just the servers consuming power: Every kilowatt-hour of electrical energy consumed by IT equipment produces heat that must then be removed by the power-hungry cooling system.
In a typical data center, only about half of the power available is used by the IT equipment, with the rest going mostly to cooling. Much of that power can be reclaimed by eliminating cooling inefficiencies, upgrading the cooling system to allow for variable cooling, and making greater use of outside air.
Replace hard drives with solid-state disks
Although more expensive per Gigabyte to purchase, SSDs consume less power – and generate less heat – than spinning disks. They also offer better performance than high performance (and relatively high energy consuming) 15K disks.
Use storage tiering to increase utilization
Increased utilization drives up your data stored per Watt of power consumed, as illustrated when SSDs are used to replace short-stored disks for high performance. But tiering is not just about increasing energy efficiency for high-performance purposes: moving the appropriate data to increased efficiency, lower performance spinning drives, and moving archive data to offline tape systems are also key.
Use the cloud
Moving some of your storage to the cloud is one way of continuing to increase storage capacity when you run into electrical supply limitations. Cloud storage facilities are way more energy-efficient as well, which is a suitable way to help meet energy consumption or CO2 footprint targets. Their energy costs (which ultimately are passed on to you) are usually lower.
That’s because cloud data centers are often built in places where power and space are cheaper than they would be if the same infrastructure were deployed in your own data center, and because their scale leads to increased efficiency.
Don’t forget deduplication and compression
These storage efficiency techniques also allow you to store more data with less power-hungry hardware or get a greater sufficient capacity with the same energy consumption.
The use of deduping and compression is certainly more prevalent than it was a few years ago. Still, very few corporate data centers are likely to use the two technologies to their maximum potential.
Determine Actual Power Consumption
Older equipment often uses power inefficiently, and newer servers can overload circuits more frequently when incorrectly allocated and aggregated. Using the PAR4 methodology in the Underwriters Laboratories UL2640 standard can maximize server capacity while eliminating the risk of overloading circuits.
Consolidate and Virtualize
Low server utilization is one of the most significant sources of waste in most data centers. Virtualizing the servers can increase overall utilization from around 10 percent (typical of dedicated servers) to between 20 percent and 30 percent, and sometimes over 50 percent with more dynamic management systems. This also reclaims a considerable amount of rack space and stranded power in the process.
Calibrate and Monitor Cold Aisle Temperatures
Experience has demonstrated that the best practice is to adopt a hot/cold aisle configuration and increase the cold aisle inlet temperatures to 80.6°F. However, this can create hot spots that waste power and cause outages, so it is necessary to balance the equipment and calibrate and monitor the cold aisle temperature to maximize cooling efficiency and minimize problems.
Optimize Data Center Space
Data centers built before the advent of server virtualization may be overbuilt for today’s equipment needs, enabling the further reduction of the necessary space for IT equipment and less IT power.
When building a new data center, it’s worth considering a modular design that breaks down the data center into individual modules that can be continually refreshed as part of a more flexible and organic data center design.
Go back to Basics
Like everything else, data centers have a growth cycle, and over time, many data centers turn into a mess. The solution is to get back to basics in the data center. It may seem too elementary, but things like making sure abandoned cables are taken out and racks are sealed off from top to bottom can go a long way when running an efficient data center.
Without basic blocking and tackling in place, the rest of the data center will suffer. Of course, you must always keep in mind the proper data centre safety as well.
