Modern data centers utilizing dual power designs have further increased reliability of IT systems by ensuring reliable power distribution and delivery. However, improper implementation can negate or diminish the effectiveness of dual power designs. The key is understanding power generation and delivery systems while avoiding these four major design failures.
To standardize a design for dual-powered computer products and simplify the decision making process for choosing computer equipment for mission critical applications, the Uptime Institute published “Fault-Tolerant Power Certification Is Essential When Buying Products for High-Availability.” Unfortunately, simply buying dual-powered gear is not enough to ensure high availability.
To fully understand dual power systems, also referred to as A-B power, it is necessary to understand the power generation and delivery systems responsible for delivering dual power in data centers.
Power Generation and Delivery Systems
Data centers designed and built utilizing Tier IV requirements are by definition “concurrently maintainable,” which means any system or component in the data center may be shut down for maintenance or may fail without affecting the delivery of services to the end user.
In the case of a dual-powered data center, this typically is achieved by delivering at least two power circuits to each cabinet, one from the A power source and one from the B power source.
If every piece of computer equipment is outfitted with dual power supplies (or A-B switches), the load will continue to run normally even if one of the power sources is shut down for maintenance. The circuits must be properly sized and deployed.
Failure to properly design, size and implement dual power infrastructure at the cabinet may lead to one of the following outcomes:
Breaker trip on failover - Improperly sized circuits may become overloaded with the loss of the companion power source thereby causing an overload condition and tripping an upstream circuit breaker.
Breaker trip during restart - Improperly loaded circuits may support a running load in a failover situation, but the restarting of connected servers during single source operation could then trip the upstream circuit breaker (thereby causing momentary starting loads as drives spin up).
Power loss on single corded gear - Some network products or legacy servers may only have single power supplies. This “single corded” gear will require an automatic transfer of A-B switch to protect the device. Failure to do so during the design phase may lead to power loss and resulting downtime at some point in the future.
Excessive power charges through under-utilization - Failing to fully utilize or fully “load” power circuits to their rated capacity may not result in downtime but may drive power subscription costs higher than necessary. Proper power planning and budgeting involves loading every circuit to the proper rated capacity while respecting safety margins.
While dual powered facilities provide concurrent maintainability and high availability when coupled with dual powered devices, proper distribution planning is still required to achieve the ultimate goal of zero downtime.