Emerging Power Architectures: New Alternatives for Today’s Data Center

Peter Panfil, VP Global Power, Emerson Network Power

The unprecedented capacity requirements of large scale computing facilities are driving massive investments in data center development. This industry is continually experimenting with new technologies and designs, to push the limits of data center performance while driving down costs.

Some of the designs and technologies that emerge from this development will be specific to the largest data centers, but others will have broad applicability down to the network edge.

This generation of data centers is marked by a philosophy of deploying only “what is needed, when it’s needed” to power a particular application or set of applications quickly and efficiently. In support of this goal, businesses are evaluating new power system architectures and the best location for backup power. Here are several alternative power configurations that improve overall cost and deployment speed while providing the availability levels required for this new generation:

Reserve Bus Architecture Streamlines Redundancy
The 2N or 2N+1 dual-bus architecture has historically been the choice of high-availability data centers. However, in today’s environment this level of redundancy is becoming more difficult to justify. Increasingly, the 2N or 2N + 1 dual-bus architecture is being replaced by various reserve architectures pioneered in large colocation facilities.

The primary alternative is the basic reserve architecture, which creates a redundant configuration, while maintaining fault tolerance and concurrent maintainability through the proper use of static transfer switches (STS). This deployment does complicate maintenance and load deployment compared to traditional 2N architecture, but the economic benefits are compelling.

Variations of the reserve configuration can be considered. The primary difference in the configurations rests with how the client loads achieve power redundancy: either sharing a reserve system, dedicating the reserve system to high-priority clients or accessing unused capacity across multiple UPS modules to create a distributed reserve environment.

Enhance Flexibility with Rack-Based Power Protection
For the developers of many large data centers, speed of deployment has risen to the top of the list of design criteria. They need to bring on capacity quickly and incrementally without compromising capital efficiency.

One way to accomplish faster speed of deployment is to drive power protection to the row and ultimately to the rack, making the rack an autonomous unit that can be brought online without adding to the load of a room or aisle-based power protection system.

Developers can now deploy rack-based power systems to energize DC powered IT equipment inspired by the Open Compute Project. This centralized rack-based power system comprises rectifiers for main power (replacing the AC/DC power supply traditionally embedded in an AC-powered server) supported by lithium ion batteries for power protection (as a point-of-use UPS).

The result is an efficient and economical backup power strategy that provides significant flexibility by enabling capacity to be added one rack at a time. The maturation of lithium ion technology is a key enabler of this strategy, providing a compact backup power source able to support short discharge times and a high discharge cycle count; high power density; and the ability to operate in the increasingly high temperatures that exist in this new generation of data center.

Embrace Simplicity and Efficiency with High-Voltage DC Power
Convergence of voice and data has dictated that telecommunications providers become major data center developers. They bring a long history with 48V DC power, with its proven reliability and efficiency, to the traditional data center. However, 48V DC may not be the Holy Grail for every application, due to the challenges of distributing low voltage DC power.

High voltage 380/400VDC power brings the benefits of DC power to the data center while eliminating the high infrastructure costs associated with distributing lower voltages. Deployed at either the room or row level, the DC UPS is sized to withstand a failure of any rectifier without impacting operation, creating internal redundancy that eliminates the need for redundant configurations common in AC UPS systems.

The biggest challenge facing DC power has been the immature supplier ecosystem, but if just a few of these new developers embrace DC power as they appear to be doing, their scale will create the demand that forces the ecosystem to be mature quickly.

Conclusion
Designers and users of these electrical architectures will want to effectively manage the total power stream within these configurations. That will necessitate the use of advanced critical power management systems to provide real-time monitoring and control of load capacity, switching, power quality and more. This wave of development—and the innovations that emerge from it—will bring new choices to organizations of all sizes, not only in how they acquire capacity, but in how they deploy it and support it within their own facilities.

For more information, see the white paper Data Center Transformation: The impact of Emerging Power Architectures on Today’s Data Centers.