Google Data Center Efficiency Best Practices -- Full Video

Summary

This video discusses how Google optimizes its data centers to minimize energy and resource consumption. Through innovations like measuring Power Usage Effectiveness (PUE), managing airflow, adjusting temperature settings, utilizing free cooling methods, and optimizing power distribution, Google has achieved significant energy savings. These best practices have allowed their data centers to use half the energy of typical ones, resulting in millions in savings. The video highlights that even small improvements, such as raising temperatures or reducing unnecessary power conversion steps, can lead to impactful efficiency gains for both large and small data centers.

Takeaways

• 💡 Google innovates data center designs to reduce energy and resource usage significantly.
• 💻 Data centers vary from small closets with few machines to large warehouses optimized for IT computing.
• 🌱 Google uses 50% less energy than typical data centers due to years of innovation in efficiency.
• ⚡ Power Usage Effectiveness (PUE) is critical for measuring data center efficiency, with Google achieving a PUE as low as 1.09.
• ❄️ Managing airflow is key to energy efficiency; eliminating hot and cold air mixing improves cooling effectiveness.
• 📈 Thermal modeling helps improve airflow, reducing energy consumption through small, simple changes like adjusting CRAC units.
• 🛠️ Google's use of low-cost containment methods, like meat locker curtains and sheet metal doors, results in significant savings.
• 🌡️ Raising the data center temperature from 72°F to 80°F saves thousands of dollars annually without compromising equipment safety.
• 🌊 Google leverages free cooling techniques, such as sea water cooling and evaporative towers, to reduce mechanical cooling costs.
• 🔋 Optimizing power distribution and reducing conversion stages increases energy efficiency, especially with UPS improvements.

Q & A

What are data centers used for at Google?

Data centers at Google are critical for delivering web services to users. They can range from small rooms with a few machines to large warehouse-scale facilities optimized for power use and IT computing.

What is PUE, and why is it important for data centers?

PUE, or Power Usage Effectiveness, is a ratio that measures how efficiently a data center uses energy. It compares total facility energy to IT equipment energy, helping to identify areas where overhead energy usage, such as cooling, can be reduced.

What was the typical PUE of an enterprise data center in 2006, and how does that compare to Google’s recent PUE?

In 2006, the typical PUE of an enterprise data center was 2.0, meaning for every watt of IT energy consumed, one watt was consumed for overhead. Google’s PUE has improved significantly, with a 12-month average PUE of 1.16 and their lowest data center achieving 1.09.

Why is airflow management crucial in data center efficiency?

Airflow management prevents the mixing of hot and cold air, which helps maintain efficient cooling. Techniques like CFD analysis and simple design changes can dramatically improve airflow, resulting in reduced energy consumption.

What is free cooling, and how does Google implement it?

Free cooling refers to using ambient temperatures, such as outside air, to cool data centers without relying on energy-intensive equipment like chillers. Google uses free cooling at all its data centers and even utilizes sea water in Finland and evaporative towers in Belgium.

What are the benefits of raising the temperature in data centers, according to Google?

By raising the temperature in their data centers from 72°F to 80°F, Google saves thousands of dollars in energy costs annually while ensuring equipment runs safely at higher temperatures, aligning with ASHRAE guidelines.

How does Google minimize energy losses in power distribution?

Google minimizes energy losses by reducing conversion stages in power distribution. Instead of converting AC power multiple times, they directly use DC power, eliminating unnecessary steps and improving efficiency.

What impact does Google’s approach to evaporative cooling have on water usage?

Although evaporative cooling uses water, Google’s efficient use of this method saves more water overall by reducing the water needed for energy production, translating into hundreds of millions of gallons saved annually.

What is the significance of measuring PUE frequently, according to Google?

Frequent PUE measurements allow for more meaningful results, providing accurate data on a data center’s performance. Google recommends measuring PUE as often as possible, ideally every second, to better manage energy efficiency.

What are the key steps Google follows to reduce energy usage in data centers?

Google follows five key steps to reduce data center energy use: 1) Measure PUE, 2) Manage Airflow, 3) Adjust Thermostat, 4) Utilize Free Cooling, and 5) Optimize Power Distribution. These steps are cost-effective and applicable to both small and large data centers.